johannesbrandenburger/typst-mcp

Overview

Typst MCP Server is an MCP implementation that enables AI models to interact with Typst, a markup-based typesetting system. It provides tools for converting between LaTeX and Typst, validating Typst syntax, and generating images from Typst code.

Best for

Best for
Developers building AI tools that need to generate or process Typst documents

Use cases

• Converting LaTeX documents to Typst format for AI-assisted typesetting
• Validating Typst syntax in AI-generated content before rendering
• Generating preview images from Typst code for visual feedback

How to use

Tools exposed

• list_docs_chapters
• get_docs_chapter
• latex_snippet_to_typst
• check_if_snippet_is_valid_typst_syntax
• typst_to_image

Tested with

Claude Desktop, Cursor, VS Code, Roo Code, OpenCode, Claude Code

Example client config

{\n  "mcpServers": {\n    "typst": {\n      "command": "docker",\n      "args": [\n        "run", "--rm", "-i",\n        "ghcr.io/johannesbrandenburger/typst-mcp:latest"\n      ]\n    }\n  }\n}

Notes

Typst MCP Server is an MCP implementation that enables AI models to interact with Typst, a markup-based typesetting system. It provides tools for converting between LaTeX and Typst, validating Typst syntax, and generating images from Typst code.

157 stars on GitHub. Last updated 2026-04-18. Licensed MIT.

Use cases

• Converting LaTeX documents to Typst format for AI-assisted typesetting
• Validating Typst syntax in AI-generated content before rendering
• Generating preview images from Typst code for visual feedback

Pros

• Open source with 157 stars on GitHub
• Python-based, easy to integrate into AI workflows
• Supports multiple Typst operations through a single MCP server

Cons

• Requires a Python environment to run
• Limited to Typst ecosystem, not a general typesetting tool
• Conversion quality may vary for complex LaTeX documents

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.