FastMCP Science Demo
Exposes science functions like generating random points and plotting sine waves as MCP tools.
README
FastMCP Tool Server Starter
Tiny FastMCP server that imports public functions from a science package and exposes them as MCP tools.
Requires Python 3.12+.
Install
python3.12 -m venv .venv
source .venv/bin/activate
pip install -e ./science-demo
pip install -e .
Or with uv that is faster and tidy than pip, but optional:
uv sync
Run
For agents that launch the server as a subprocess:
fast-mcp-starter --transport stdio
For agents that connect to a running MCP URL:
fast-mcp-starter --transport streamable-http --host 127.0.0.1 --port 8000
Endpoint:
http://127.0.0.1:8000/mcp
Test With A LangGraph Agent
See notebooks/test_with_agent.ipynb for a small external LangGraph agent that connects to this MCP server.
Hook In Your Repo
Expose normal public Python functions in your external package, add that package as a dependency in pyproject.toml, then import and register those functions in server.py and server.py.
Keep science-demo as a working example while you add your own repo. Delete it later only if you do not want the demo tools.
This starter does that with:
from science_demo.science_tools import generate_random_points, plot_sine_wave
mcp.tool()(generate_random_points)
mcp.tool()(plot_sine_wave)
Demo Tools
The local science-demo package exposes:
generate_random_points(output_dir: str, count: int = 30, seed: int = 42) -> ArtifactResult
plot_sine_wave(output_dir: str, num_points: int = 200) -> ArtifactResult
Both return typed structured content:
{"status": "success", "files": ["..."], "message": "...", "metadata": {}}
Test
python -m pytest
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.