MCP servers · modelcontextprotocol

MCP reference servers

Seven small example servers maintained by the Model Context Protocol project: files, Git, web fetching, memory, time, step-by-step thinking and a test server.

What it does

This collection shows how MCP servers are meant to work. It contains seven reference servers: Filesystem (read and write files in folders you allow), Git (read, search and change repositories), Fetch (download a web page and convert it for the model), Memory (a simple knowledge graph that persists between chats), Time (time zones and conversions), Sequential Thinking (structured, revisable reasoning steps) and Everything (a test server that exercises every protocol feature).

The TypeScript servers start with npx and the Python ones with uvx or pip. They are a good way to learn MCP or to try a client, and a starting point when you build your own server with one of the official SDKs.

Limitations and requirements

The maintainers describe these as educational reference implementations, not production-ready software: review your own security needs before use. Filesystem and Git can change files; Fetch can request any URL the machine can reach, including local network addresses. Many older servers (GitHub, Slack, PostgreSQL and others) were moved to an archived repository and are no longer maintained here. Licence: new code Apache-2.0, some older contributions remain MIT.

Safety

Our team reviewed what this resource runs and the permissions it needs before publishing. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Claude Plugins Radar first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source
    GitHub preview card for iliasabk/claude-plugins-radar
    Preview card provided by GitHub
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
firecrawl

Firecrawl MCP Server (web search and scraping)

Firecrawl's MCP server that lets an AI assistant search the web, turn pages and PDFs into clean Markdown, crawl sites and interact with dynamic pages.

7.8K GitHub starsWeb, search & browserProductivity & automation
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
docker

Docker Hub MCP Server

Docker's MCP server that helps an AI assistant find and compare container images on Docker Hub and, with your token, manage your own repositories and tags.

171 GitHub starsCloud & DevOpsSoftware development
Updated 13 Nov 2026