Skip to content
mcp/harbor
LangChain

cgraphy for LangChain

io.github.pmgarg/cgraphy

Code knowledge graph over MCP: token-budgeted context for AI coding agents.

client:LangChain transport:stdio runtime:pypi

Install cgraphy in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "cgraphy": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["cgraphy"],
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

cgraphy in other clients

cgraphy MCP server