Skip to content
mcp/harbor
LangChain

connexagents mcp for LangChain

io.github.jldlab/connexagents-mcp

Fallback layer for AI agents: a stuck agent calls find_specialist, pays only if it works.

client:LangChain transport:stdio runtime:npm

Install connexagents mcp in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "connexagents-mcp": {
            "transport": "stdio",
            "command": "npx",
            "args": ["-y", "connexagents-mcp"],
        }
})

tools = await client.get_tools()

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

connexagents mcp in other clients

connexagents mcp MCP server