Modular MCP Server & Client
A modular and extensible tool server built on FastMCP that supports multiple tools organized across files and communicates via MCP protocol.
README
š¤ļø Modular MCP Server & Client
This project provides a modular and extensible tool server built on FastMCP. It supports multiple tools organized across files and is compatible with a local or remote client that communicates via the MCP protocol.
š Project Structure
āāā server.py # Defines and exports the shared FastMCP instance
āāā main.py # Entry point to run the server
āāā tools/
ā āāā weather_tools.py # Weather-related tools (alerts, forecast)
āāā client/
ā āāā main.py # Entry point to run the client
āāā config.yaml # Configuration file for the server
š Getting Started
š§ Requirements
- Python 3.10+
uvpackage manager (used to run client/server scripts)- MCP-compatible client and server setup
Add Environment Variables
touch .env
echo "ANTHROPIC_API_KEY=<your key here>" >> .env
echo ".env" >> .gitignore
š„ļø Run the Server
To start the tool server:
uv run server/main.py
š§āš» Run the Client
To start the client server:
uv run client/main.py <Path to server>
Replace <Path to server> with the local or remote path to the server script (e.g. server/main.py).
š§© Extending the Server
You can easily extend this server with additional tools. 1. Create a new module in the tools/ directory (e.g., tools/finance_tools.py). 2. Define your functions using the @mcp.tool() decorator. 3. In config.yaml, add your new module to the tools list to register the tools.
Example:
# config.yaml
tools:
- tools.weather_tools
- tools.search_tools # Your new tools
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.