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.…
memento-mcp is an MCP project maintained in the gannonh/memento-mcp repository. The maintainer describes its purpose as “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…”. Read the project documentation for the complete scope.
The documented npm package is @gannonh/memento-mcp. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
The example declares MEMORY_STORAGE_TYPE, NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD, NEO4J_DATABASE, NEO4J_VECTOR_INDEX, NEO4J_VECTOR_DIMENSIONS, NEO4J_SIMILARITY_FUNCTION, OPENAI_API_KEY, OPENAI_EMBEDDING_MODEL, DEBUG. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
{
"mcpServers": {
"memento": {
"command": "npx",
"args": [
"-y",
"@gannonh/memento-mcp"
],
"env": {
"MEMORY_STORAGE_TYPE": "neo4j",
"NEO4J_URI": "bolt://127.0.0.1:7687",
"NEO4J_USERNAME": "neo4j",
"NEO4J_PASSWORD": "YOUR_NEO4J_PASSWORD",
"NEO4J_DATABASE": "neo4j",
"NEO4J_VECTOR_INDEX": "entity_embeddings",
"NEO4J_VECTOR_DIMENSIONS": "1536",
"NEO4J_SIMILARITY_FUNCTION": "cosine",
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
"OPENAI_EMBEDDING_MODEL": "text-embedding-3-small",
"DEBUG": "true"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| MEMORY_STORAGE_TYPE | Declared in the maintainer’s client configuration. | Check documentation |
| NEO4J_URI | Declared in the maintainer’s client configuration. | Check documentation |
| NEO4J_USERNAME | Declared in the maintainer’s client configuration. | Check documentation |
| NEO4J_PASSWORD | Declared in the maintainer’s client configuration. | Check documentation |
| NEO4J_DATABASE | Declared in the maintainer’s client configuration. | Check documentation |
| NEO4J_VECTOR_INDEX | Declared in the maintainer’s client configuration. | Check documentation |
| NEO4J_VECTOR_DIMENSIONS | Declared in the maintainer’s client configuration. | Check documentation |
| NEO4J_SIMILARITY_FUNCTION | Declared in the maintainer’s client configuration. | Check documentation |
| OPENAI_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
| OPENAI_EMBEDDING_MODEL | Declared in the maintainer’s client configuration. | Check documentation |
| DEBUG | Declared in the maintainer’s client configuration. | Check documentation |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
WebSocket MCP Server for Mail Operations
MCP server for Polarion ALM — read and write documents and work items
Predict anything with Chronulus AI forecasting and prediction agents.
B2A2H platform — tracks GA4, Vercel deployments, GitHub workflows with AI-powered ROI analytics.