Reference implementations for the Model Context Protocol.
This repository houses reference implementations for the Model Context Protocol (MCP), showcasing its features and SDK usage. It serves as an educational resource for developers looking to build their own MCP servers. The MCP provides secure and controlled access for Large Language Models (LLMs) to various tools and data sources.
·
This repository is a collection of reference implementations for the Model Context Protocol (MCP), as well as references to community-built servers and additional resources.
[!IMPORTANT] If you are looking for a list of MCP servers, you can browse published servers on the MCP Registry. The repository served by this README is dedicated to housing just the small number of reference servers maintained by the MCP steering group.
[!WARNING] The servers in this repository are intended as reference implementations to demonstrate MCP features and SDK usage. They are meant to serve as educational examples for developers building their own MCP servers, not as production-ready solutions. Developers should evaluate their own security requirements and implement appropriate safeguards based on their specific threat model and use case.
The servers in this repository showcase the versatility and extensibility of MCP, demonstrating how it can be used to give Large Language Models (LLMs) secure, controlled access to tools and data sources. Typically, each MCP server is implemented with an MCP SDK:
These servers aim to demonstrate MCP features and the official SDKs.
The following reference servers are now archived and can be found at servers-archived.
@brave/brave-search-mcp-server).TypeScript-based servers in this repository can be started with npx.
For example, this will start the Memory server:
npx -y @modelcontextprotocol/server-memoryPython-based servers in this repository can be started with uvx or pip. uvx is recommended for ease of use and setup.
For example, this will start the Git server:
# With uvx
uvx mcp-server-git
# With pip
pip install mcp-server-git
python -m mcp_server_gitFollow these instructions to install uv / uvx and these to install pip.
However, running a server on its own isn't very useful, and should instead be configured into an MCP client. For example, here's the Claude Desktop configuration to use the above server:
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-memory"]
}
}
}On Windows, wrap npx with cmd /c:
{
"mcpServers": {
"memory": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@modelcontextprotocol/server-memory"]
}
}
}Additional examples of using the Claude Desktop as an MCP client might look like:
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/allowed/files"]
},
"git": {
"command": "uvx",
"args": ["mcp-server-git", "--repository", "path/to/git/repo"]
},
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
}On Windows, apply the same wrapper to the npx-based filesystem entry above by changing its "command" to "cmd" and prepending "/c", "npx" to its existing args. Leave the uvx entries unchanged.
An MCP server talks to its client over a transport. The protocol defines two standard ones, and they run very differently:
| Transport | How the server runs | How a client reaches it |
|---|---|---|
| stdio | The client launches the server as a subprocess and talks to it over the process's stdin and stdout. The server opens no port. | A command and args in the client's configuration, as in the examples above |
| Streamable HTTP | The server runs on its own as an HTTP service, and can serve many clients | A URL, such as http://localhost:3001/mcp |
Every server in this repository serves stdio, and only Everything also serves Streamable HTTP (its README shows how to start it that way, and covers its deprecated HTTP+SSE transport too). So when you run uvx mcp-server-git or npx -y @modelcontextprotocol/server-memory in a terminal, it opens no port, prints at most a one-line startup notice, and then appears to hang. That is expected: it is waiting for a client to send it messages on stdin. You do not normally start a stdio server yourself; your MCP client starts it from its configuration and stops it when it is done.
To try a server without setting up a client, use the MCP Inspector. Given a stdio server's command, it launches the server for you and lets you browse and call its tools; given a URL, it connects to a running Streamable HTTP server:
# A stdio server: the Inspector launches it
npx @modelcontextprotocol/inspector uvx mcp-server-git
# A Streamable HTTP server: start it first, then connect to its URL
npx @modelcontextprotocol/server-everything streamableHttp
npx @modelcontextprotocol/inspector --transport http --server-url http://localhost:3001/mcpFor more, see the transport layer in the MCP architecture overview, and Transports in the specification.
Interested in creating your own MCP server? Visit the official documentation at modelcontextprotocol.io for comprehensive guides, best practices, and technical details on implementing MCP servers.
See ADDITIONAL.md for a curated list of frameworks and resources that simplify building MCP servers and clients.
See CONTRIBUTING.md for information about contributing to this repository.
See RELEASING.md for how packages are published (OIDC trusted publishing from CI — no registry tokens) and how to retry a failed publish.
See SECURITY.md for reporting security vulnerabilities.
This project is licensed under the Apache License, Version 2.0 for new contributions, with existing code under MIT - see the LICENSE file for details.
If you find MCP servers useful, please consider starring the repository and contributing new servers or improvements!
Managed by Anthropic, but built together with the community. The Model Context Protocol is open source and we encourage everyone to contribute their own servers and improvements!
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add memory -- npx -y @modelcontextprotocol/server-memory{
"mcpServers": {
"memory": {
"args": [
"-y",
"@modelcontextprotocol/server-memory"
],
"command": "npx"
}
}
}code --add-mcp '{"name":"memory","args":["-y","@modelcontextprotocol/server-memory"],"command":"npx"}'[mcp_servers.memory]
command = "npx"
args = ["-y", "@modelcontextprotocol/server-memory"]Runs locally on your device. Your client starts the server itself, so nothing has to be hosted.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/model-context-protocol-servers to learn what the "Model Context Protocol Servers" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
npx -y @modelcontextprotocol/server-memory
npx @modelcontextprotocol/inspector uvx mcp-server-git
npx @modelcontextprotocol/server-everything streamableHttp
npx @modelcontextprotocol/inspector --transport http --server-url http://localhost:3001/mcpuvx mcp-server-git| Name | What it does |
|---|---|
create_entities | Create multiple new entities in the knowledge graph |
create_relations | Create multiple new relations between entities in the knowledge graph. Relations should be in active voice |
add_observations | Add new observations to existing entities in the knowledge graph |
delete_entities | Delete multiple entities and their associated relations from the knowledge graph |
delete_observations | Delete specific observations from entities in the knowledge graph |
delete_relations | Delete multiple relations from the knowledge graph |
read_graph | Read the entire knowledge graph |
search_nodes | Search for nodes in the knowledge graph based on a query |
open_nodes | Open specific nodes in the knowledge graph by their names |
| Name | What it does |
|---|---|
knowledge-graph | The full knowledge graph with all entities and relations |
Read live from the server on September 22, 2026.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/model-context-protocol-servers)Nothing comparable is listed yet.
v2.4.0Release notesv2.3.0Release notesv2.2.0Release notesv2.1.0Release notesv2.0.0Release notesv1.0.0Release notes2026.8.31Release 2026.8.31Release notes2026.8.18Release 2026.8.18Release notes2026.7.10Release 2026.7.10Release notes2026.7.4Release 2026.7.4Release notes2026.1.26Release 2026.1.26Release notes2026.1.14Release 2026.1.14Release notes2025.12.18Release 2025.12.18Release notes2025.11.25Release 2025.11.25Release notes2025.9.25Release 2025.9.25Release notes2025.8.4Release 2025.8.4Release notes2025.7.1Release 2025.7.1Release notes2025.4.24Release 2025.4.24Release notes2025.4.6Release 2025.4.6Release notes2025.1.17Release 2025.1.17Release notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "model-context-protocol-servers" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.