mcpField
T
test-mcp-server

test-mcp-server

Local
github.com/dudeinthemirrorDeveloper Tools0Updated 82w ago

About test-mcp-server

test-mcp-server is a development project for running and inspecting an MCP server. Its README documents local startup in two modes and connecting with the MCP inspector, but does not describe server capabilities.

Key features

  1. 01Development startup with FastAPI
  2. 02Two documented server entry points
  3. 03MCP inspector connection instructions

Use cases

  1. 01Starting the server during development
  2. 02Connecting the inspector to the local endpoint

MCP support

The project runs an MCP server at a local `/mcp` endpoint and documents connecting to it with the MCP inspector over SSE.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

test-mcp-server

Development

Install uv

This project uses the uv packager. To install it on your machine, run:

curl -LsSf https://astral.sh/uv/install.sh | sh
Install direnv

This project uses direnv to load and unload environment variables depending on the current directory

brew install direnv

First time you cd into this project you will be prompted to run:

direnv allow
Dependencies

To install dependencies, run:

uv sync
Linting, formatting

This project uses ruff. Ruff is written in Rust, designed to be extremely fast and efficient

# Lint files or directories
ruff check ./src

# Format files
ruff format ./src

# Fix issues automatically
ruff check --fix ./src
  • (optional) in VSCode you can install the Ruff extension (+ uninstall Black)
Running and debugging
  • start the server in dev mode
uv run fastapi dev src/main.py --host 127.0.0.1 --port 8088

OR,

uv run fastapi dev src/simple_integration.py --host 127.0.0.1 --port 8088
  • start the MCP inspector
npx @modelcontextprotocol/inspector http://127.0.0.1:8088/mcp
  • open the inspector in the browser http://127.0.0.1:5173
  • in the left panel:
    • Transport Type: SSE
    • URL: http://127.0.0.1:8088/mcp
    • click on Connect

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.