Skip to content
LangChain

codabench mcp for LangChain

io.github.harshitagr/codabench-mcp

MCP server for the Codabench REST API — drives a full ML-benchmark participant workflow.

client:LangChain transport:stdio runtime:pypi

Install codabench mcp in LangChain

pip install langchain-mcp-adapters

from langchain_mcp_adapters.client import MultiServerMCPClient

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

tools = await client.get_tools()

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

codabench mcp in other clients