kegg mcp for LangChain
io.github.mrfentmen/kegg-mcp
Search KEGG genes and compounds, read entries and list their pathways - keyless.
client:LangChain
transport:stdio
runtime:npm
Install kegg mcp in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"kegg-mcp": {
"transport": "stdio",
"command": "npx",
"args": ["-y", "@mrfentmen/kegg-mcp"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs