Ckg Mcp

Name: Ckg Mcp
Author: Yarmoluk

by Yarmolukcommunityv0.1.1

Compact Knowledge Graph MCP server that exposes pre-structured domain knowledge as graph traversals for agent workflows. It provides prerequisite chains, dependency paths, and concept searches across bundled domains instead of text chunk retrieval.

From the registry: Structured domain knowledge for AI agents. 42x more accurate than RAG, 11x fewer tokens.

GitHub Repository

Install & configure

Prerequisites

required
Install Python package
Install the MCP server from PyPI using pip.
```
$ pip install ckg-mcp
```

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `ckg-mcp` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install Python package** — Install the MCP server from PyPI using pip. Run: `pip install ckg-mcp`

Canonical MCP server config (stdio transport):
- command: `ckg-mcp`
- args: []

Note: README shows a Claude Desktop example using the stdio command `ckg-mcp`. No arguments or environment variables are documented.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: README shows a Claude Desktop example using the stdio command `ckg-mcp`. No arguments or environment variables are documented.