Skip to main content
Glama
cognitivemyriad

Verified Repo Memory MCP

by cognitivemyriad
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

Verified Repo Memory Banner

Verified Repo Memory MCP v0.1.0

CI TypeScript License: MIT

Stale-proof repository memory with citations + just-in-time verification + TTL (repo-scoped).

An MCP server providing "safe memory" for AI coding agents. Memories are scoped per repository, backed by code citations, and verified just-in-time so an agent never receives stale information when the underlying code has changed.

Quickstart

Run via npx:

npx -y vrm-local --repo /path/to/repo

Tools

  • vrm_store: Store a new memory with file citations.

  • vrm_search: Search for candidate memories by keywords.

  • vrm_retrieve: JIT-verify candidates and return only valid memories. (Main tool for agents)

  • vrm_list: List memories by status (valid, stale, missing).

  • vrm_forget: Manually delete a memory.

Example I/O

Store: Input:

{
  "subject": "API version sync",
  "fact": "When changing API version, update client/server/docs together.",
  "citations": [{ "path": "src/api.ts", "startLine": 10, "endLine": 15 }]
}

Output:

{
  "stored": true,
  "memoryId": "uuid-...",
  "expiresAt": "2026-03-21T00:00:00Z"
}

Retrieve: Input:

{ "query": "API version" }

Output:

{
  "query": "API version",
  "valid": [ ... ],
  "stats": { "verified": 1, "validCount": 1 }
}

How it works

graph TD
    A[Agent] -->|Store Fact + Citation| B(Verified Repo Memory)
    B --> C{Save to Disk}
    C -->|Hash Code Snippet| D[(memories.json)]
    
    A -->|Retrieve Fact| B
    B --> E{JIT Verification}
    E -->|Check File Hash| F{Unchanged or Relocated?}
    F -->|Yes| G[Return VALID Memory]
    F -->|No| H[Return STALE/MISSING]

  1. Citations: Every fact is linked to a file path and a line range. The exact code snippet is hashed and saved.

  2. JIT Verification: Before returning a memory to the agent in vrm_retrieve, the server checks the physical file. If the snippet has moved, it relocates the citation. If it has been changed or deleted, the memory is marked STALE/MISSING and omitted from the results.

  3. TTL (Time-To-Live): Memories expire automatically (default 28 days) unless they are successfully retrieved and utilized, which extends their life.

Data location

Data is strictly repo-scoped and saved in: <repoRoot>/.verified-repo-memory/

This includes memories.json and a fingerprint/metadata file to prevent accidental cross-repo pollution. Add this directory to your .gitignore.

Security

  • No Network Transmissions: This is a stdio local-only server without HTTP calls.

  • Path Security: Disallows any path traversal (../) out of the repository root, as well as accessing .git/ or .verified-repo-memory/.

  • No Stdout Pollution: Strict logging only to stderr.

  • Secret Scan: Built-in heuristic secret scanning to reject memories that look like API keys/private keys (can be disabled via --no-secret-scan).

Usage with Claude

Claude Desktop

To add this server to the Claude Desktop app, edit your configuration file:

  • On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • On Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the following configuration:

{
  "mcpServers": {
    "verified-repo-memory": {
      "command": "npx",
      "args": [
        "-y",
        "vrm-local",
        "--repo",
        "/absolute/path/to/your/repo"
      ]
    }
  }
}

Claude Code

To add this server to Claude Code using stdio transport:

claude mcp add mcp-verified-repo-memory --transport stdio -- npx -y vrm-local

Note for Windows users: You may need to prepend cmd /c to the command:

claude mcp add mcp-verified-repo-memory --transport stdio -- cmd /c npx -y vrm-local

Publishing to MCP Registry

To publish this server to the official registry:

  1. Initialize publisher: npx @modelcontextprotocol/publisher init

  2. Login: npx @modelcontextprotocol/publisher login github

  3. Publish: npx @modelcontextprotocol/publisher publish

Note: Once published, the version in server.json is immutable and cannot be changed for that release.

Available Tools

5 tools
vrm_forgetC

Manually delete a memory by ID.

ParametersJSON Schema
NameRequiredDescriptionDefault
memoryIdYes
hardDeleteNo

TDQS

C2.8/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a deletion operation (implying mutation/destructive), but doesn't clarify whether deletion is permanent, reversible, requires specific permissions, or has side effects. The 'hardDelete' parameter suggests deletion behavior varies, but the description doesn't explain this. For a mutation tool with zero annotation coverage, this leaves significant behavioral gaps.

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 extremely concise at just 5 words, front-loading the core action ('Manually delete') immediately. Every word earns its place - 'Manually' distinguishes from automatic deletion, 'delete' specifies the action, 'a memory' identifies the resource, and 'by ID' indicates the key parameter. No wasted words or redundant information.

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?

For a deletion tool with 2 parameters, 0% schema coverage, no annotations, and no output schema, the description is inadequate. It doesn't explain what constitutes a 'memory' in this system, whether deletion affects related data, what confirmation or response to expect, or the implications of the hardDelete parameter. The agent lacks crucial context to use this tool safely and effectively.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate for undocumented parameters. It mentions 'by ID' which maps to the memoryId parameter, but doesn't explain the UUID format requirement. It completely ignores the 'hardDelete' parameter and its default value (true), leaving the agent to guess what this boolean controls. The description adds minimal value beyond what's obvious from parameter names.

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

Purpose4/5

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

The description clearly states the action ('Manually delete') and target resource ('a memory by ID'), making the purpose immediately understandable. It distinguishes itself from sibling tools (list, retrieve, search, store) by focusing on deletion rather than querying or storage operations. However, it doesn't specify what type of memory system this operates on or the broader context.

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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (like needing to know a memory ID first), when deletion is appropriate versus other operations, or what happens after deletion. The agent must infer usage from the tool name and sibling tools alone.

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

vrm_listC

List memories by status.

ParametersJSON Schema
NameRequiredDescriptionDefault
statusNoall
limitNo
verifyNo

TDQS

C2.6/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden but discloses minimal behavioral traits. It implies a read-only operation ('List') but doesn't address pagination, rate limits, authentication needs, or what happens when 'verify' is true. The description doesn't contradict annotations (none exist), but it's insufficient for a tool with parameters.

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 extremely concise—a single sentence with no wasted words. It's front-loaded with the core purpose. However, this conciseness comes at the cost of completeness, as noted in other dimensions.

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?

Given the tool has 3 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain return values, error conditions, or how parameters interact. For a list operation with filtering and verification options, more context is needed to guide effective use.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate but adds minimal value. It mentions 'status' filtering, which aligns with one parameter, but doesn't explain the meaning of status values (valid/stale/missing), the purpose of 'limit' or 'verify', or how they affect results. This leaves key parameters undocumented.

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

Purpose3/5

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

The description 'List memories by status' clearly states the verb ('List') and resource ('memories'), but it's vague about scope and doesn't differentiate from sibling tools like vrm_search or vrm_retrieve. It specifies filtering by 'status' but lacks context about what 'memories' are in this system.

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?

The description provides no guidance on when to use this tool versus alternatives like vrm_search or vrm_retrieve. There's no mention of prerequisites, use cases, or exclusions. The agent must infer usage from the tool name and parameters alone.

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

vrm_retrieveC

JIT-verify candidates and return valid memories.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes
limitNo
includeStaleNo
touchNo

TDQS

C2.6/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'JIT-verify' (just-in-time verification) and 'return valid memories', but doesn't explain what verification entails, whether it's a read-only operation, what 'stale' memories are, or what 'touch' does. For a tool with 4 parameters and no annotation coverage, this leaves significant behavioral gaps.

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 extremely concise at just one sentence with no wasted words. It's front-loaded with the core purpose. While it may be too brief for completeness, it earns full marks for conciseness as every word contributes meaning.

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?

Given the complexity (4 parameters, no annotations, no output schema, 0% schema coverage), the description is incomplete. It doesn't explain what the tool returns, how verification works, or the semantics of key parameters like 'includeStale' and 'touch'. For a memory retrieval tool with multiple configuration options, this leaves too much undefined.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate by explaining parameters. It mentions 'candidates' (implied to relate to the 'query' parameter) and 'valid memories' (implied output), but doesn't clarify what 'query' should contain, what 'limit' controls, what 'includeStale' means, or what 'touch' does. The description adds minimal value beyond the bare schema.

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

Purpose3/5

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

The description states the tool's purpose as 'JIT-verify candidates and return valid memories', which is somewhat vague. It specifies a verb ('verify') and resource ('memories'), but doesn't clearly distinguish what 'candidates' are or how this differs from sibling tools like vrm_search or vrm_list. The purpose is understandable but lacks specificity.

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?

The description provides no guidance on when to use this tool versus alternatives like vrm_search or vrm_list. There's no mention of prerequisites, context, or exclusions. The agent must infer usage from the tool name and parameters alone, which is insufficient for optimal tool selection.

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

vrm_storeC

Store a memory with file citations. Snippets are auto-extracted.

ParametersJSON Schema
NameRequiredDescriptionDefault
subjectYes
factYes
reasonNo
tagsNo
ttlDaysNo
citationsYes

TDQS

C2.7/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'Snippets are auto-extracted' which adds some context about automation. However, it lacks critical details: whether this is a write operation (implied by 'store'), permissions needed, rate limits, error handling, or what happens to existing memories. For a tool with 6 parameters and no annotations, this 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.

Conciseness5/5

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

The description is extremely concise with two short sentences that are front-loaded. 'Store a memory with file citations' states the core purpose immediately, and 'Snippets are auto-extracted' adds a key feature. There is zero wasted language, making it efficient for an AI agent to parse.

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?

Given the complexity (6 parameters, no annotations, no output schema), the description is incomplete. It doesn't explain what a 'memory' entails, how citations work, what the tool returns, or error conditions. For a storage tool with multiple parameters and siblings, more context is needed to guide proper usage.

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

Parameters1/5

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

Schema description coverage is 0%, so the description must compensate by explaining parameters. It mentions 'file citations' which relates to the 'citations' parameter, and 'memory' which might relate to 'subject' or 'fact'. However, it doesn't explain any of the 6 parameters (subject, fact, reason, tags, ttlDays, citations) or their purposes. The description adds minimal value beyond the schema.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'Store a memory with file citations' specifies the verb (store) and resource (memory). It distinguishes from siblings like vrm_list (list) and vrm_retrieve (retrieve). However, it doesn't explicitly differentiate from vrm_search, which might also involve memory operations.

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?

The description provides no guidance on when to use this tool versus alternatives like vrm_list or vrm_search. It mentions 'Snippets are auto-extracted' which hints at a feature, but doesn't clarify use cases, prerequisites, or exclusions. No explicit when/when-not instructions are present.

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.

  1. 5 tool updatesv0.1.0
    • First observedvrm_forget
    • First observedvrm_list
    • First observedvrm_retrieve
    • First observedvrm_search
    • First observedvrm_store
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: forget deletes, list enumerates, retrieve verifies and returns, search finds candidates, and store creates. The descriptions explicitly differentiate them, such as distinguishing retrieve (with JIT verification) from search (fast, no verification).

Naming Consistency5/5

All tools follow a consistent 'vrm_' prefix and verb_noun pattern (e.g., vrm_forget, vrm_list, vrm_retrieve, vrm_search, vrm_store). This predictable naming makes it easy for agents to understand and select tools without confusion.

Tool Count5/5

With 5 tools, the set is well-scoped for a memory management server, covering core operations like store, retrieve, search, list, and forget. Each tool earns its place, providing a complete yet manageable surface without bloat or thinness.

Completeness5/5

The tool surface offers complete CRUD/lifecycle coverage for memory management: store (create), retrieve/read (with verification), search (find), list (enumerate), and forget (delete). There are no obvious gaps, enabling agents to handle all typical workflows without dead ends.

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

Latest Blog Posts

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/cognitivemyriad/verified-repo-memory-mcp'

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