MCP Reference Servers
The official collection of reference servers and example implementations maintained by the Model Context Protocol project.
Project overview
The official collection of reference servers and example implementations maintained by the Model Context Protocol project. Its core areas include Filesystem, Git, Fetch, Protocol testing. Start with the repository documentation and the smallest practical scope before adopting it broadly.
Core capabilities
Filesystem
Exposes Filesystem to compatible clients through MCP tools.
Git
Exposes Git to compatible clients through MCP tools.
Fetch
Exposes Fetch to compatible clients through MCP tools.
Protocol testing
Exposes Protocol testing to compatible clients through MCP tools.
Setup and connection
This usage path is based on the current public documentation for MCP Reference Servers. Complete the steps in order before using it from your agent.
Let an AI Agent install it
Send this prompt to Codex, Claude Code, or another AI agent that can work with your local environment.
Help me install this MCP: MCP Reference Servers
Project URL: https://github.com/modelcontextprotocol/servers
Read the README and installation files first, confirm the current environment and target directory, then follow the project's documented installation method. Run a minimal verification task afterward and report the install location, steps, and result. Ask before requesting credentials, additional permissions, overwriting files, or performing risky actions.- Prepare a compatible agent or runtime
- Confirm access to the local files or services required by the project
Project URL: https://github.com/modelcontextprotocol/servers/tree/main/src
Copy the URL and follow the steps below to complete setup.- 1Apply the configuration
Use the command or configuration above to add the resource to the current agent environment.
- 2Complete required setup
Complete path, permission, or connection settings for the current runtime.
- 3Run a minimal task
Run a minimal task in the agent. If the resource is recognized and returns the documented type of result, the setup is active.
Run a minimal task in the agent. If the resource is recognized and returns the documented type of result, the setup is active.
- Reference implementations are not the same as production hosted services.
- Each component's status must be reviewed separately.
Use cases
You need to connect an AI agent to tools, browsers, code, or data through MCP
Your current task needs Filesystem or Git
Assessment
Why it may be useful
- You need to connect an AI agent to tools, browsers, code, or data through MCP
- Your current task needs Filesystem or Git
What to know first
- Reference implementations are not the same as production hosted services.
- You want to use it in production without reading the repository documentation or reviewing permissions
README
MCP Reference Servers
Overview
The official collection of reference servers and example implementations maintained by the Model Context Protocol project. Model Context Protocol Servers.
Getting started
- This usage path is based on the current public documentation for MCP Reference Servers. Complete the steps in order before using it from your agent.
- Project focus: The official collection of reference servers and example implementations maintained by the Model Context Protocol project.
- Published characteristics: Reference implementations, Multiple servers, Some components archived.
- Run a minimal task in the agent. If the resource is recognized and returns the documented type of result, the setup is active.
Configuration
Project URL: https://github.com/modelcontextprotocol/servers/tree/main/src
Copy the URL and follow the steps below to complete setup.