Advertise
MCP.so
Sign In
G

Graphiti MCP Pro

@itcook

Repository

Basic information

Category

Other

Transports

stdio

Author

itcook

Submitted by

Wei Lai

About Graphiti MCP Pro

Base on Graphiti, Enhanced Core Capabilities, Broader AI Model Compatibility, and Comprehensive Management UI.

#memory#graphiti#ai#management

Graphiti MCP Pro config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "graphiti_pro": {
      "transport": "http",
      "url": "http://localhost:8082/mcp"
    }
  }
}

Graphiti MCP Pro tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list directly from this server's endpoint using the button above.

Overview

What is Graphiti Mcp Pro?

Graphiti Mcp Pro is an enhanced memory repository MCP service and management platform built on Graphiti, a framework for temporally‑aware knowledge graphs designed for AI agents in dynamic environments. It adds asynchronous parallel processing, broader AI model compatibility, and a comprehensive visual Web UI for managing the service.

How to use Graphiti Mcp Pro?

Deploy via Docker Compose (recommended) by cloning the repository, optionally configuring the .env file, then running docker compose up -d; access the management interface at http://localhost:6062. For manual installation, ensure Python 3.10+, uv, Node.js 20+, Neo4j 5.26+, and an AI model service are available, then run uv sync, configure .env, and start the service with uv run main.py -m (management backend enabled) or uv run main.py (MCP only). The frontend can be built separately using pnpm in the manager/frontend directory.

Key features of Graphiti Mcp Pro

  • Asynchronous parallel processing (up to 5 tasks per group)
  • Four new MCP tools for managing add_memory tasks
  • Unified configuration management with backend override
  • Broader model compatibility via the instructor library
  • Separated model configuration for LLM, small LLM, and embedding
  • Full management platform with real‑time monitoring and logs

Use cases of Graphiti Mcp Pro

  • Building context‑aware AI applications that require dynamic, temporal knowledge graphs
  • Managing distinct developer projects by grouping memories under different group IDs
  • Performing historical queries on incremental data without full graph recomputation
  • Combining different AI models (e.g., large + small LLMs) for efficient entity and relationship extraction

Frequently asked questions

1

Does the management backend have authentication?

No, the management backend does not implement authorization. Do not expose the service on public servers.

2

What transport protocol does Graphiti Mcp Pro use?

Only the `streamable-http` transport protocol is supported; `stdio` and `sse` support from the original project has been removed.

3

How does configuration work when the management backend is enabled?

When the management backend is enabled, parameters in the `.env` file only take effect on the first startup; subsequent configurations are managed through the backend database.

4

Can I use models like DeepSeek, Qwen, or local models?

Yes, through integration with the `instructor` library, Graphiti Mcp Pro supports any model that provides an OpenAI‑compatible API, including DeepSeek, Qwen, and models run via Ollama or vLLM.

5

What are the known limitations regarding testing?

The project has not been thoroughly tested due to resource constraints, so it is recommended for personal use only.

Comments

More Other MCP servers

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

Glasswarp

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

ICSS

chokcoco

不止于 CSS

20.7K

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K
Advertise