Memento MCP: A Knowledge Graph Memory System for LLMs
{
"mcpServers": {
"memento": {
"env": {
"DEBUG": "true",
"NEO4J_URI": "bolt://127.0.0.1:7687",
"NEO4J_DATABASE": "neo4j",
"NEO4J_PASSWORD": "memento_password",
"NEO4J_USERNAME": "neo4j",
"OPENAI_API_KEY": "your-openai-api-key",
"NEO4J_VECTOR_INDEX": "entity_embeddings",
"MEMORY_STORAGE_TYPE": "neo4j",
"OPENAI_EMBEDDING_MODEL": "text-embedding-3-small",
"NEO4J_VECTOR_DIMENSIONS": "1536",
"NEO4J_SIMILARITY_FUNCTION": "cosine"
},
"args": [
"/path/to/memento-mcp/dist/index.js"
],
"command": "/path/to/node"
}
}
}Memento MCP: A Knowledge Graph Memory System for LLMs
Is it safe?
No known CVEs for @smithery/cli.
No authentication — any process on your machine can connect.
MIT. View license →
Is it maintained?
Last commit 158 days ago. 415 stars. 19,779 weekly downloads.
Will it work with my client?
Transport: stdio, sse. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
Context cost
4 tools. ~600 tokens (0.3% of 200K).
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y @smithery/cli 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
add_entityAdd a new entity to the knowledge graph with name, type, and observations
add_relationCreate a directed relation between two entities with strength and confidence
semantic_searchFind semantically related entities based on meaning using vector embeddings
point_in_time_queryRetrieve the exact state of the knowledge graph at a specific moment in the past
This server is missing a description.If you've used it, help the community.
Add informationLast scanned 12h ago
No known vulnerabilities.
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.