Typst MCP Server

If you want an AI assistant working directly with Typst MCP, the typst mcp mcp server is the bridge. A Model Context Protocol (MCP) server that provides Typst documentation to Claude Code and other MCP clients.

What Typst MCP does

A Model Context Protocol (MCP) server that provides Typst documentation to Claude Code and other MCP clients.

Tools it exposes

Once connected, the assistant can call these 5 tools directly:

• Tools — The Tools tool exposed by this server
• typst_search — Search through Typst documentation for specific topics, functions, or syntax
• typst_browse — Browse the Typst documentation structure as a hierarchical tree
• typst_read — The typst_read tool exposed by this server
• Development — The Development tool exposed by this server

Installing the typst mcp mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Requirements

• Python 3.12 or higher - uv package manager

Where it fits

Knowledge and memory servers address the most frustrating trait of language models — walking into every conversation with no recollection of the last one. Typst MCP sits in that group, and the shape of its toolset — Tools, typst_search, typst_browse among others — tells you what it is really for. Worth comparing against the other knowledge memory servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

• This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
• Maintained by FujishigeTemma, written in Python.
• MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the typst mcp mcp server actually does with your data.
• Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.