LaTeX PDF MCP Server
Converts LaTeX source code into professionally formatted PDF documents.
LaTeX PDF MCP Server
A Model Context Protocol (MCP) server that provides tools for converting LaTeX source code into PDF documents. This server enables AI assistants to generate high-quality PDF documents from LaTeX markup with professional formatting capabilities.
Features
- LaTeX to PDF Conversion: Convert LaTeX source code directly to PDF format
- Professional Document Generation: Supports all standard LaTeX features for academic and professional documents
- Local File Generation: Creates PDF files in a specified directory for easy access
- HTTP Server Integration: Generates downloadable links for created PDFs
- Error Handling: Comprehensive error reporting for LaTeX compilation issues
Prerequisites
Before using this MCP server, ensure you have:
- Node.js (version 18 or higher)
- LaTeX Distribution: A complete LaTeX installation such as:
- latexmk: Usually included with LaTeX distributions
Installation
From npm (Recommended)
npm install -g latexpdf-mcp
From Source
- Clone the repository:
git clone https://github.com/ihor-sokoliuk/latexpdf-mcp.git
cd latexpdf-mcp
- Install dependencies:
pnpm install
- Build the project:
pnpm run build
Configuration
Claude Desktop Configuration
Add the server to your Claude Desktop configuration file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"latexpdf-mcp": {
"command": "latexpdf-mcp",
"env": {
"LATEXPDF_OUTPUT_DIR": "/path/to/your/pdf/directory"
}
}
}
}
Output Directory
By default, PDFs are generated in: C:\Users\Admin\Documents\GeneratedPDF
You can customize the output directory by setting the LATEXPDF_OUTPUT_DIR environment variable in your MCP configuration.
Example configurations:
Windows:
{
"mcpServers": {
"latexpdf-mcp": {
"command": "latexpdf-mcp",
"env": {
"LATEXPDF_OUTPUT_DIR": "C:\\Users\\YourName\\Documents\\MyPDFs"
}
}
}
}
macOS/Linux:
{
"mcpServers": {
"latexpdf-mcp": {
"command": "latexpdf-mcp",
"env": {
"LATEXPDF_OUTPUT_DIR": "/home/yourname/Documents/PDFs"
}
}
}
}
Usage
Once configured, you can use the server through your MCP-compatible client:
Available Tools
create_pdf
Converts LaTeX source code into a PDF document.
Parameters:
file_name(string, required): Name of the output PDF file (must end with .pdf)latex_source(string, required): LaTeX source code to convert
Example:
\documentclass{article}
\usepackage[utf8]{inputenc}
\title{Sample Document}
\author{Your Name}
\date{\today}
\begin{document}
\maketitle
\section{Introduction}
This is a sample LaTeX document generated via MCP.
\subsection{Features}
\begin{itemize}
\item Professional formatting
\item Mathematical expressions: $E = mc^2$
\item Cross-references and citations
\end{itemize}
\end{document}
PDF Access
After generating a PDF, you can access it via HTTP server:
- Navigate to the output directory (default:
C:\Users\Admin\Documents\GeneratedPDF, or your customLATEXPDF_OUTPUT_DIR):
cd [YOUR_OUTPUT_DIRECTORY]
- Start a local HTTP server:
python -m http.server
- Access your PDFs at
http://localhost:8000/[filename].pdf
The server automatically provides download links in this format when PDFs are generated.
Development
Project Structure
latexpdf-mcp/
├── index.ts # Main server implementation
├── package.json # Package configuration
├── tsconfig.json # TypeScript configuration
├── pnpm-lock.yaml # Dependency lock file
└── dist/ # Compiled JavaScript output
Building
pnpm run build
Development Mode
pnpm run watch
Troubleshooting
Common Issues
- LaTeX not found: Ensure LaTeX is properly installed and
latexmkis in your PATH - Permission errors: Check write permissions for the output directory
- Compilation errors: Review LaTeX syntax and required packages
Error Messages
The server provides detailed error messages for:
- Missing LaTeX installation
- Compilation failures
- File system permissions
- Invalid input parameters
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
This project is licensed under the MIT License. See the LICENSE file for details.
Links
- Repository: https://github.com/ihor-sokoliuk/latexpdf-mcp
- Issues: https://github.com/ihor-sokoliuk/latexpdf-mcp/issues
- Model Context Protocol: https://modelcontextprotocol.io
Author
Ihor Sokoliuk - GitHub Profile
This MCP server enables seamless LaTeX to PDF conversion within AI-assisted workflows, perfect for generating academic papers, technical documentation, and professional reports.
Related Servers
Scout Monitoring MCP
sponsorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Ollama MCP Server
Integrates Ollama's local LLM models with MCP-compatible applications. Requires a local Ollama installation.
MCP OAuth Sample
A sample MCP OAuth server implementation using Next.js, providing OAuth 2.1 authentication with Google and PostgreSQL.
Figma
Interact with the Figma API to access and manage design files and resources.
BloodHound-MCP
integration that connects BloodHound with AI through MCP, allowing security professionals to analyze Active Directory attack paths using natural language queries instead of Cypher.
Local Logs MCP Server
MCP for monitoring local application logs with real-time tailing, error tracking, and log search capabilities.
Moralis Web3 API
Interact with the Moralis Web3 API to access blockchain data across multiple networks through a structured interface.
Fluent (ServiceNow SDK)
Manage ServiceNow metadata, modules, records, and tests using Fluent, a TypeScript-based declarative DSL. Supports all ServiceNow SDK CLI commands.
REPL MCP Server
A universal REPL session manager supporting Python, Node.js, Ruby, and more, with session management and LLM-assisted recovery.
ndlovu-code-reviewer
Manual code reviews are time-consuming and often miss the opportunity to combine static analysis with contextual, human-friendly feedback. This project was created to experiment with MCP tooling that gives AI assistants access to a purpose-built reviewer. Uses the Gemini cli application to process the reviews at this time and linting only for typescript/javascript apps at the moment. Will add API based calls to LLM's in the future and expand linting abilities. It's also cheaper than using coderabbit ;)
Remote MCP Server (Authless)
An example of a remote MCP server without authentication, deployable on Cloudflare Workers.