Tailnet MCP bridge for LangChain
io.github.zedong-peng/tailnet-mcp
Reach an MCP server inside your Tailscale tailnet from an agent's sandbox, over stdio.
client:LangChain
transport:stdio
runtime:oci
Install Tailnet MCP bridge in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"tailnet-mcp": {
"transport": "stdio",
"command": "docker",
"args": ["run", "-i", "--rm", "ghcr.io/zedong-peng/tailnet-mcp:v0.3.0"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs