What does 'just-in-time verification' mean in this MCP server?

The server validates stored repository data against the actual codebase when you retrieve it, ensuring citations remain accurate. If data has exceeded its TTL (set via VRM_TTL_DAYS), it flags or refreshes the information automatically.

How do I set up Verified Repo Memory locally?

Install via `npx @cognitivemyriad/vrm-local@0.1.2`. Configure VRM_TTL_DAYS (1–365 days), VRM_DATA_DIR for storage location, VRM_MAX_FILE_BYTES for file size limits, and VRM_SECRET_SCAN to enable secret detection.

Can this server prevent secrets from being stored in repository memory?

Yes. Set VRM_SECRET_SCAN to 'on' to enable secret scanning. This prevents API keys, tokens, and credentials from being cached in your repository memory.

What happens when stored repository data expires?

Data older than VRM_TTL_DAYS is marked stale. The server will flag it as unverified or prompt re-validation against the live repository on next retrieval, preventing outdated context from being used.

Is there a file size limit for repository parsing?

Yes. VRM_MAX_FILE_BYTES controls the maximum file size the server will parse. Adjust this if you're working with large codebases or want to exclude massive generated files from memory.

MCP ServerSTDIOOfficialv0.1.2

Verified Repo Memory MCP Server

Store and retrieve repository context with automatic freshness verification and citations. Developers use this to maintain accurate, time-bounded memory of codebases without stale information polluting AI conversations.

io.github.cognitivemyriad/verified-repo-memory

Try MCP with AI models View source

Hosted URL

Local install

Transport

STDIO

Auth

No auth required

What the Verified Repo Memory MCP server does

How models use it and what it is built for.

Connect to Verified Repo Memory

Local install — runs as a subprocess.

npx @cognitivemyriad/vrm-local@0.1.2

Environment variables

Configuration this server reads at startup.

VRM_TTL_DAYS
Default TTL in days (1-365).
VRM_DATA_DIR
Override data dir path.
VRM_MAX_FILE_BYTES
Max file parsing size bytes.
VRM_SECRET_SCAN
Enable secret scan (on/off).

Resources

Where to find authoritative docs and source for Verified Repo Memory.

Source repository

Example prompts for Verified Repo Memory

Paste any of these into Agent Studio after connecting Verified Repo Memory.

Store the current repository structure and main dependencies with a 7-day TTL
Retrieve verified facts about this repo's API endpoints with citation sources
Check if stored repository memory has expired and refresh it
What configuration options does VRM_SECRET_SCAN enable for this server?

Verified Repo Memory MCP server — FAQ

Common questions about connecting and running Verified Repo Memory.

What does 'just-in-time verification' mean in this MCP server?
The server validates stored repository data against the actual codebase when you retrieve it, ensuring citations remain accurate. If data has exceeded its TTL (set via VRM_TTL_DAYS), it flags or refreshes the information automatically.
How do I set up Verified Repo Memory locally?
Install via `npx @cognitivemyriad/vrm-local@0.1.2`. Configure VRM_TTL_DAYS (1–365 days), VRM_DATA_DIR for storage location, VRM_MAX_FILE_BYTES for file size limits, and VRM_SECRET_SCAN to enable secret detection.
Can this server prevent secrets from being stored in repository memory?
Yes. Set VRM_SECRET_SCAN to 'on' to enable secret scanning. This prevents API keys, tokens, and credentials from being cached in your repository memory.
What happens when stored repository data expires?
Data older than VRM_TTL_DAYS is marked stale. The server will flag it as unverified or prompt re-validation against the live repository on next retrieval, preventing outdated context from being used.
Is there a file size limit for repository parsing?
Yes. VRM_MAX_FILE_BYTES controls the maximum file size the server will parse. Adjust this if you're working with large codebases or want to exclude massive generated files from memory.

Skip the local setup — run MCP in your browser

MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.

Open Agent Studio