agentmods.dev

graphmem-mcp

graphmem-mcp is an MCP server for Claude Code, Codex, Cursor from Sathvik-1007/GraphMem-MCP. Its token cost is not measured, scanned A, original, MIT.

A local server that gives an AI coding agent a persistent knowledge graph: connected records of information that can be searched and followed across sessions. It uses local text embeddings, which help match related pieces of text by meaning.

In plain words
What is it for?
Use it to store and retrieve project knowledge for an AI agent running locally. It requires four environment settings, including a database path, embedding model, traversal limit, and log level.
Why use it?
It addresses the problem of an agent forgetting project knowledge or relying only on the current conversation. The stored graph can preserve relationships between facts for later use.

MCP server for Claude CodeCodexCursor

not rated 1 1mo ago A scan tokens not measured original MIT
View the source file Sathvik-1007/GraphMem-MCP
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.

agentmods
npx agentmods add mcp/sathvik-1007/graphmem-mcp/graphmem-mcp
Clone the repo
git clone --depth 1 https://github.com/Sathvik-1007/GraphMem-MCP

Made for: Claude Code, Codex, Cursor.

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.

agentmods badge for graphmem-mcp

README.md
[![agentmods](https://agentmods.dev/badge/mcp/sathvik-1007/graphmem-mcp/graphmem-mcp.svg)](https://agentmods.dev/mcp/sathvik-1007/graphmem-mcp/graphmem-mcp)
Your own site
<a href="https://agentmods.dev/mcp/sathvik-1007/graphmem-mcp/graphmem-mcp"><img src="https://agentmods.dev/badge/mcp/sathvik-1007/graphmem-mcp/graphmem-mcp.svg" alt="Measured on agentmods" 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. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

graphmem-mcp 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 5d 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 · 14 lines

What it actually says

{
  "graphmem-mcp": {
    "command": "uvx",
    "args": [
      "graphmem-mcp"
    ],
    "env": {
      "GRAPHMEM_DB_PATH": "",
      "GRAPHMEM_EMBEDDING_MODEL": "",
      "GRAPHMEM_TRAVERSAL_NODE_BUDGET": "",
      "GRAPHMEM_LOG_LEVEL": ""
    }
  }
}
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.

  1. 5d ago First seen · 14 lines scan A 85159e40952d

Subscribe to this mod's changes

graphmem-mcp is an MCP server published in the GitHub repository Sathvik-1007/GraphMem-MCP (1 stars, last pushed 1mo 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.

Data and AIMemory and contextRAG and vectors
Related

Other mcp servers, from other repositories

context-engine

Task-aware context compression for logs, RAG, and coding workflows. Runs locally from the melonelish-context-engine Python package.

melonelish/context-engine · not measured

token-savior

Optimized MCP server for AI coding agents. Structural codebase navigation + persistent memory engine — 97.9% accuracy at −80% tokens on tsbench. Runs locally from the token-savior-recall Python package. Needs 3 environment variables to run.

sepehrbayat/SEPCC · not measured

rag-rat

CLI and MCP entrypoint for indexing repositories into local source, graph, history, and memory evidence. Runs locally from the @rag-rat/bin npm package.

cq27-dev/rag-rat · not measured

inspeximus

MCP server "inspeximus" as configured in DanceNitra/inspeximus. Runs locally from the inspeximus[mcp] Python package. Needs 1 environment variable to run.

DanceNitra/inspeximus · not measured

coalent

A real-time, provenance-invalidated cognitive cache layer for AI agents and RAG. Runs locally from the coalent Python package. Needs 2 environment variables to run.

Vectorlink-Labs/coalent · not measured

re-call

Trustworthy retrieval for an AI agent's own memory — verdict, confidence and provenance per hit, or an explicit abstention. Runs locally from the recall-rag Python package. Needs 3 environment variables to run.

GiulioDER/RE-call · not measured