mlx-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mlx-mcplook up how to quantize a model with MLX LM in the docs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mlx-mcp
mlx-mcp gives Claude Code, Codex and other coding agents the MLX, MLX Data and MLX LM docs, so your agent can check the docs before it writes MLX code instead of working from memory.
It runs on your Mac, needs no account or API key, and works offline after the first search.
An independent project, not affiliated with Apple or the MLX maintainers.
Maintained by Alfredo Sandoval and Joseph Sandoval.
Install
You need an Apple silicon Mac with macOS 14 or later, and uv.
Add mlx-mcp to your agent below. Every client runs the same command,
uvx --python 3.13 mlx-mcp serve, so there's nothing else to install. uv
downloads Python 3.13 if you don't have it.
Claude Code
claude mcp add --scope user mlx-docs -- uvx --python 3.13 mlx-mcp serveCodex
codex mcp add mlx-docs -- uvx --python 3.13 mlx-mcp serveCursor
Or add it by hand in ~/.cursor/mcp.json:
{
"mcpServers": {
"mlx-docs": {
"command": "uvx",
"args": ["--python", "3.13", "mlx-mcp", "serve"]
}
}
}VS Code
Or add it by hand in .vscode/mcp.json:
{
"servers": {
"mlx-docs": {
"type": "stdio",
"command": "uvx",
"args": ["--python", "3.13", "mlx-mcp", "serve"]
}
}
}Other MCP clients
Add a stdio server named mlx-docs that runs this command:
{
"command": "uvx",
"args": ["--python", "3.13", "mlx-mcp", "serve"]
}Related MCP server: context
Use it
Ask your agent, for example: "Use mlx-mcp to port this code to MLX."
Your agent can also check which docs versions mlx-mcp has, and every page it reads says which version it's from.
Your agent starts mlx-mcp when it needs it. The first start downloads about 65 MB, mostly MLX, and the first search downloads the 90 MB search model. After that it works offline.
Update
uvx --python 3.13 mlx-mcp@latest --versionThen start a new agent session.
Uninstall
Remove mlx-docs from each agent you connected:
Claude Code:
claude mcp remove --scope user mlx-docsCodex:
codex mcp remove mlx-docsCursor, VS Code and other clients: delete the
mlx-docsentry.
Then delete ~/.cache/mlx-mcp to free the space.
If something doesn't work
Run uvx --python 3.13 mlx-mcp prepare and start a new session. It downloads
anything missing and checks that search and fetch work. If that doesn't fix
it, open an issue with
what the command printed.
If Cursor, VS Code or another app can't find uvx, run command -v uvx in a
terminal and use the path it prints as the command.
Good to know
The bundled docs may not match the MLX version you have installed.
uvx --python 3.13 mlx-mcp infoshows the versions mlx-mcp has.uvx --python 3.13 mlx-mcp prepare --refreshdownloads the latest MLX and MLX Data docs. MLX LM stays at its bundled version. Start a new session after refreshing.mlx-mcp has the published docs, not the MLX source code. The docs don't always say which kernel or device runs an operation. For that, read the MLX source or measure it.
uvx --python 3.13 mlx-mcp --helplists the commands.
License
MIT. Includes text from the MLX, MLX Data and MLX LM projects, © Apple Inc., under the MIT License. See the third-party notices. To report a security problem, see Security.
This server cannot be deployed
Maintenance
Related MCP Connectors
Token-efficient search for coding agents over public and private documentation.
The documentation, as a tool your agent can call: 950+ AI-dev guides. Search + fetch tools.
Search GitHub, npm, PyPI, StackOverflow, ArXiv from one MCP — built for coding agents.
Read-only search and Markdown pages from the OpenPlanr docs, for coding agents.
Related MCP Servers
- MIT
- AlicenseNot gradedqualityCmaintenanceProvides up-to-date documentation for AI agents by locally querying a community-driven registry of pre-built docs packages.Apache 2.0
- AlicenseAqualityBmaintenanceProvides fast, token-efficient search over coding agent documentation (e.g., Claude Code, Cursor) using local SQLite FTS5 indexing, with tools for searching snippets, reading pages, and grepping markdown.5MIT
- AlicenseNot gradedqualityFmaintenanceEnables AI coding agents to search, index, and manage documentation libraries with hybrid retrieval and live web fallback, all self-hosted and offline.1MIT