LaTeX MCP Server

An MCP (Model Context Protocol) server that can supercharge your VSCode + LaTex Workshop writing workflow

Currently houses MCP tools, and new tools can be easily added in either Python and TypeScript. The Python process is the MCP server; selected tools are delegated to a small Node/TypeScript module via a bridge.

LaTex MCP Server + Copilot/Claude/Cursor, what can you do?

• Read your cited papers, verify / add onto your claims
• Access your python scripts to generate new figures / latex tables based on your experiment data, and place them into latex autonomously
• Can verify every step and ensure your pdf compiles
• Functionally it can autonomously take your outline + experimental results and turn it into a paper (may looks like slop though)

Your browser does not support the video tag.

Python Tools

• list_tex_files
  Lists all .tex files under your LaTeX workspace (relative paths). Useful for LLMs or agents to discover available chapters and sections.

• read_file
  Reads a text or binary-safe slice of a file given a relative path inside the workspace. Supports specifying a maximum number of bytes to return.

• extract_bibliography
  Parses a BibTeX file and returns structured entry metadata, including download URLs (DOI, arXiv). Helps agents or scripts work with citation data programmatically.

• download_bibliography
  Downloads PDFs for bibliography entries listed in resources/cited_papers/index.json. Can force re-downloads and limit the number of new downloads.

• compile_latex
  Runs LaTeX compilation (pdflatex/xelatex via latexmk) on the main document and returns success plus a log snippet. Supports specifying the entry .tex file and number of passes.

• read_pdf
  Extracts text and metadata from a PDF filepath using pypdf, with page and character limits. Stores a JSON artifact for downstream use.

• read_pdf_from_citation
  Resolves a citation key via resources/cited_papers/index.json to its PDF and extracts text (auto-downloads if needed). Returns extracted text, metadata, and the citation key.

TypeScript Bridge Tools

• summarize_text
  Produces a concise natural language summary of provided LaTeX or text content. Accepts a maximum sentence count for the summary.

• suggest_bib_key
  Suggests a stable BibTeX key based on authors, year, and title metadata. Useful for generating consistent citation keys.

Install (with uv)

From the repository root:

cd latex-mcp-server
uv tool install -e .

or

uv tool install -e ./latex-mcp-server

This will make the console script latex-mcp-server available on your PATH.

If you prefer a one-off run without installing as a tool:

uv run latex-mcp-server

MCP Configuration Snippet

Add to your mcp.json (VS Code / Claude Desktop user settings):

"latex-mcp-server": {
  "command": "uv",
  "args": ["tool", "run", "latex-mcp-server", "--workspace", "ABSOLUTE_PATH_TO_YOUR_PROJECT_ROOT"]
}

If you omit --workspace, the server will infer the current working directory.

Windows example

On Windows (PowerShell / Bash), if your paper_1 root is at C:\Users\User\projects\paper_1, use:

"latex-mcp-server": {
  "command": "uv",
  "args": [
    "tool", "run", "latex-mcp-server",
    "--workspace", "C:/Users/User/projects/paper_1"
  ]
}

Forward slashes are fine; they avoid the need to escape backslashes. Be sure to replace the placeholder ABSOLUTE_PATH_TO_YOUR_PAPER_1_ROOT — leaving a placeholder like WORKSPACE_FOLDER_PATH will cause the runtime error:

Workspace does not exist: C:\Users\User\WORKSPACE_FOLDER_PATH\PAPER_1

Alternative: Install once, then call directly

After running:

cd latex-mcp-server
uv tool install -e .

You can simplify the config to:

... View full README on GitHub