tfl mcp for LangChain
io.github.mrfentmen/tfl-mcp
TfL live data: line status across tube, DLR and rail, stop search and real-time arrivals - keyless.
client:LangChain
transport:stdio
runtime:npm
Install tfl mcp in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"tfl-mcp": {
"transport": "stdio",
"command": "npx",
"args": ["-y", "@mrfentmen/tfl-mcp"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs