
michabbb/graphiti-mcp-but-working
Developer toolsЭта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал
Graphiti is a framework for building and querying temporally-aware knowledge graphs, specifically tailored for AI agents operating in dynamic environments.
Обзор
Graphiti is a framework for building and querying temporally-aware knowledge graphs, specifically tailored for AI agents operating in dynamic environments. Unlike traditional retrieval-augmented generation (RAG) methods, Graphiti continuously integrates user interactions, structured and unstructured enterprise data, and external information into a coherent, queryable graph. The framework supports incremental data updates, efficient retrieval, and precise historical queries without requiring complete graph recomputation, making it suitable for developing interactive, context-aware AI applications. This is an enhanced Model Context Protocol (MCP) server implementation for Graphiti. The MCP server exposes Graphiti's key functionality through the MCP protocol, allowing AI assistants to interact with Graphiti's knowledge graph capabilities. This enhanced version includes several important improvements over the original implementation: 1.
README
Показан фрагмент оригинального README. Открыть оригинал.
Graphiti MCP Server - Enhanced Fork
Graphiti is a framework for building and querying temporally-aware knowledge graphs, specifically tailored for AI agents operating in dynamic environments. Unlike traditional retrieval-augmented generation (RAG) methods, Graphiti continuously integrates user interactions, structured and unstructured enterprise data, and external information into a coherent, queryable graph. The framework supports incremental data updates, efficient retrieval, and precise historical queries without requiring complete graph recomputation, making it suitable for developing interactive, context-aware AI applications.
This is an enhanced Model Context Protocol (MCP) server implementation for Graphiti. The MCP server exposes Graphiti’s key functionality through the MCP protocol, allowing AI assistants to interact with Graphiti’s knowledge graph capabilities.
Key Enhancements in This Fork
This enhanced version includes several important improvements over the original implementation:
- 🚀 Latest Graphiti Core Compatibility - Uses the current version of graphiti-core with all latest features and improvements
- 🤖 GPT-5, O1, O3 Model Support - Proper handling of OpenAI’s reasoning models with automatic parameter adjustment (disables temperature, reasoning, and verbosity parameters)
- 🔒 Token-Based Authentication - Production-ready nonce token authentication system enabling secure public deployment
- 📊 Queue Monitoring Tool - New
get_queue_statustool to monitor episode processing queues, showing pending tasks, active workers, and jobs currently being processed - 💾 Redis-Based Persistent Queues - Worker queues backed by Redis with BRPOPLPUSH pattern for crash recovery and graceful shutdown support (SIGTERM/SIGINT handlers)
- 🛡️ Enhanced Security - Pure ASGI middleware-based authentication with constant-time token comparison to prevent timing attacks
- 🔐 Password-Protected Graph Clearing -
clear_graphtool now requires password authentication via CLEAR_GRAPH_PASSWORD environment variable - 🌐 DNS Rebinding Protection - ALLOWED_HOSTS configuration for secure external access when binding to 0.0.0.0
- 📋 New
list_group_idsTool - Discover and manage all group IDs across nodes and relationships in your knowledge graph - 🗑️ Atomic Group Deletion - New
delete_everything_by_group_idtool for complete group removal in a single call (episodes, nodes, and edges) - 🔇 Telemetry Control - Automatic disabling of telemetry for privacy-focused deployments (set before graphiti_core imports)
- ⚡ Simplified Dependencies - Removed Azure OpenAI dependencies for easier setup and deployment
- 🌐 MCP 2025-06-18 Support - Uses the new Streamable HTTP transport standard (with SSE fallback for legacy clients)
- 📦 Reproducible Builds - Tracked uv.lock file ensures consistent dependency versions across all deployments
Установка
npx mcp-remote http://localhost:8000/mcp" // Use /mcp for Streamable HTTP or /sse for legacy SSEКонфигурация
{
"mcpServers": {
"graphiti-memory": {
"transport": "stdio",
"command": "/Users/<user>/.local/bin/uv",
"args": [
"run",
"--isolated",
"--directory",
"/Users/<user>/dev/graphiti-mcp-but-working",
"--project",
".",
"python",
"-m",
"graphiti_mcp_server",
"--transport",
"stdio"
],
"env": {
"NEO4J_URI": "bolt://localhost:7687",
"NEO4J_USER": "neo4j",
"NEO4J_PASSWORD": "password",
"OPENAI_API_KEY": "sk-XXXXXXXX",
"MODEL_NAME": "gpt-4.1-mini"
}
}
}
}