Graphiti Knowledge Graph
Built by michabbb as a working implementation of Graphiti's knowledge graph functionality, this server processes episodes (text, messages, or JSON) into nodes (entities) and facts (relationships) with temporal metadata stored in Neo4j. It supports dynamic information that evolves over time and includes custom entity extraction for requirements, preferences, and procedures. The implementation features Docker deployment, authentication via nonce tokens, background processing queues to prevent race conditions, making it valuable for applications that need persistent, queryable memory across conversations and complex data relationships.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/michabbb/graphiti-mcp-but-working
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Graphiti Knowledge Graph from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.