MCP Servers

mcpserver-local

A local Python MCP server that provides basic tools like greet, add_numbers, and system_info, designed for process-based connections via stdin/stdout.

Category

README

Local MCP Server

This project is a small Python MCP server implemented with mcp and managed with uv. It is bootstrapped / created entirely using Copilot agent with mcp-server-dev SKILLS.

Launch the server

From the repository root:

cd <project folder>
uv run mcpserver-local

This starts the MCP server using the default MCP transport, which is the stdio transport.

Quick local test

A simple CLI helper is available for manual testing:

uv run mcpserver-local-cli greet Ada
uv run mcpserver-local-cli add_numbers 2 3
uv run mcpserver-local-cli system_info
uv run mcpserver-local-cli help

How a client / agent connects

The server is designed for local process-based connection via stdin/stdout. A client or agent can spawn uv run mcpserver-local and exchange MCP messages over the process pipes.

Local client pattern

A typical client uses a subprocess to launch the server and then sends/receives MCP frames on stdin/stdout.

Example pseudo-code:

import subprocess

proc = subprocess.Popen(
    ["uv", "run", "mcpserver-local"],
    stdin=subprocess.PIPE,
    stdout=subprocess.PIPE,
    stderr=subprocess.PIPE,
    text=True,
)

# exchange MCP JSON/RPC frames with proc.stdin / proc.stdout
# depending on the MCP client implementation

Notes

mcpserver-local-cli is a convenience tool for local testing, not a transport endpoint for external MCP clients.
If you need network access later, the server can be extended with a transport that supports TCP or websockets.

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.

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.

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.

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.