data-ai MCP Server
Typst MCP Server is an MCP (Model Context Protocol) implementation that helps AI models interact with Typst, a markup-based typesetting system. The server provides tools for converting between LaTeX and Typst, validating Typst syntax, and generating images from Typst code.
Discovered via unknown and last synced 4d ago.
1. Install the package
docker run --rm -i ghcr.io/johannesbrandenburger/typst-mcp:latest
2. Add to claude_desktop_config.json
{
"mcpServers": {
"typst-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/johannesbrandenburger/typst-mcp:latest"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
sending complex Typst illustrations to the user, the LLM should render the code to an image and check if it looks correct.
LLM should select the relevant chapter to read based on the task at hand.
relevant for multi modal models.
available as `check_if_snippets_are_valid_typst_syntax(typst_snippets: list)` for validating multiple Typst snippets at once.
the LLM get an overview of the documentation and select a chapter to read.
are better at writing LaTeX than Typst, so this tool helps convert LaTeX code to Typst.
on the chapter selected by the LLM, this tool retrieves the content of the chapter.
Description
Label for trace events (e.g. `cryo-lab`, `ai-lab`). Default: `default`
Directory to write JSONL trace logs. Tracing disabled if unset.
Directory for ontology node YAML files. Ontology disabled if unset.
Description
Compile a `.typ` or `.tex` file to PDF. Returns structured errors.
Parse section tree with IDs, levels, line ranges, and word counts.
Extract raw source + plain text for a named section.
Map a source line number → PDF page + section.
Map a PDF page → source sections with line ranges.
Replace section content. Auto-backs up; rolls back on compile failure.
Insert a paragraph at `start`, `end`, or paragraph-N within a section.
Find unused keys, missing keys, and duplicates in a `.bib` file.
Heuristic review: completeness, citations, clarity, consistency.
Section-level diff between two documents.
List all figures, captions, source files, and where each is referenced.
Write a document as a YAML ontology node. Requires `TYPST_MCP_ONTOLOGY_DIR`.
Typst
✓
✓ BibTeX / Hayagriva