MCP Template Server

A template for building mcp servers in python
  • python

5

GitHub Stars

python

Language

6 months ago

First Indexed

2 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

You can run a Model Context Protocol (MCP) server to connect Cursor IDE with your own tools. This server supports both remote HTTP SSE connections and local stdio workflows, letting you test and use your MCP-powered tools directly from Cursor.

How to use

Connect Cursor IDE to an MCP server using either a remote SSE URL or a local stdio setup. For a remote server, point Cursor to the SSE endpoint you provide (for example, the /sse path on your deployed server). For a local workflow, start the MCP server on your machine and configure Cursor to communicate via stdio. Once connected, you can interact with your MCP-enabled tools by issuing prompts and receiving structured tool responses that your agent can act on.

How to install

Prerequisites you need before installing: a modern runtime environment that matches the server setup you plan to use (Python for the dev flow shown, or a container/Docker environment if you prefer). Choose one of the following install methods and follow the steps exactly.

# Docker method (simplified quick-path)
# Clone the repository
# Note: adapt the repository URL if you are starting from a template
# Build and run using Docker Compose

docker compose up --build -d

docker compose logs -f

docker compose ps

docker compose down

# SSE endpoint will be available at http://localhost:8000/sse
# Traditional setup using uvx/python workflow
# Install the package with development dependencies
uv pip install -e ".[dev]"

# Start using stdio transport (default)
uv run mcp-simple-tool

# Start using SSE transport on port 8000
uv run mcp-simple-tool --transport sse --port 8000

# Run tests
uv run pytest -v

Additional setup notes

Environment variables you may configure (place in a .env file or set in your environment): MCP_SERVER_PORT 8000, MCP_SERVER_HOST 0.0.0.0, DEBUG false, MCP_USER_AGENT you_can_customize.

To connect Cursor IDE to your local server, use the stdio flow and point Cursor to the local command you ran. For example, if you started the server with the stdio path shown above, add a new MCP server in Cursor with Type set to stdio and Command set to the runtime command you used (for example, uv) and Args including the relevant subcommands.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational