Memento MCP Server

Memento MCP: Knowledge graph memory system for LLMs

Local serverstdioPython

What is the Memento MCP MCP server?

Memento MCP MCP server exists for a simple reason — assistants are far more useful when they can act on Memento MCP directly instead of describing what you should do. Memento MCP: Knowledge graph memory system for LLMs.

What you get

Scalable, high performance knowledge graph memory system with semantic retrieval, contextual recall, and temporal awareness. Provides any LLM client that supports the model context protocol (e.g., Claude Desktop, Cursor, Github Copilot) with resilient, adaptive, and persistent long-term ontological memory.

  • Unified Storage — Consolidates both graph and vector storage into a single database
  • Native Graph Operations — Built specifically for graph traversal and queries
  • Integrated Vector Search — Vector similarity search for embeddings built directly into Neo4j
  • Scalability — Better performance with large knowledge graphs
  • Simplified Architecture — Clean design with a single database for all operations

What the assistant can call

Once Memento MCP is connected, these are the calls the assistant has available:

  • diagnose_vector_search — Information about the Neo4j vector index, embedding counts, and search functionality
  • force_generate_embedding — Forces the generation of an embedding for a specific entity
  • debug_embedding_config — Information about the current embedding service configuration
  • Entities — Entities are the primary nodes in the knowledge graph. Each entity has:
  • Relations — Relations define directed connections between entities with enhanced properties:
  • Prerequisites — The Prerequisites tool exposed by this server
  • Configuration — The Configuration tool exposed by this server

Setting it up

The server ships on npm as @smithery/cli, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Configuration and credentials

You will need 8 environment variables: MEMORY_STORAGE_TYPE, NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD, NEO4J_DATABASE, NEO4J_VECTOR_INDEX, NEO4J_VECTOR_DIMENSIONS, NEO4J_SIMILARITY_FUNCTION. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Neo4j 5.13+ (required for vector search capabilities)

Choosing this one

This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Memento MCP's toolset — diagnose_vector_search, force_generate_embedding, debug_embedding_config and 4 more — is a fair guide to whether it matches your workflow. It is maintained by gannonh; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Memento MCP'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.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the memento mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
diagnose_vector_searchInformation about the Neo4j vector index, embedding counts, and search functionality
force_generate_embeddingForces the generation of an embedding for a specific entity
debug_embedding_configInformation about the current embedding service configuration
EntitiesEntities are the primary nodes in the knowledge graph. Each entity has:
RelationsRelations define directed connections between entities with enhanced properties:
PrerequisitesThe Prerequisites tool exposed by this server.
ConfigurationThe Configuration tool exposed by this server.

How to install the Memento MCP MCP server

{
  "mcpServers": {
    "memento": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "MEMORY_STORAGE_TYPE": "your-value",
        "NEO4J_URI": "your-value",
        "NEO4J_USERNAME": "your-value",
        "NEO4J_PASSWORD": "your-value",
        "NEO4J_DATABASE": "your-value",
        "NEO4J_VECTOR_INDEX": "your-value",
        "NEO4J_VECTOR_DIMENSIONS": "your-value",
        "NEO4J_SIMILARITY_FUNCTION": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Neo4j 5.13+ (required for vector search capabilities)
VariableDescriptionRequired
MEMORY_STORAGE_TYPEConfiguration value read at startup.Optional
NEO4J_URIConfiguration value read at startup.Optional
NEO4J_USERNAMEConfiguration value read at startup.Optional
NEO4J_PASSWORDConfiguration value read at startup.Optional
NEO4J_DATABASEConfiguration value read at startup.Optional
NEO4J_VECTOR_INDEXConfiguration value read at startup.Optional
NEO4J_VECTOR_DIMENSIONSConfiguration value read at startup.Optional
NEO4J_SIMILARITY_FUNCTIONConfiguration value read at startup.Optional

Example prompts to try

  • Use Memento MCP to diagnose vector search.
  • Use Memento MCP to force generate embedding.
  • Use Memento MCP to debug embedding config.

Frequently asked questions

It connects Memento MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (diagnose_vector_search, force_generate_embedding, debug_embedding_config, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Memento MCP directly.