Test MCP Server
A basic MCP server implementation for testing purposes. Communicates via stdio and is designed to work with MCP-compliant clients.
README
MCP Server for local development context
Description
This project is designed to facilitate the usage of MCP-compliant clients such as Claude Code, Claude Desktop, Google Gemini, etc.
By having this local MCP server running and configured with an MCP client, you essentially allow the client access the the tools and resources that server.py exposes.
This allows, for example, your MCP client to be able to run certain git commands on your computer, and receive the output so that it can gain context.
There are ambitious plans to expand this project to analyze code significantly, including plans to expose the python dis module so that the client can view bytecode generated from different code segments and replace it to increase different metrics.
Prerequisites
- Python 3.10 or higher.
uv(recommended for dependency management) orpip.
Installation
-
Clone the repository:
git clone <repository-url> cd mcp_test -
Install dependencies:
# Using Python 3.10 or higher with pyenv pyenv install 3.10.0 pyenv local 3.10.0 # Using uv uv venv source .venv/bin/activate uv pip install -r requirements.txt # OR using pip python3 -m venv .venv source .venv/bin/activate pip install -r requirements.txt
Usage
Allow MCP client to run the server using Python: TODO: UPDATE WITH CLAUDE CODE & GOOGLE ANTIGRAVITY SPECIFIC INSTRUCTIONS
The server listens on `stdio` by default. It assumes an MCP-compliant client will start it and communicate via standard input/output.
Commit Pattern
According to Google, there are 11 types of commits (listed below).
Please mark the beginning of your commit with an identifier string indicating what type of commit it is.
This helps keep track of the development cadence and is also useful for extracting relevant information
from commit history. I also realize I am talking to myself here lol.
Example: git commit -m "docs: Adding documentation because I am a responsible engineer"
feat: Introduces a new feature.
fix: Patches a bug in the code.
docs: Changes to documentation only (README, comments).
style: Formatting, whitespace, missing semicolons; no code change in meaning.
refactor: Restructures code without changing functionality (neither a feature nor a fix).
perf: Improves performance.
test: Adds or corrects tests.
build: Changes affecting the build system or external dependencies (npm, webpack).
ci: Changes to CI configuration files and scripts (GitHub Actions, Jenkins).
chore: Maintenance tasks, updating dependencies, build process changes that don't touch src or test files.
revert: Reverts a previous commit.
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.