Dense Knowledge MCP server

Dense Knowledge

<!-- mcp-name: io.github.Lucky44k/dense-knowledge-mcp -->

A local-first MCP memory server for persistent LLM knowledge.

Dense Knowledge lets an AI assistant keep structured research between sessions without a database, embedding model, or hosted account. It stores portable .mmp files, searches their compact indexes with BM25, and loads full entries only when they are relevant.

question -> compact index/search -> selected knowledge blocks -> answer
             inexpensive             detailed context

It works with LM Studio, Claude Desktop, Cursor, VS Code, and other clients that support local stdio Model Context Protocol servers.

Why Dense Knowledge?

inspected, diffed, and backed up.

• Selective context: index first, body blocks only on demand.
• Local and portable: plain ASCII-in-UTF-8 files that can be copied,

and synonym expansion.

• No vector infrastructure: deterministic BM25 search with abbreviation

them.

• Append-only history: updates supersede older entries instead of erasing

unsourced inferences are marked as hypotheses.

• Explicit provenance: established and contested claims carry source IDs;

for common prompt-injection contamination.

• Safer retrieval: stored text is wrapped as untrusted data and screened

The bundled context benchmark uses 40 entries. In its synthetic fixture, searching and reading the two best blocks uses 94.3% less estimated context than loading the complete package. The benchmark is reproducible and clearly documents its tokenizer-neutral counting method.

Quick start

Install uv, then place this server definition in your MCP client:

{
  "mcpServers": {
    "dense-knowledge": {
      "command": "uvx",
      "args": ["dense-knowledge-mcp"]
    }
  }
}

uvx downloads the published package when needed. Dense Knowledge uses the platform's default data directory unless --root is supplied:

{
  "mcpServers": {
    "dense-knowledge": {
      "command": "uvx",
      "args": [
        "dense-knowledge-mcp",
        "--root",
        "/absolute/path/to/memory"
      ]
    }
  }
}

Configuration differs slightly between clients. Ready-to-copy instructions are available for:

• LM Studio
• Claude Desktop
• Cursor
• Visual Studio Code

To install the command-line tools permanently:

uv tool install dense-knowledge-mcp
mmp setup
mmp doctor

mmp setup creates the memory directory and can safely merge the server into an LM Studio mcp.json. Existing servers are preserved. Replacing an existing Dense Knowledge entry requires --force and creates a backup first.

See it work

The CLI exposes the same storage operations as the MCP server:

mmp create quantum_physics.mmp "quantum physics"
mmp write quantum_physics.mmp --rev 0 --from examples/research_entries.json
mmp search quantum_physics.mmp "experimental tests of local realism"
mmp read quantum_physics.mmp e1

Typical search output contains candidates, not full bodies:

<mmp_data file="quantum_physics.mmp" trust="untrusted">
quantum_physics.mmp|e1|F|2.5427|Bell inequality separates local realism from quantum predictions
</mmp_data>

Shortened. The full README is on GitHub.