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.
git clone --depth 1 https://github.com/LH8PPL/core-memory-kitInstalling this writes the configuration, not the program: `cmk` has to be on your PATH already, or the server will not start.
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.
[](https://agentmods.dev/mcp/lh8ppl/core-memory-kit/cmk)<a href="https://agentmods.dev/mcp/lh8ppl/core-memory-kit/cmk"><img src="https://agentmods.dev/badge/mcp/lh8ppl/core-memory-kit/cmk/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.
<a href="https://agentmods.dev/mcp/lh8ppl/core-memory-kit/cmk"><img src="https://agentmods.dev/badge/mcp/lh8ppl/core-memory-kit/cmk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 1mo 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.
What it actually says
{
"cmk": {
"type": "stdio",
"command": "cmk",
"args": [
"mcp",
"serve"
]
}
}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.
- 1mo ago First seen · 10 lines scan A 08bc82e2acb4
cmk is an MCP server published in the GitHub repository LH8PPL/core-memory-kit (7 stars, last pushed 15d 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.
Other mcp servers, from other repositories
groundmemory
Persistent, semantic memory for AI agents - mcp-native, local-first, framework-agnostic, production-ready. Runs locally from the groundmemory Python package.
ultramemory
MCP server "ultramemory", hosted remotely at api.ultramemory.us, as configured in LogicLabsAI/ultramemory-mcp.
ultramemory-mcp
Cross-tool memory for your AI that recalls first every turn and admits when it doesn't know. Remote server at api.ultramemory.us.
memory-mcp
A python implementation of AI memory in MCP. Runs locally from the memory-mcp Python package.
ori-memory
Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search. Runs locally from the ori-memory npm package.
ai-memory
MCP server "ai-memory" as configured in alphaonedev/ai-memory-mcp. Runs in Docker (ghcr.io/alphaonedev/ai-memory:0.5.1). Needs 1 environment variable to run.