It helps an agent avoid relying on stale repository facts by linking information to sources and verifying it at the point of use.

verified-repo-memory — MCP server by cognitivemyriad

verified-repo-memory

verified-repo-memory is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from cognitivemyriad/mcp-verified-repo-memory. Its token cost is not measured, scanned A, original, MIT.

A local repository-memory service that stores project information with citations and rechecks it when needed. It uses a time-to-live, meaning stored information can expire, and requires four environment variables to run.

In plain words

What is it for?: Use it to retrieve repository-specific context with citations and just-in-time checks, after configuring its data directory, expiry, file-size, and secret-scanning settings.
Why use it?: It helps an agent avoid relying on stale repository facts by linking information to sources and verifying it at the point of use.

Written for no agent in particular: it speaks MCP, so any client can run it.

Good fit Use it to retrieve repository-specific context with citations and just-in-time checks, after configuring its data directory, expiry, file-size, and secret-scanning settings.

Compare 6 mcp servers from other repositories ↓

Install with agentmods

npx agentmods add mcp/cognitivemyriad/mcp-verified-repo-memory/verified-repo-memory

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/cognitivemyriad/mcp-verified-repo-memory

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/cognitivemyriad/mcp-verified-repo-memory/verified-repo-memory/github.svg)](https://agentmods.dev/mcp/cognitivemyriad/mcp-verified-repo-memory/verified-repo-memory)

Your own site

<a href="https://agentmods.dev/mcp/cognitivemyriad/mcp-verified-repo-memory/verified-repo-memory"><img src="https://agentmods.dev/badge/mcp/cognitivemyriad/mcp-verified-repo-memory/verified-repo-memory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/cognitivemyriad/mcp-verified-repo-memory/verified-repo-memory"><img src="https://agentmods.dev/badge/mcp/cognitivemyriad/mcp-verified-repo-memory/verified-repo-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

verified-repo-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 15 lines

What it actually says

{
  "verified-repo-memory": {
    "command": "npx",
    "args": [
      "-y",
      "@cognitivemyriad/vrm-local"
    ],
    "env": {
      "VRM_TTL_DAYS": "",
      "VRM_DATA_DIR": "",
      "VRM_MAX_FILE_BYTES": "",
      "VRM_SECRET_SCAN": ""
    }
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 15 lines scan A 4195953b81f4

Subscribe to this mod's changes

verified-repo-memory is an MCP server published in the GitHub repository cognitivemyriad/mcp-verified-repo-memory (1 stars, last pushed 8mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context agent agentic-ai agents ai ai-agents coding-agent

verified-repo-memory next to 6 mcp servers from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
verified-repo-memorycognitivemyriad/mcp-verified-repo-memory	MCP server	1	8mo ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
shared-sessionsAgentWorkforce/relay	MCP server	1.1k	today	Apache-2.0	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
nightgate-mcpODATANO/NIGHTGATE-MCP	MCP server	3	8d ago	Apache-2.0	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
agent-memory-osyamantaka520/Agent-Memory-OS	MCP server	9	1mo ago	Apache-2.0	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
open-designHelixDevelopment/code	MCP server	2	25d ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
claude-flowamangit1314/repo-rag	MCP server	0	1mo ago	none	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
claude-memory-mcpTim-Fischer-zh/claude-memory	MCP server	4	7mo ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode