An MCP server configuration for Core Memory Kit, a project memory system for Claude Code. MCP is a way for an agent to use external tools through a standard connection.

It is for starting Core Memory Kit's MCP service with `cmk mcp serve`.

It provides the configured connection needed for the memory system to serve its tools to the coding agent.

cmk — MCP server by LH8PPL

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/lh8ppl/core-memory-kit/cmk

Clone the repo

git clone --depth 1 https://github.com/LH8PPL/core-memory-kit

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

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

cmk 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 2d 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.

.mcp.json · 10 lines

What it actually says

{
  "cmk": {
    "type": "stdio",
    "command": "cmk",
    "args": [
      "mcp",
      "serve"
    ]
  }
}

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.

2d ago First seen · 10 lines scan A 08bc82e2acb4

Subscribe to this mod's changes

cmk is an MCP server published in the GitHub repository LH8PPL/core-memory-kit (6 stars, last pushed 5d 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-memory ai-agents ai-memory anthropic claude claude-code

deja

MCP server "deja" as configured in vshulcz/deja-vu. Launched with deja mcp.

vshulcz/deja-vu · not measured

ori-memory

Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search. Runs locally from the ori-memory npm package.

aayoawoyemi/Ori-Mnemos · not measured

synap

Persistent memory for AI agents — log and recall conversation context over MCP. Remote server at synap-mcp.maximem.ai.

maximem-ai/maximem_synap_sdk · not measured

perenna

A lightweight, Git-backed permanent memory for AI agents. Runs locally from the perenna Python package. Needs 4 environment variables to run.

scarletkc/Perenna · not measured

commitlore

MCP server "commitlore" as configured in MongLong0214/commitlore. Runs ./dist/commitlore.mjs with node.

MongLong0214/commitlore · not measured

inspeximus

The agent memory that takes it back: correct a fact once and the retired value stops coming back, by key, with no LLM in the loop. Long-term memory for AI agents in a zero-dependency single file + MCP server, with value-ranked recall, per-type decay, consolidation, revert, and tamper-evident erasure. Runs locally from…

DanceNitra/inspeximus · not measured