What can you do with this server?

The md-log-mcp server lets AI coding agents save, manage, and retrieve versioned Markdown reports and assets in the md-log platform for human review and annotation. File Operations * Save — Create or overwrite a .md file; missing folders are auto-created; supports embedded image uploads with asset:// link rewriting; accepts a commit message * Read — Retrieve a file's current content or any specific historical (immutable) version * Append — Append content to an existing file with optimistic concurrency and auto-retry on conflict * Update — Replace a file's full content with optional optimistic locking via expected_version * Move/Rename — Move or rename a .md file while preserving its full version history and annotations * Delete — Soft-delete a file (requires explicit confirm: true as a safety guard) Version Control * List a file's complete immutable version history (newest first), including version number, commit message, author, timestamp, and size Asset Management * Upload images (via base64 or local file path) and receive an asset:// reference to embed in Markdown Folder Management * Create nested folders (mkdir -p), list folder contents, move, rename, and delete folders (with optional cascade: true for recursive soft-delete) Search * Search documents by title (substring match) and body text (full-text, ranked results with snippets) Other Features * Optimistic concurrency control to prevent conflicts * Strict POSIX path validation (enforces .md extension, rejects ../., control characters) * Authentication via Personal Access Tokens (PATs) * Available via local stdio transport (npx) or remote Streamable HTTP transport

How do I use md-log-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@md-log-mcp Save a markdown report summarizing the bug fix in src/main.js" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

md-log-mcp

Official

by md-log

Overview Schema Related Servers Score Discussions

TypeScript

Remote

md-log-mcp

npm version MCP Registry License: MIT Node

Review the report, not the diff. An MCP server that lets your AI coding agent — Claude Code, Claude Desktop, Codex, Cursor — save its work and analysis as immutable, versioned Markdown reports into md-log, a human-in-the-loop review & archive layer for "vibe coding." You then read and stylus-annotate (S-Pen / Apple Pencil) those reports on web, phone, and tablet — every save a new immutable version.

A Model Context Protocol server — two transports, one tool set — that lets Claude Code (and other agents) save .md files — text and embedded screenshots together — straight into md-log, a human-in-the-loop review & archive layer for vibe coding. The recommended way to connect is the hosted remote endpoint (https://mcp.md-log.com/mcp, a URL + your key — no install); a local stdio (npx -y md-log-mcp) transport is the alternative. The agent writes a report by path (my-project/2026-07-07-error-report.md); missing folders are auto-created, images are uploaded and their references rewritten to asset:// links, and every save becomes an immutable new version. The same report is then readable, editable, and stylus-annotatable (S-Pen / Apple Pencil where supported) on a phone or tablet, and on the web.

md-log is a hosted service at https://app.md-log.com — you don't run any server yourself. This package is just the connector: a thin authenticated HTTP client that validates POSIX paths, orchestrates asset uploads, maps errors to stable agent codes, and forwards everything to the hosted md-log service — the single authority for auth, storage, versioning and quota. All you need is a Personal Access Token from the web app.

Stack

@modelcontextprotocol/sdk (TypeScript) — one McpServer (15 tools), two transports.
stdio transport (md-log-mcp) — JSON-RPC over stdin/stdout; the default local mode (so stdout is reserved for the protocol; logs go to stderr). PAT from env.
Streamable HTTP transport (md-log-mcp-http) — the remote mode: agents connect by URL with no local install; the PAT is taken per request from the Authorization header. See Remote (Streamable HTTP) mode.
TypeScript, bundled with tsup to ESM dist/server.js (stdio) + dist/http.js (HTTP). Runtime deps: the MCP SDK and zod (input schemas). Node's built-in fetch/http are the only network layers — no web framework.
PAT auth — a md-log Personal Access Token sent to the backend as Authorization: Bearer.

Related MCP server: logbook-mcp

Requirements

Node 22+
A Personal Access Token (PAT) minted in the md-log web app (Settings → Tokens; shown once)

That's it — the md-log service itself is hosted at https://app.md-log.com; there is nothing to install or self-host.

Tools (15)

Every tool returns dual output — a human-readable content[].text and a machine-readable structuredContent — and validates the POSIX path (NFC-normalize; reject ../., control chars, empty/whitespace segments, backslashes, reserved names; enforce 255-byte name / 1024-byte path limits; require .md for files) before any backend call. All requests hit the base URL in MDLOG_API_BASE_URL (which already includes /api/v1).

Tool	What it does
`save_markdown` ⭐	The headline tool. Create or overwrite a `.md` by path (force last-writer-wins); missing folders auto-created. Optionally uploads embedded images first (each given as `data_base64` or a local `file_path`) and rewrites each `placeholder` in the content to an `asset://<key>` link. Accepts `commit_message` — a recommended 1-2 line change summary shown in the version history.
`upload_asset`	Upload one image (reserve → presigned PUT → complete) and return an `asset://<key>` reference to embed as `![alt](asset://<key>)`. Provide the image as either `data_base64` (inline base64) or `file_path` (a local file the server reads) — exactly one; with `file_path`, `filename` defaults to the basename and `content_type` is inferred from the extension (png/jpg/jpeg/gif/webp/avif).
`append_to_markdown`	Append to an existing file with optimistic concurrency (GET current → concat → conditional PUT with `base_version_no`). Auto-retries once on conflict, then surfaces `CONFLICT`. Accepts `commit_message` — a recommended 1-2 line change summary shown in the version history.
`update_markdown`	Replace a file's content. Pass `expected_version` for optimistic concurrency (mismatch → `CONFLICT`); omit it to force LWW. Accepts `commit_message` — a recommended 1-2 line change summary shown in the version history.
`get_markdown`	Read a file's content by path (materializes inline content or a presigned content URL for large docs). Pass `version` (a `version_no` from `list_versions`) to read an old immutable version.
`list_versions`	List a file's immutable version history, newest first (`version_no`, `commit_message`, author, `registered_at`, size).
`delete_markdown`	Soft-delete a file. Requires `confirm:true` (otherwise `VALIDATION`); resolves the path to a document key first.
`create_folder`	`mkdir -p` — create every missing segment; already-existing folders count as success.
`list_folders`	Return the full folder tree.
`list_files`	List the documents and immediate subfolders inside a folder path.
`search_markdown`	Search by TITLE (substring) + BODY full-text (current versions; whole-word match, ranked, body hits include a snippet).
`move_markdown`	Move and/or rename a `.md` by path (`from_path` → `to_path`); destination folders auto-created; the document KEEPS its key, so version history and reviewers' annotations survive.
`move_folder`	Move a folder (whole subtree) under a new parent (`new_parent_path` empty/omitted = root); parent auto-created; cyclic moves rejected server-side.
`rename_folder`	Rename a folder in place (descendant paths rewritten server-side).
`delete_folder`	Delete a folder. Requires `confirm:true`; by default only an EMPTY folder is deleted — pass `cascade:true` to soft-delete the whole subtree (`rm -r`).

Error codes surfaced to the agent

Backend failures return { isError: true, content:[{type:"text", ...}] } with a mapped code in structuredContent.error.code:

NOT_FOUND · CONFLICT (carries the server head {server_version_no, server_checksum, …} in detail) · UNAUTHORIZED · RATE_LIMITED · QUOTA_EXCEEDED · BACKEND_UNAVAILABLE · VALIDATION · FOLDER_EXISTS (swallowed as success by create_folder) · ERROR.

Authentication

The MCP/PC lane authenticates with a Personal Access Token (mdlog_pat_…) — minted once in the web app's Settings and supplied via env. The client attaches it as Authorization: Bearer <PAT> (plus X-API-Token for compatibility) on every request. The backend is the single source of truth for auth and quota.

Variable	Required	Example	Notes
`MDLOG_API_BASE_URL`	yes	`https://app.md-log.com/api/v1`	The hosted service base, including `/api/v1`. No version suffix is appended; a trailing slash is stripped.
`MDLOG_PAT`	yes	`mdlog_pat_xxxxxxxxxxxxxxxxxxxxxxxx`	Bearer PAT. Store it securely (OS keychain) — never commit it.

The server fails fast at startup with a clear message if either var is missing or the base URL is malformed.

Build

npm install
npm run build      # tsup → dist/server.js (ESM, Node 22)
npm run typecheck  # tsc --noEmit (optional)

Smoke test

scripts/smoke.mjs spawns the built server over stdio (MCP SDK Client + StdioClientTransport), then runs initialize → tools/list → save_markdown (a small report embedding a tiny data: PNG) → get_markdown (reads it back, checks the marker) → search_markdown — printing PASS/FAIL per step and exiting non-zero on any failure. Run it against a live backend with a real PAT:

npm run build
MDLOG_API_BASE_URL="http://localhost:8080/api/v1" \
MDLOG_PAT="mdlog_pat_xxxx" \
node scripts/smoke.mjs        # or: npm run smoke

Connect a client

Mint the PAT in the web app's Settings → Tokens, store it securely, then add md-log to your MCP client. Never commit a PAT.

📄 연결 가이드 (HTML) — md-log.com/guides/customer-guide.html: 웹 앱에서 발급받은 MCP 키(PAT) 로 URL 연결(권장) 또는 npx 로컬 연결 (Claude Code · Desktop · Codex · Cursor).

Recommended — remote (URL), no install

Point your client at the hosted endpoint and pass the PAT as a Bearer header. Nothing to install — no Node.js, no npx. (You don't even need this package for the hosted connection.)

# Claude Code
claude mcp add --transport http md-log https://mcp.md-log.com/mcp \
  --header "Authorization: Bearer mdlog_pat_xxxxxxxxxxxxxxxxxxxxxxxx"

// Cursor / Claude Desktop / any client that takes JSON — the `type` field MUST be "http"
{
  "mcpServers": {
    "md-log": {
      "type": "http",
      "url": "https://mcp.md-log.com/mcp",
      "headers": { "Authorization": "Bearer mdlog_pat_xxxxxxxxxxxxxxxxxxxxxxxx" }
    }
  }
}

Over the remote endpoint, embed images inline (base64); uploading a local image by path (file_path) works only with the local method below.

Alternative — local (stdio via `npx`)

Runs this connector as a local subprocess (needs Node 22+; npx fetches the published package, nothing to build). Use it if you prefer a local process, need local-file (file_path) image uploads, or self-host md-log without a hosted MCP endpoint.

{
  "mcpServers": {
    "md-log": {
      "command": "npx",
      "args": ["-y", "md-log-mcp"],
      "env": {
        "MDLOG_API_BASE_URL": "https://app.md-log.com/api/v1",
        "MDLOG_PAT": "mdlog_pat_xxxxxxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

Mint & secure the PAT. Create it in the web Settings → Tokens (it is shown only once) and keep it out of version control — prefer the OS keychain. On macOS, for example:
security add-generic-password -a "$USER" -s md-log-pat -w "mdlog_pat_xxxx"
export MDLOG_PAT="$(security find-generic-password -a "$USER" -s md-log-pat -w)"
If a PAT leaks, revoke it in the web app and mint a new one.

Remote (Streamable HTTP) mode

The second bin, md-log-mcp-http, serves the same 15 tools over MCP's Streamable HTTP transport — a single POST /mcp endpoint — so agents connect by URL with no local install. Use it when you want to host the connector centrally (a container / small VM behind a TLS reverse proxy) instead of every user running npx.

How it differs from stdio:

PAT per request. The token is not read from env; each request carries its own Authorization: Bearer <mdlog_pat_…> header, so one endpoint serves many users — each with their own md-log token. (MDLOG_PAT is ignored in this mode.)
Stateless. A fresh client + server per request; no session store (replica / autoscale friendly).
No local files. The file_path image source is refused (it would read the server's disk); send images inline as data_base64. Everything else is identical.

Run it

npm run build
MDLOG_API_BASE_URL="https://app.md-log.com/api/v1" \
node dist/http.js            # or: npm run start:http
# → md-log-mcp-http ready — POST http://127.0.0.1:8787/mcp

Configuration (env)

Variable	Required	Default	Notes
`MDLOG_API_BASE_URL`	yes	—	Hosted md-log base, including `/api/v1`.
`MDLOG_HTTP_HOST`	no	`127.0.0.1`	Bind interface. Localhost-only by default; set `0.0.0.0` only behind a TLS reverse proxy.
`MDLOG_HTTP_PORT`	no	`8787`	TCP port.
`MDLOG_HTTP_PATH`	no	`/mcp`	The MCP endpoint path.
`MDLOG_HTTP_ALLOWED_ORIGINS`	no	(none)	Comma-separated browser `Origin` allowlist (DNS-rebinding defense). A request that carries an `Origin` not on the list is `403`d; non-browser clients (no `Origin`) are always allowed.
`MDLOG_HTTP_ALLOWED_HOSTS`	no	(none)	Optional comma-separated `Host` allowlist (extra DNS-rebinding defense).
`MDLOG_HTTP_MAX_BODY_BYTES`	no	`33554432` (32 MiB)	Max request body (base64 images inflate ~33%).

Security posture (per the MCP spec): binds to 127.0.0.1 by default, requires a Bearer token on every MCP request, validates Origin against the allowlist to defeat DNS-rebinding, and caps the body size. A GET /health liveness probe (no auth) returns {"status":"ok"}. GET/DELETE on the MCP endpoint return 405 (stateless: no standalone SSE stream, no session to terminate).

Connect an agent by URL

{
  "mcpServers": {
    "md-log": {
      "type": "http",
      "url": "https://your-host.example/mcp",
      "headers": { "Authorization": "Bearer mdlog_pat_xxxxxxxxxxxxxxxxxxxxxxxx" }
    }
  }
}

Client config shape varies (Claude Code / Cursor / etc.) — the essentials are the endpoint URL and an Authorization: Bearer <PAT> header. Always terminate TLS in front of a public deployment; the PAT rides on every request.

Scripts

npm run build — bundle to dist/server.js (stdio) + dist/http.js (Streamable HTTP) (tsup, ESM, Node 22).
npm run dev — rebuild on change (tsup --watch).
npm run typecheck — tsc --noEmit.
npm run smoke — stdio smoke test against a live backend (needs env + a build).
npm run smoke:http — backend-free HTTP-transport smoke test (handshake + auth/origin/file_path guards).
npm start — run the built stdio server (node dist/server.js).
npm run start:http — run the built HTTP server (node dist/http.js).

Available Tools

15 tools

append_to_markdownAppend to MarkdownA

Append content to the end of an existing .md file using optimistic concurrency (GET current -> concat -> PUT with base_version_no). Auto-retries once on conflict, then surfaces CONFLICT.

ParametersJSON Schema

Name	Required	Description
`path`	Yes	POSIX path to the .md file, e.g. 'reports/2026/error-report.md'. Folders auto-created.
`content`	Yes	Markdown to append. A newline separator is inserted if needed.
`commit_message`	No	A concise 1-2 line summary of WHAT you appended and WHY, written for a human reviewer scanning the version history (stored on the new version, shown next to it on web & mobile). ALWAYS provide this — summarize the appended change yourself (e.g. 'Added the 2026-07 rollback postmortem section').

TDQS

A4.2/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Details the optimistic concurrency pattern (GET->concat->PUT with base_version_no), auto-retry on conflict, and conflict surfacing. Fully discloses internal workflow beyond the action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with core purpose, no wasted words. Efficient and clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers concurrency, retries, and base_version_no. Lacks mention of file existence handling and return value (no output schema). Adequate for a simple tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. Description does not add extra meaning beyond schema; no parameter elaboration.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Append content to the end of an existing .md file', using a specific verb and resource. Distinguishes from siblings like save_markdown (overwrite) and update_markdown (partial update) by the append behavior.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage for appending with concurrency control but does not explicitly contrast with alternatives like save_markdown or update_markdown. No when-not-to-use or alternative guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

create_folderCreate FolderA

Create a folder path, creating every missing parent segment (mkdir -p). Already-existing folders are treated as success.

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	POSIX folder path, e.g. 'reports/2026'. No '.md' suffix.

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Describes key behaviors: recursive parent creation and idempotent handling of existing folders. No annotations, so description carries burden; missing potential edge cases (e.g., invalid path) but adequate for this tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no wasted words, front-loads the main action (create folder path) and key qualifier (mkdir -p).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Simple tool with one parameter; description covers behavior and idempotency. No output schema needed. Complete for intended use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema already provides 100% coverage with a clear description and example. The tool description adds no additional information about the path parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool creates a folder path with mkdir -p behavior, specifically distinguishing from sibling folder operations like delete_folder or move_folder.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Purpose is clear, but no explicit when-to-use or alternatives are given. However, sibling tools are distinct operations, making it unlikely to confuse.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

delete_folderDelete FolderA

Delete a folder. Requires confirm:true (otherwise VALIDATION). By default only an EMPTY folder is deleted (a non-empty one is refused); pass cascade:true to soft-delete the whole subtree — every subfolder and document under it (like rm -r). Documents are soft-deleted (recoverable), but prefer move_folder/move_markdown when reorganizing.

ParametersJSON Schema

Name	Required	Description
`path`	Yes	POSIX path of the folder to delete.
`cascade`	No	true = delete the folder AND everything under it. Default false = refuse unless empty.
`confirm`	Yes	Must be true to actually delete. A safety guard against accidental deletes.

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses required confirm flag, default behavior (only empty folder), cascade effect (like rm -r), and that documents are soft-deleted (recoverable). No annotations present; description carries full burden.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, no redundancy. Front-loaded with 'Delete a folder' then immediate conditions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers behavior, safety, alternatives, and recovery. No output schema, but description explains enough for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage but description adds context: path is POSIX, confirm as safety guard, cascade for non-empty. Incorporates real-world analogy (rm -r).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb 'delete' with specific resource 'folder'. Distinguishes from siblings by mentioning move_folder/move_markdown as alternatives for reorganization.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use (delete folder) and when not (reorganizing, prefer move tools). Provides conditions for cascade and confirm flags.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

delete_markdownDelete MarkdownA

Soft-delete a .md file. Requires confirm:true (otherwise VALIDATION). Resolves the path to a document key, then DELETE /documents/{key}.

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	POSIX path to the .md file, e.g. 'reports/2026/error-report.md'. Folders auto-created.
`confirm`	Yes	Must be true to actually delete. A safety guard against accidental deletes.

TDQS

A3.8/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits. It mentions 'soft-delete' but does not clarify if the deletion is reversible or what the actual side effects are. The mention of a DELETE endpoint suggests a hard delete, creating ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (two sentences) and front-loaded with the core purpose. Every sentence adds meaningful information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description covers the main action and API endpoint. It is mostly complete for a simple delete tool, though it omits details on error handling or restoration of soft-deleted files.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds value by explaining the path resolution to a document key and emphasizing the confirm requirement. This goes beyond the schema's parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Soft-delete a .md file,' providing a specific verb and resource. It distinguishes from sibling tools like delete_folder by targeting only .md files.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description specifies the required confirm:true condition, but does not provide guidance on when to use this tool versus alternatives like move_markdown or update_markdown.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_markdownGet MarkdownA

Read a .md file's content by path. Pass version (a version_no from list_versions) to read an OLD immutable version instead of the current one.

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	POSIX path to the .md file, e.g. 'reports/2026/error-report.md'. Folders auto-created.
`version`	No	Version number to read (see list_versions). Omit for the current version.

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses the core behavior (reading content) and the versioning nuance. No annotations exist, so the description carries full burden; it is fairly transparent but does not mention error handling (e.g., missing file) or authentication requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no wasted words. The most critical information is front-loaded: the tool's purpose and the optional version parameter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool without output schema, the description is nearly complete. It could briefly mention the return format (e.g., file contents as a string) but the current level is sufficient for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% as both parameters are described. The description adds meaningful context by linking version to list_versions and clarifying its optionality, which is not fully explained in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Read a .md file's content by path'), specifying verb and resource. It distinguishes from sibling tools like save_markdown or update_markdown by focusing solely on reading.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use the optional 'version' parameter to read old versions, providing clear context. However, it does not explicitly state when not to use this tool (e.g., for writing) or mention alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_filesList FilesA

List the documents (and immediate subfolders) inside a folder path. Omit path (or pass '' / '/') to list the ROOT folder.

ParametersJSON Schema

Name	Required	Description	Default
`path`	No	POSIX folder path, e.g. 'reports/2026'. Omit or pass '' / '/' to list the ROOT folder.

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses that the tool lists both documents and immediate subfolders, and specifies behavior when path is omitted. No side effects are mentioned, but for a read-only list tool, this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the main purpose, and contains no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description does not explain the return format (e.g., list of names or objects). For full completeness, it should mention what the response contains, though the tool name implies a list.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds an example ('e.g. reports/2026') and explains behavior for omitted/empty path, which adds meaning beyond the schema description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List the documents (and immediate subfolders) inside a folder path.' It specifies the verb 'List' and the resources (documents and subfolders), distinguishing it from sibling 'list_folders' which likely lists only folders.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes usage guidance: 'Omit path (or pass '' / '/') to list the ROOT folder.' This explains a key usage pattern. However, it does not explicitly contrast with siblings like list_folders, though the name implies differentiation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_foldersList FoldersC

Return the full folder tree.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

C2.9/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided and the description does not disclose behavioral traits such as recursion depth, permissions, or performance impact. Full burden falls on description which is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence is concise and front-loaded, but lacks additional structured information that could be included without verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no parameters, the description does not clarify what 'full folder tree' entails, such as structure format, depth, or scope. Incomplete for a potentially large return.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist and schema coverage is 100%, so description adds no additional meaning. Baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool returns the full folder tree, distinguishing it from siblings like list_files and list_versions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives like list_files. Lacks context for usage scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_versionsList VersionsA

List a .md file's immutable version history, newest first (version_no, commit_message, author, registered_at, size). Read an old version's content with get_markdown + version.

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	POSIX path to the .md file, e.g. 'reports/2026/error-report.md'. Folders auto-created.

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It describes the tool as listing immutable version history (read-only), lists return fields, and states ordering. Additive to schema by disclosing behavior and output format.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no wasted words. First sentence front-loads the key action and return details. Second sentence provides a helpful cross-reference to a sibling tool. Efficient and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple single-parameter tool with no output schema, the description is complete: it explains what is returned (5 fields), ordering (newest first), and how to use the output with another tool. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and schema already describes path clearly. Description does not add extra parameter semantics beyond what schema provides, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists version history of a .md file with specific fields and ordering. It distinguishes itself from the sibling get_markdown by directing users to use that tool for reading old versions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context that this is for listing history and points to get_markdown for reading old versions. Lacks explicit when-not-to-use but sufficiently guides usage among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

move_folderMove FolderA

Move a folder (with its whole subtree: documents, versions, annotations) under a new parent. new_parent_path '' or omitted = move to the root. Parent folders are auto-created. Moving a folder into its own subtree is rejected by the server.

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	Current POSIX path of the folder to move.
`new_parent_path`	No	POSIX path of the destination PARENT folder. Empty/omitted = root.

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It discloses that the entire subtree is moved, parent folders are auto-created, and moving into own subtree is rejected. These are critical behavioral traits for a move operation. It does not discuss auth needs or rate limits, but the core behaviors are well covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loading the primary action and then specifying key behaviors. No extraneous information or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, but the description covers the input semantics and constraints (auto-create, subtree move). It might lack return value details, but for a move operation this is acceptable. Overall, it provides sufficient context for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (both parameters described). The description adds meaning beyond the schema: new_parent_path '' or omitted means root, and parent folders are auto-created. This provides concrete usage guidance not present in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Move a folder'), the resource ('folder'), and the scope ('whole subtree: documents, versions, annotations'). This distinguishes it from siblings like rename_folder (rename only) and delete_folder (destructive).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: new_parent_path semantics ('' or omitted moves to root), auto-creation of parent folders, and rejection of moving into own subtree. It lacks explicit comparison to alternatives like move_markdown for individual documents, but the sibling list makes this inferable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

move_markdownMove MarkdownA

Move and/or rename a .md file: from_path -> to_path. Destination folders are auto-created (mkdir -p). The document KEEPS its identity (same document key), so its whole version history and reviewers' annotations survive the move — never re-save + delete to relocate a file. Fails if a different file already occupies to_path.

ParametersJSON Schema

Name	Required	Description	Default
`to_path`	Yes	Target POSIX path (must end in .md). Same folder + new name = rename; new folder + same name = move; both may change at once.
`from_path`	Yes	Current POSIX path of the .md file.

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so description carries full burden. It discloses auto-creation, identity preservation, and failure condition. Missing permissions or idempotency, but covers critical behaviors.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences front-load the purpose, then detail behavior and failure condition. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and medium complexity, description covers purpose, behavior, and edge cases. Could mention return value, but not essential.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and description adds value by explaining the from->to relationship and clarifying move vs. rename semantics beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool moves and/or renames .md files. It distinguishes from sibling tools like move_folder and rename_folder by specifying the file type and the identity-preserving behavior.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context: auto-creates destination folders, preserves document identity and version history, and fails on conflict. However, it does not explicitly state when not to use it versus alternatives like copy+delete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

rename_folderRename FolderA

Rename a folder in place (descendant paths are rewritten automatically; documents, versions and annotations are untouched).

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	Current POSIX path of the folder.
`new_name`	Yes	New folder NAME (a single path segment, not a path).

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Discloses key behavior: descendant paths are rewritten automatically, content untouched. Lacks auth or side-effect details, but for a rename tool it is sufficiently transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence with a parenthetical that adds critical detail. No wasted words; front-loaded with the main action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 2-param tool with no output schema, the description covers behavioral details (path rewriting) and parameter intent. Could mention return value, but completeness is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (both parameters documented in schema). Description adds no extra meaning beyond 'rename in place'. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the action (rename) and resource (folder), and distinguishes from move_folder by noting 'in place'. The parenthetical explains automatic descendant path rewriting, leaving no ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied but not explicitly compared to alternatives like move_folder. No guidance on when not to use, though the description makes the rename behavior clear enough for an agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

save_markdownSave MarkdownA

Save (create or overwrite) a .md file in md-log by path; missing folders are auto-created. Optionally upload embedded images as assets first and rewrite their refs to asset:// links. This is a force-write (last-writer-wins) — the headline agent tool.

ParametersJSON Schema

Name	Required	Description
`path`	Yes	POSIX path to the .md file, e.g. 'reports/2026/error-report.md'. Folders auto-created.
`assets`	No	Embedded images to upload before saving. Each is uploaded, then its `placeholder` in `content` is replaced with the resulting asset:// reference.
`content`	Yes	Full markdown content of the file.
`commit_message`	No	A concise 1-2 line summary of WHAT changed in this version and WHY, written for a human reviewer scanning the version history (it is stored on the version and shown next to it on web & mobile). ALWAYS provide this — summarize the change yourself (e.g. 'Reworked the retention job to batch-delete expired blobs; fixes slow GC'). For a brand-new file, briefly state what the document is.

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It discloses force-write behavior (last-writer-wins), auto-creation of folders, and optional image upload with placeholder replacement. These are key behavioral traits beyond basic mutation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero waste. First sentence states the core action and key features (auto-create folders, optional images). Second sentence adds the force-write note and role. Information is front-loaded and every part earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters, no output schema, and no annotations, the description covers the main workflow, important behaviors, and roles. It lacks error handling or return value info but is adequate for an agent using a write tool with clear side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all 4 parameters (coverage 100%) with detailed descriptions. The description adds high-level context about the workflow (image upload before saving) but does not significantly add meaning to individual parameters beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it saves (creates or overwrites) a .md file by path, with folder auto-creation and optional image upload. It distinguishes itself from sibling tools like append_to_markdown by calling itself 'the headline agent tool' for writing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

While not explicitly saying when not to use, the description positions this as the primary write tool ('headline agent tool') and mentions it's a force-write. The sibling update_markdown exists but the name 'save' implies create/overwrite, giving implicit guidance. Missing explicit comparison to alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_markdownSearch MarkdownA

Search documents by TITLE (substring) and BODY (full-text over current versions; whole-word match, ranked, body hits carry a bolded snippet). Use it to find a prior report by its content or name.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes	Search query; matched against document titles (substring) and body text (words).

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully discloses search behavior: title substring, body whole-word match, ranking, and bolded snippets. However, it omits details like case sensitivity, pagination, or result limits, which would further aid the agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences only, each serving a clear purpose: first explains behavior, second provides usage guidance. No redundant or vague phrasing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with one parameter and no output schema, the description adequately covers search scope and result features (bolded snippet). It could mention result structure or limits, but overall is fairly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already covers parameter semantics with 100% coverage ('Search query; matched against document titles (substring) and body text (words).'). The description adds minimal semantic value beyond usage context, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'search' and resource 'documents', and details the matching behavior (title substring, body full-text whole-word, ranked, bolded snippet). It distinguishes from all sibling tools, none of which perform search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use it to find a prior report by its content or name', providing clear context for when to use. It does not mention exclusions or alternatives, but no other search tool exists among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

update_markdownUpdate MarkdownA

Replace the content of an existing .md file. Pass expected_version for optimistic concurrency (mismatch -> CONFLICT); omit it to force last-writer-wins.

ParametersJSON Schema

Name	Required	Description
`path`	Yes	POSIX path to the .md file, e.g. 'reports/2026/error-report.md'. Folders auto-created.
`content`	Yes	New full markdown content.
`commit_message`	No	A concise 1-2 line summary of WHAT changed in this version and WHY, written for a human reviewer scanning the version history (stored on the version, shown next to it on web & mobile). ALWAYS provide this — diff the old and new content in your head and summarize the change yourself (e.g. 'Corrected the JWT TTL table and added the tablet 90d refresh note').
`expected_version`	No	Version you based your edit on. Omit to force-overwrite (LWW).

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description is expected to disclose behavioral traits. It covers the concurrency behavior well but omits details on required authentication, error cases (e.g., file not found), and side effects beyond the conflict scenario. The schema mentions 'Folders auto-created' but the description does not.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, each earning its place. The first sentence states the core purpose, and the second provides crucial usage guidance. No superfluous text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and no output schema, the description covers the main behavioral nuance (concurrency) but lacks information about return values, prerequisites, and error states beyond the conflict case. For a mutation tool, more detail on what happens upon success or failure would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, setting a baseline of 3. The description adds context on the concurrency semantics for 'expected_version' (mismatch -> CONFLICT), which is slightly more detailed than the schema's description. No additional meaning is added for other parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses 'Replace the content of an existing .md file', specifying the verb 'replace' and the resource 'content of an existing .md file'. This clearly differentiates from the sibling tool 'append_to_markdown', which appends rather than replaces.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly advises when to use the 'expected_version' parameter for optimistic concurrency and when to omit it for last-writer-wins. However, it does not provide explicit guidance on when to prefer this tool over alternatives like 'append_to_markdown' or 'save_markdown'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

upload_assetUpload AssetA

Upload a single image as an asset (reserve -> presigned PUT -> complete) and return an 'asset://' reference you can embed in markdown image syntax: alt . Provide the image as EITHER data_base64 (inline base64) OR file_path (a local file to read) — exactly one.

ParametersJSON Schema

Name	Required	Description
`path`	Yes	The .md document path this asset is associated with (used for quota/scoping).
`filename`	No	Original file name. Optional with `file_path` (defaults to its basename).
`file_path`	No	Absolute or relative local filesystem path to the image file to read and upload. Provide EITHER this OR `data_base64`, not both.
`data_base64`	No	Base64-encoded raw image bytes. Provide EITHER this OR `file_path`, not both.
`content_type`	No	MIME type, e.g. 'image/png'. Optional with `file_path` when the extension is recognized (png/jpg/jpeg/gif/webp/avif).

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It reveals the internal 3-step process (reserve -> presigned PUT -> complete) and the return format. This is good transparency, though it could mention potential side effects like overwriting an existing asset with the same key.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the purpose and process, then details parameters. Every part adds value with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the 5 parameters (100% schema coverage), no output schema, and moderate complexity, the description is mostly complete. It explains the return value and process. However, it lacks guidance on error cases (e.g., what happens if both image sources are provided) and does not specify if the asset key is auto-generated or derived from the filename.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds significant value by explaining the process, the mutual exclusivity of file_path/data_base64, and the return format. It clarifies the 'path' parameter's role as a document association for quota/scoping, which is not in the schema's parameter description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Upload a single image as an asset' and specifies the resource (an image asset). It distinguishes from sibling tools (e.g., save_markdown, append_to_markdown) by focusing on image upload and returning a markdown-compatible reference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use the tool: for embedding an image in markdown. It explicitly states the mutually exclusive requirement of `data_base64` or `file_path`. However, it does not explicitly state when not to use it or provide alternatives for other asset types.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

15 tool updatesv1.0.8Jul 14, 2026
- First observedappend_to_markdown
- First observedcreate_folder
- First observeddelete_folder
- First observeddelete_markdown
- First observedget_markdown
- First observedlist_files
- First observedlist_folders
- First observedlist_versions
- First observedmove_folder
- First observedmove_markdown
- First observedrename_folder
- First observedsave_markdown
- First observedsearch_markdown
- First observedupdate_markdown
- First observedupload_asset

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0

Disambiguation5/5

Each tool targets a distinct operation: content manipulation, folder management, listing, search, asset upload, and concurrency control. No overlap in purpose.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (e.g., save_markdown, delete_folder, list_versions).

Tool Count5/5

15 tools cover the domain comprehensively without bloat. Each tool serves a clear need for managing markdown files and folders with versioning.

Completeness4/5

Covers full CRUD for documents and folders, plus listing, search, version history, assets, and concurrency. Minor gaps: no explicit tool to restore a previous version, but that can be done via get_markdown (old version) and save_markdown.

Maintenance

ActivitySlowing

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

hjarni AOAuth
com.hjarni
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Note Taking Workplace & Productivity
3
MarkupBase AOAuth
com.markupbase.mcp
MarkupBase turns AI-generated Markdown and HTML into durable, versioned artifacts that people can review and discuss. Its MCP server lets agents publish new versions, preserve contextual comments, include hosted images, and respond to feedback through secure account-linked identities, creating a clear human review boundary without requiring real-time editing.
Content Management Systems RAG Systems Workplace & Productivity
122
Agentage MemoryOAuth
io.agentage
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Knowledge & Memory File Systems
2
gread A
io.github.NitroRCr
An MCP server that gives your AI access to the source code and docs of all public github repos
Version Control Code Analysis Documentation Access
5361

Related MCP Servers

repro-mcp
Research & Data Developer Tools
ABindoff
A
license
Not graded
quality
D
maintenance
An MCP server that logs AI-assisted scientific computing sessions, capturing prompts, responses, decisions, and environment snapshots to human-readable markdown files for reproducibility.
Updated 4 months ago (2026-05-21 04:39 UTC)
MIT
logbook-mcp
Note Taking Monitoring
aether-technologies
A
license
Not graded
quality
D
maintenance
A local MCP server for AI agents to log activities, query logs, and leave notes for each other, featuring a web UI and REST API.
Updated 5 months ago (2026-03-27 17:02 UTC)
MIT
Engram
Agent Orchestration Knowledge & Memory
tomcat65
A
license
Not graded
quality
D
maintenance
A self-hosted MCP server enabling multiple AI coding agents to share state, preserve context across sessions, and coordinate with each other.
Updated 2 months ago (2026-07-17 02:30 UTC)
40
Apache 2.0
SecondBrain
Knowledge & Memory RAG Systems Note Taking
no-carve-only-pizza
A
license
A
quality
C
maintenance
A local-first MCP server that provides a shared Markdown-based memory for AI coding agents, enabling cross-agent context persistence via tools like memory_search and memory_capture.
Updated a month ago (2026-08-10 21:34 UTC)
10
1
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/md-log/md-log-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

md-log-mcp

Stack

Requirements

Tools (15)

Error codes surfaced to the agent

Authentication

Build

Smoke test

Connect a client

Recommended — remote (URL), no install

Alternative — local (stdio via npx)

Remote (Streamable HTTP) mode

Run it

Configuration (env)

Connect an agent by URL

Scripts

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

Alternative — local (stdio via `npx`)