MenteDB MCP Server

⚠️ Beta — MenteDB is under active development. APIs may change between minor versions.

The MCP (Model Context Protocol) server for MenteDB, the mind database for AI agents.

What is this?

This MCP server lets any AI agent (Claude, GPT, Copilot, or any MCP compatible client) use MenteDB as persistent memory. Store, search, relate, and consolidate memories through the standard MCP protocol. The server exposes 32 tools spanning core memory operations, knowledge graph traversal, context assembly, memory consolidation, cognitive systems, and LLM based extraction, all over stdio transport.

Quick Start

Install from crates.io:

# Requires Rust: https://rustup.rs
cargo install mentedb-mcp

Then run the auto-setup for your client:

# GitHub Copilot CLI
mentedb-mcp setup copilot

# Claude Desktop
mentedb-mcp setup claude

# Cursor
mentedb-mcp setup cursor

This creates the MCP config, agent instructions, and alwaysAllow list automatically. No manual file editing needed.

Manual Configuration

If you prefer manual setup, see the client-specific configs below.

Claude Desktop

Add to ~/.config/claude/claude_desktop_config.json (macOS/Linux) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "mentedb": {
      "command": "mentedb-mcp",
      "args": ["--data-dir", "~/.mentedb"]
    }
  }
}

Cursor

Add to your Cursor MCP configuration:

{
  "mcpServers": {
    "mentedb": {
      "command": "mentedb-mcp",
      "args": ["--data-dir", "~/.mentedb"],
      "transportType": "stdio"
    }
  }
}

GitHub Copilot (VS Code)

Add to .vscode/mcp.json in your project:

{
  "servers": {
    "mentedb": {
      "type": "stdio",
      "command": "mentedb-mcp",
      "args": ["--data-dir", "~/.mentedb"]
    }
  }
}

GitHub Copilot CLI

Add to ~/.copilot/mcp-config.json:

{
  "mcpServers": {
    "mentedb": {
      "command": "mentedb-mcp",
      "args": ["--data-dir", "~/.mentedb"],
      "alwaysAllow": [
        "store_memory", "get_memory", "recall_memory", "search_memories",
        "relate_memories", "forget_memory", "forget_all", "ingest_conversation",
        "assemble_context", "get_related", "find_path", "get_subgraph",
        "find_contradictions", "propagate_belief", "consolidate_memories",
        "apply_decay", "compress_memory", "evaluate_archival", "extract_facts",
        "gdpr_forget", "process_turn", "record_pain", "detect_phantoms",
        "resolve_phantom", "record_trajectory", "predict_topics",
        "detect_interference", "check_stream", "write_inference",
        "register_entity", "get_cognitive_state", "get_stats"
      ]
    }
  }
}

The alwaysAllow list lets memory tools run without approval prompts. Remove it if you prefer manual approval per tool call.

Embeddings

The server uses local Candle embeddings by default with the all-MiniLM-L6-v2 model (384 dimensions). No API key needed for semantic search. The model auto-downloads from Hugging Face on first use (~80MB) and is cached locally. If the download fails (offline), it falls back to hash embeddings.

LLM Extraction (Optional)

Embeddings power search. For LLM based memory extraction via ingest_conversation, you can optionally configure an API key:

{
  "mcpServers": {
    "mentedb": {
      "command": "mentedb-mcp",
      "args": ["--data-dir", "~/.mentedb", "--llm-provider", "anthropic"],
      "env": {
        "MENTEDB_LLM_API_KEY": "sk-ant-..."
      }
    }
  }
}

Supported providers: openai, anthropic, ollama, mock (default). Without an API key, ingest_conversation uses the mock provider which does basic keyword extraction.

Available Tools (32 tools)

Core Memory (8 tools)

Memory types: episodic, semantic, procedural, anti_pattern, reasoning, correction.

Edge types: caused, before, related, contradicts, supports, supersedes, derived, part_of.

Context Assembly (1 tool)

Knowledge Graph (5 tools)

Memory Consolidation (6 tools)

Cognitive Systems (12 tools)

Configuration

CLI Arguments

mentedb-mcp [OPTIONS]

Options:
  --data-dir <PATH>           Data directory path [default: ~/.mentedb]
  --embedding-dim <DIM>       Embedding vector dimension [default: 384]
  --llm-provider <PROVIDER>   LLM provider for extraction: openai, anthropic, ollama, mock [default: mock]
  --llm-api-key <KEY>         API key for the LLM provider (overrides env var)
  --llm-model <MODEL>         Model name override for the LLM provider
  -h, --help                  Print help

Environment Variables

The server writes logs to both stderr (for MCP clients) and a rolling file at <data-dir>/mentedb-mcp.log.

Resources

MCP resources provide read only access to server state.

Architecture

The server runs on stdio transport using the rmcp framework. It is backed by the MenteDB engine, which is composed of 13 Rust crates covering storage, indexing, graph, context assembly, consolidation, cognitive systems, embedding, and extraction. Cognitive subsystems (pain registry, phantom tracker, trajectory tracker) are initialized at startup and maintained in memory for the lifetime of the server process.

Issues

Found a bug or have a feature request? Open an issue.

License

Apache-2.0