Graphiti Pro
Graphiti MCP Pro server implementation by itcook that provides AI assistants with persistent memory capabilities through a knowledge graph built on Neo4j, featuring episode-based memory storage, entity relationship tracking, and semantic search across nodes and facts with temporal metadata support. The implementation includes a comprehensive web-based management dashboard with real-time logging, token usage analytics, and configuration management, plus asynchronous task processing for memory operations with queue management and worker coordination. Built with FastAPI and React, it supports multiple LLM providers through OpenAI-compatible APIs, includes encrypted credential storage, and provides both HTTP and stdio transports, making it valuable for AI applications requiring long-term memory persistence, relationship discovery, and administrative oversight of memory operations across different conversation contexts and user groups.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/itcook/graphiti-mcp-pro
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Graphiti Pro 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.