Skip to main content
Glama

SiteGPT Docs

by io.github.sitegpt

query_docs_filesystem_site_gpt_docs

Read-onlyIdempotent

Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at / that contains ONLY the SiteGPT Docs documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks.

This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its .mdx path (e.g. /quickstart.mdx, /api-reference/create-customer.mdx) to head or cat. To search the docs with exact keyword or regex matches, use rg. To understand the docs structure, use tree or ls.

Workflow: Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path.

Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run --help on any command for usage.

Each call is STATELESS: the working directory always resets to / and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with && or pass absolute paths (e.g., cd /api-reference && ls or ls /api-reference). Do NOT assume that cd in one call affects the next call.

Examples:

  • tree / -L 2 — see the top-level directory layout

  • rg -il "rate limit" / — find all files mentioning "rate limit"

  • rg -C 3 "apiKey" /api-reference/ — show matches with 3 lines of context around each hit

  • head -80 /quickstart.mdx — read the top 80 lines of a specific page

  • head -80 /quickstart.mdx /installation.mdx /guides/first-deploy.mdx — read multiple pages in one call

  • cat /api-reference/create-customer.mdx — read a full page when you need everything

  • cat /openapi/spec.json | jq '.paths | keys' — list OpenAPI endpoints

Output is truncated to 30KB per call. Prefer targeted rg -C or head -N over broad cat on large files. To read only the relevant sections of a large file, use rg -C 3 "pattern" /path/file.mdx. Batch multiple file reads into a single head or cat call whenever possible.

When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the .mdx extension. For example, /quickstart.mdx becomes /quickstart and /api-reference/overview.mdx becomes /api-reference/overview.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
commandYesA shell command to run against the virtualized documentation filesystem (e.g., `rg -il "keyword" /`, `tree / -L 2`, `head -80 /path/file.mdx`).

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A5/5.0
Behavior5/5

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

Even though annotations already declare readOnlyHint, idempotentHint, and destructiveHint, the description adds substantial non-obvious behavior: the filesystem is virtualized/in-memory, not a real machine, no network writes or process control, each call is stateless, output is truncated to 30KB, and paths must be converted to URLs in responses. This goes well beyond what the annotations convey and contains no contradictions.

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 long but information-dense, front-loading the critical sandbox/staleness constraints before command examples and output handling. Every section serves a purpose: the distinction from a real shell, the workflow, the stateless warning, concrete examples, truncation guidance, and URL conversion.

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?

Given the tool has one parameter, no output schema, and moderate operational complexity, the description covers all necessary invocation contexts: what the filesystem contains, which commands work, how to search, how to read pages, how to batch reads, output limits, and how to reference results in responses. Nothing essential is missing.

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?

Although the schema covers the single `command` parameter 100%, the description dramatically enhances semantic understanding by listing supported commands, providing illustrative examples for tree, rg, head, cat, and jq, and explaining how `cd` behaves across calls. For an agent choosing command syntax, this is far more useful than the schema alone.

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 opens with a precise verb-resource pair: "Run a read-only shell-like query against a virtualized, in-memory filesystem" containing only documentation pages and OpenAPI specs. It explicitly distances the tool from a real shell, and its workflow note contrasts it with the sibling search tool, making the tool's specific role unmistakable.

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?

The description gives explicit selection guidance: use the search tool for broad/conceptual queries, and use this tool for exact keyword/regex matching, structural exploration, or reading full pages. It also tells the agent how to compensate for statelessness (use absolute paths or `&&` chaining), which is the kind of practical usage guidance an agent needs.

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

All SiteGPT Docs toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0
Disambiguation4/5

query_docs_filesystem and search_site_gpt_docs both retrieve documentation content, but their descriptions make the distinction clear: one is exact/regex/filesystem-oriented reading, the other is broad semantic search. submit_feedback is completely distinct.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case: query_docs_filesystem, search_site_gpt_docs, submit_feedback. The naming is uniform and predictable despite the long first name.

Tool Count5/5

Three tools is well-scoped for a documentation server: two complementary retrieval methods and one feedback channel. Every tool has a clear purpose and none are redundant or excessive.

Completeness5/5

The tool surface covers the full documentation workflow: exploring/searching, reading specific pages, and reporting issues. No obvious gaps exist for the stated purpose of interacting with SiteGPT Docs.

Resources