mcp-memory-service

Overview

mcp-memory-service is an open-source memory backend that provides persistent storage for AI agent pipelines like LangGraph, CrewAI, and AutoGen. It offers both REST API and MCP protocol access, with support for Remote MCP integration with claude.ai in browsers. The service features knowledge graphs with typed edges, autonomous memory consolidation, and local embeddings via ONNX. It can be self-hosted with OAuth 2.0 authentication and supports multi-agent scenarios with memory sharing and inter-agent messaging through tagging.

Try asking AI

After installing, here are 4 things you can ask your AI assistant:

• store_memorymemory_store(content: string, tags: string[], conversation_id: string = null, agent_id: string = null)

  Store a memory entry with content and tags for later retrieval

  Try:Store that the API limit is 100 requests per minuteTry:Remember that our project uses Python 3.11
• search_memoriesmemory_search(query: string, tags: string[], agent_id: string = null, limit: int = 10)

  Search stored memories using semantic search and filtering

  Try:Find memories about API rate limitsTry:Search for project architecture decisions
• delete_memorymemory_delete(memory_id: string)

  Delete a specific memory entry by ID

  Try:Remove the outdated API limit informationTry:Delete the temporary note about the server maintenance
• get_memory_graphmemory_graph_get(agent_id: string = null)

  Retrieve the knowledge graph of memories with relationships

  Try:Show me the knowledge graph of our systemTry:Get all memories related to authentication
• add_memory_edgememory_graph_add_edge(source_id: string, target_id: string, relation: string)

  Add a relationship between two memory entries

  Try:Connect the API limit memory to the provider switching decisionTry:Relate the bug fix to the original issue
• consolidate_memoriesmemory_consolidate(days_old: int = 30, compression: float = 0.5)

  Automatically consolidate old memories into compressed summaries

  Try:Consolidate memories older than 60 daysTry:Compress memories with minimal detail loss

Comparable tools

Installation

# Basic installation
pip install mcp-memory-service

# Start the server
MCP_ALLOW_ANONYMOUS_ACCESS=true memory server --http

{
  "mcpServers": {
    "mcp-memory": {
      "command": "python",
      "args": ["-m", "mcp_memory_service.server"],
      "env": {
        "MCP_ALLOW_ANONYMOUS_ACCESS": "true",
        "MCP_STREAMABLE_HTTP_MODE": "1"
      }
    }
  }
}

MCP_STREAMABLE_HTTP_MODE=1 MCP_SSE_HOST=0.0.0.0 MCP_SSE_PORT=8765 python -m mcp_memory_service.server

Compare mcp-memory-service with