map-server
A minimal MCP server built on the official Python SDK, running over Streamable HTTP. It provides demo tools (echo, add) and a time resource for testing MCP clients.
README
Example MCP Server (Streamable HTTP)
A minimal MCP server built on the official Python SDK (mcp==2.0.0), running
over Streamable HTTP so it can live in a container and be reached over the
network.
It ships with two demo tools (echo, add) and one resource (time://now)
so you have something to test against immediately — replace them with your
own.
Run it
docker compose up -d --build
docker compose logs -f mcp-server
The server listens on http://localhost:8000/mcp.
Test it without a client
curl -i -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"test","version":"0.1"}}}'
The response headers include mcp-session-id — reuse it in an
Mcp-Session-Id header on subsequent calls (tools/list, tools/call,
resources/read, etc.) once you've sent a notifications/initialized
message.
Point a client at it
Any MCP client that supports Streamable HTTP just needs the URL:
http://localhost:8000/mcp (or your host's address/port if not running
locally).
Add your own tools
@mcp.tool()
def my_tool(arg: str) -> str:
"""This docstring becomes the tool description the model sees."""
return do_something(arg)
Resources (@mcp.resource("scheme://path")) and prompts (@mcp.prompt())
follow the same pattern. Restart the container after changes:
docker compose up -d --build
Notes
MCP_HOST/MCP_PORTenv vars control what the server binds to inside the container — leaveMCP_HOST=0.0.0.0or it won't be reachable from outside the container.- This has no authentication. Fine for local/dev use behind
localhost:8000; if you expose it beyond your machine, put it behind a reverse proxy or gateway that handles auth (or use the SDK's built-in OAuth support viatoken_verifier/auth_server_provider). - The old
from mcp.server.fastmcp import FastMCPimport path some tutorials still show is gone as ofmcp==2.0.0— it's nowfrom mcp.server import MCPServer.
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.