- Home
- MCP servers
- LaTeX
LaTeX
- python
4
GitHub Stars
python
Language
5 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"robertodure-mcp-latex-server": {
"command": "python",
"args": [
"la tex_server.py"
],
"env": {
"LATEX_BASE_PATH": "C:\\path\\to\\your\\latex\\files",
"LATEX_LOG_LEVEL": "INFO"
}
}
}
}You can use the MCP LaTeX Server to create, edit, read, and validate LaTeX documents from your AI assistant or editor. It centralizes LaTeX file management and ensures you can generate professional documents with predefined templates, package handling, and syntax checks.
How to use
You connect your MCP client to the LaTeX server to perform actions such as creating new LaTeX documents, editing existing files, reading content, listing files, and validating syntax. Start by configuring either Claude Desktop or your editor to communicate with the local MCP server. Use the available tools to perform practical tasks like generating an article with a specified document class, inserting sections, or applying edits across your LaTeX projects. You can also enumerate documents in a directory, inspect their content, and verify that the LaTeX code is syntactically sound before compiling.
How to install
# Prerequisites
- Python 3.8+
- LaTeX distribution installed (see steps below)
- VS Code (optional, for editor integration)
- Claude Desktop or Claude in VS Code (optional, for MCP integration)
# Quick setup
# 1) Clone the project
git clone https://github.com/RobertoDure/mcp-latex-server
cd mcp-latex-server
# 2) Install dependencies (quick setup)
python setup.py
# 3) Verify installation
python latex_server.py --help
Additional sections
Configuration and integration details are provided below to help you run the server smoothly with MCP clients. You can set environment variables to customize base paths and logging. A JSON configuration file allows you to lock down base directories, allowed file types, and default document settings. You can start the server using a Python command, or through the UV-based runtime for faster startup.
Configuration
Available configuration options help you tailor the server to your workspace. You can set the LaTeX base path, enable or disable validation, and choose a default document class and common packages. The environment variables and a sample config.json provide concrete, reproducible defaults.
Troubleshooting
If the server won’t start, verify your Python version is 3.8 or newer and that dependencies are installed. Run with debug logging to identify initialization issues. If your client cannot connect, confirm the MCP server configuration paths, ensure Python is on your PATH, and restart the client after changes. For permission or LaTeX issues, check file permissions and ensure your LaTeX distribution is correctly installed and up to date.
Notes
The server supports a built-in template system, automatic package handling, and basic LaTeX syntax validation. It is designed to coordinate with AI assistants to produce structured LaTeX documents such as articles, reports, books, letters, beamer presentations, and minimal documents.
Available tools
create_latex_file
Creates a new LaTeX document with specified parameters such as file path, document type, title, author, date, packages, geometry, and content.
edit_latex_file
Edits an existing LaTeX file using operations like replace, insert_before, insert_after, append, or prepend.
read_latex_file
Reads and returns the contents of a LaTeX file.
list_latex_files
Lists all LaTeX files in a directory, with options to search recursively.
validate_latex
Performs basic LaTeX syntax validation to detect common errors.
get_latex_structure
Extracts the document structure including sections and subsections.