Graphiti MCP Server
Configures the Graphiti MCP server to use an external Neo4j instance as its graph database backend for storing and querying knowledge graph data.
Supports pointing the OpenAI-compatible API base at a local Ollama endpoint so the Graphiti MCP server can use locally hosted models for LLM and embedding operations.
Uses OpenAI as the default LLM and embeddings provider, configured with an OpenAI API key, to power Graphiti's entity extraction and embedding capabilities.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Graphiti MCP Server (slim image) — fork of upstream
This repo is a fork of the upstream Graphiti MCP server (
getzep/graphiti, app code inmain.py/src//config/, unchanged except where noted inpyproject.toml). All credit for the server itself goes to the Zep AI / Graphiti team; this fork only re-packages it into a slim Docker image.
A slim Docker packaging of the upstream Graphiti MCP server.
Compared with the upstream docker/Dockerfile.standalone (~3.2GB), this image:
installs only the default dependencies — no
providers/azureextras, so no sentence-transformers → PyTorch/CUDA (~2.5GB saved)uses a multi-stage build (no pip/uv/curl/sfw in the final image)
ships a python-based healthcheck instead of curl
Expected size: ~350MB.
Configuration
LLM + embeddings default to OpenAI (set OPENAI_API_KEY). Point api_base at an
OpenAI-compatible endpoint (Ollama, vLLM, …) for local models. The server connects to an
external FalkorDB (default) or Neo4j — configure via config/config.yaml, env vars, or CLI
flags (same precedence as upstream). See the upstream
README for details.
Related MCP server: Graphiti Memory MCP Server
Build locally
docker build -t graphiti-mcp .
# optionally pin graphiti-core:
docker build --build-arg GRAPHITI_CORE_VERSION=0.31.1 -t graphiti-mcp .Run
docker run --rm -p 8000:8000 --env-file .env graphiti-mcpMCP endpoint:
http://localhost:8000/mcp(also available with a trailing slash — it redirects)Health check:
http://localhost:8000/health
CI
.github/workflows/docker.yml builds on pushes to main, tags, and PRs (build-only),
fetches the latest graphiti-core version from PyPI, pins it as a build arg, and pushes
multi-platform images (amd64 + arm64) to ghcr.io/<owner>/<repo> with tags
latest, the git SHA, core-<version>, and v* tags.
Repo settings needed: Settings → Actions → General → Workflow permissions → Read and
write permissions (for GITHUB_TOKEN to push to GHCR).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Query your own knowledge graph from any MCP client. The graph lives in a database you own.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Personal knowledge graph as an AI memory layer over MCP - read, save, and link your memories.
Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA temporally-aware knowledge graph MCP server for AI agents, enabling episodic ingestion, entity management, and semantic search with support for multiple LLM and embedding providers.Apache 2.0
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to manage and query a temporally-aware knowledge graph memory, supporting episode tracking, entity relationships, and semantic search via MCP tools.1-
- FlicenseNot gradedqualityDmaintenanceEnables building and querying knowledge graphs by ingesting documents into Neo4j using Gemini for entity extraction, and exposes MCP tools for graph health, document ingestion, and knowledge base querying.-
- AlicenseAqualityDmaintenanceProvides persistent, multi-tenant knowledge graph memory for MCP-capable AI tools, allowing them to recall and store entities, observations, and relations across sessions with keyword search.103MIT