← Discover
GitHub · modelcontextprotocol/servers↑ +50 today

Sample servers for artificial intelligence agents

Model Context Protocol (MCP) servers enable generative artificial intelligence models to access external data sources and tools through a standard interface. This protocol allows different artificial intelligence applications to securely and consistently connect with databases or software tools.

Updates

  • October 25, 2026: Stars 91,368 → 91,545, latest release v2.1.0 (October 25, 2026).
  • October 19, 2026: Stars 91,136 → 91,368, latest release v2.0.0 (October 19, 2026).
  • October 11, 2026: Stars 90,905 → 91,136, latest release v1.0.0 (October 11, 2026).
  • October 1, 2026: Stars 90,906 → 90,905, latest release 2026.8.31 (August 31, 2026).

What you get

  • You ensure your large language models (LLMs) securely access local files, data stores, and persistent memory.
  • You can connect your artificial intelligence applications with external data sources by examining reference server examples.
  • You access ready-made templates to develop your own servers using different software development kits (SDKs).

Installation

Installing and starting the Git server
# With uvx
uvx mcp-server-git

# With pip
pip install mcp-server-git
python -m mcp_server_git

Running it

Running the memory server
npx -y @modelcontextprotocol/server-memory

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to connect my artificial intelligence model to external data sources using Model Context Protocol (MCP) reference servers. First, guide me in starting the memory server with the npx -y @modelcontextprotocol/server-memory command and configuring the desktop client setup. Also, explain the steps to provide access to code repositories using the uvx mcp-server-git command.

Repository: https://github.com/modelcontextprotocol/servers. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

SDKContextMCPLLMArtificial Intelligence
Who it is forIt is intended for developers who want to securely integrate artificial intelligence models with external tools such as local files, memory, and code repositories.

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-10-01: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.