LSD MCP Template
Template for serving FastMCP servers over Streamable HTTP within a LangGraph Server, including an example math_add tool.
README
LSD MCP Template
Template for exposing one or more FastMCP servers from a LangGraph Server custom HTTP route. It is set up for LangSmith Deployments and serves MCP over Streamable HTTP.
The default MCP endpoint is:
/mcp
This template intentionally does not include custom auth. Add auth separately if your deployment needs it.
What's Included
- Minimal LangGraph health graph so LangGraph Server boots normally.
- Custom Starlette app mounted through
langgraph.json. - Lazy MCP app construction so importing the graph server does not build your MCP server.
- Configurable MCP server registry in
src/lsd_mcp_template/mcp_config.py. - One example tool:
math_add(x: int, y: int).
Local Development
uv sync --group dev
make dev
The local MCP endpoint will be available at:
http://127.0.0.1:1424/mcp
Run tests with:
make test
Defining Your MCP Server
Edit src/lsd_mcp_template/server.py and replace the example tool with your own tools:
from fastmcp import FastMCP
def build_server() -> FastMCP:
mcp = FastMCP("My MCP Server")
@mcp.tool(name="my_tool")
def my_tool(value: str) -> str:
return value
return mcp
To expose multiple MCP servers, add more specs in src/lsd_mcp_template/mcp_config.py:
MCP_SERVER_SPECS = (
MCPServerSpec(
name="default",
path="/mcp",
factory="lsd_mcp_template.server:build_server",
),
MCPServerSpec(
name="other",
path="/other-mcp",
factory="lsd_mcp_template.other_server:build_server",
),
)
Each factory must return a fastmcp.FastMCP instance.
Deploy
Use this directory as the repository root for the LangSmith Deployment. The deployment entrypoints are already declared in langgraph.json:
- Graph:
./src/lsd_mcp_template/graph.py:graph - Custom HTTP app:
./src/lsd_mcp_template/webapp.py:app
Set any environment variables your custom tools need in the deployment configuration. The example math_add tool does not require environment variables.
Optional:
export MCP_STATELESS_HTTP=true
When set, the custom route creates the FastMCP Streamable HTTP app in stateless mode.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.