Context Mem MCP Server

Memory + context infrastructure for AI agents. LLM Wiki auto-sync, 15 content-aware summarizers, hybrid search (BM25 + vector + optional LLM judge)

Local serverstdioPython

What is the Context Mem MCP server?

Context Mem MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Memory + context infrastructure for AI agents. LLM Wiki auto-sync, 15 content-aware summarizers, hybrid search (BM25 + vector + optional LLM judge), entity intelligence, decision trails, Obsidian plugin. Fully local, zero cost. MIT.

What you get

Two problems with today's AI tooling that no one has solved together in a single package.

What the assistant can call

Once Context Mem is connected, these are the calls the assistant has available:

  • Benchmark — Retrieval Recall
  • LongMemEval97.8% R@5
  • LoCoMo98.1% R@10
  • MemBench98.0% R@5
  • ConvoMem97.7% R@10
  • observe — Store observation with auto-summarization, importance scoring, entity extraction, topic detection
  • recall — Retrieve verbatim content by filter (importance, type, flag, time)
  • search — Hybrid search (BM25 + vector + optional LLM judge)
  • ask — Natural language Q&A over the full memory store
  • timeline — Reverse-chronological observations with importance badges and flags
  • stats — Token economics for current session (raw vs. compressed)
  • save_knowledge — Save a knowledge entry with contradiction detection + temporal validity windows

Setting it up

Installation goes through your MCP client rather than a global install: point it at context-mem on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Choosing this one

This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Context Mem's toolset — Benchmark, LongMemEval, LoCoMo and 11 more — is a fair guide to whether it matches your workflow. It is maintained by jubakitiashvili; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Context Mem's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Context Mem.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the context mem mcp server does with a few real requests.

Available tools

ToolWhat it does
BenchmarkRetrieval Recall
LongMemEval**97.8% R@5**
LoCoMo**98.1% R@10**
MemBench**98.0% R@5**
ConvoMem**97.7% R@10**
observeStore observation with auto-summarization, importance scoring, entity extraction, topic detection
recallRetrieve verbatim content by filter (importance, type, flag, time)
searchHybrid search (BM25 + vector + optional LLM judge)
askNatural language Q&A over the full memory store
timelineReverse-chronological observations with importance badges and flags
statsToken economics for current session (raw vs. compressed)
save_knowledgeSave a knowledge entry with contradiction detection + temporal validity windows
search_knowledgeSearch (superseded entries filtered by default)
promote_knowledgePromote to global cross-project store

How to install the Context Mem MCP server

{
  "mcpServers": {
    "context-mem": {
      "command": "npx",
      "args": ["-y", "context-mem"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Context Mem to Benchmark.
  • Use Context Mem to LongMemEval.
  • Use Context Mem to LoCoMo.

Frequently asked questions

It connects Context Mem to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Benchmark, LongMemEval, LoCoMo, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Context Mem directly.