Modular MCP Server & Client
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Modular MCP Server & Clientget the weather forecast for New York City"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 serverRelated MCP server: my-mcp-server2
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" >> .gitignoreš„ļø Run the Server
To start the tool server:
uv run server/main.pyš§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 toolsThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Nifty's MCP server ā exposes tasks, projects, messages, and files as tools for AI agents.
A simple MCP server built with FastMCP and python
Related MCP Servers
- FlicenseBqualityDmaintenanceA Model Context Protocol server built with FastMCP that enables dynamic tool loading and configuration from individual Python files. It provides a flexible framework for automatically discovering, testing, and running tools via Stdio or HTTP transport modes.1
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server built with FastMCP that features dynamic tool loading and modular management via a dedicated tool directory. It supports both stdio and HTTP transport modes, enabling efficient development and deployment of custom MCP tools.
- FlicenseBqualityDmaintenanceA Model Context Protocol server framework featuring dynamic tool loading and automatic tool discovery from a dedicated directory. It leverages FastMCP to provide a robust environment for building, configuring, and testing individual Python-based tools.1
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jackmichaud/modular-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server