Tvmcp

A minimal Python MCP server template that exposes a streamable HTTP endpoint for easy Render deployments.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "kj14god-tvmcp": {
      "command": "python",
      "args": [
        "src/server.py"
      ]
    }
  }
}

You have a lightweight Python MCP server template that exposes an MCP endpoint via streamable HTTP. It’s designed for quick local testing and easy deployment, letting MCP clients connect to your server at a dedicated /mcp path.

How to use

Use the server by running the local MCP instance and connecting your MCP client to the dedicated endpoint path. Start the server in one terminal and, in a separate terminal, run an inspector tool to verify connectivity. The MCP endpoint is exposed at the /mcp path, and you’ll connect your client to that path over the Streamable HTTP transport.

How to install

Prerequisites you need on your system before getting started:

Python 3.13 or later
conda (or another environment tool) for creating an isolated environment
pip (comes with Python)

Follow these concrete steps to set up and run the server locally:

# 1) Clone the template repository
git clone <your-repo-url>
cd mcp-server-template

# 2) Create and activate a Python environment (conda is shown here)
conda create -n mcp-server python=3.13
conda activate mcp-server

# 3) Install required Python packages
pip install -r requirements.txt

# 4) Run the MCP server
python src/server.py

# 5) In another terminal, start an inspector to test the MCP endpoint
npx @modelcontextprotocol/inspector

Additional steps and notes

Test the MCP connection by opening a browser or using your MCP client to reach http://localhost:3000 and connect to http://localhost:8000/mcp using the Streamable HTTP transport. The crucial path to connect to is the /mcp endpoint.

Configuration and customization

To add functionality, decorate your functions with the MCP tool decorator to expose new capabilities to MCP clients. For example, you can implement a simple calculator tool that can be invoked by clients.

@mcp.tool
def calculate(x: float, y: float, operation: str) -> float:
    """Perform basic arithmetic operations."""
    if operation == "add":
        return x + y
    elif operation == "multiply":
        return x * y
    # additional operations can be added here

Available tools

calculate

A simple arithmetic tool exposed to MCP clients that can perform add and multiply operations based on the provided operands and operation type.