codegraph for LangChain
io.github.codegraph-ai/codegraph
Semantic code graph: 42 tools, 38 languages. Callers, impact, AI context, memory, PR review.
client:LangChain
transport:stdio
runtime:npm
Install codegraph in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"codegraph": {
"transport": "stdio",
"command": "npx",
"args": ["-y", "@astudioplus/codegraph-mcp"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs