OverleafMCP MCP Server

MCP server that lets AI assistants read Overleaf projects, parse LaTeX document structure, and push section-level edits back via Git. That is what the overleafmcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

An MCP (Model Context Protocol) server that provides access to Overleaf projects via Git integration. This allows Claude and other MCP clients to read LaTeX files, analyze document structure, extract content, and write files from and to Overleaf projects.

• 📄 File Management: List, read, and write files from and to Overleaf projects
• 📋 Document Structure: Parse LaTeX sections and subsections
• 🔍 Content Extraction: Extract specific sections by title
• 📊 Project Summary: Get overview of project status and structure
• 🏗️ Multi-Project Support: Manage multiple Overleaf projects

The tools it exposes

The server publishes 8 tools. What each one is for:

• list_projects — The list_projects tool exposed by this server
• list_files — List files in a project (default: .tex files). - extension: File extension filter (optional) - projectName: Project identifier (optional, defaults to
• read_file — Read a specific file from the project. - filePath: Path to the file (required) - projectName: Project identifier (optional)
• get_sections — Get all sections from a LaTeX file. - filePath: Path to the LaTeX file (required) - projectName: Project identifier (optional)
• get_section_content — Get content of a specific section. - filePath: Path to the LaTeX file (required) - sectionTitle: Title of the section (required) - projectName
• status_summary — Get a comprehensive project status summary. - projectName: Project identifier (optional)
• write_file — Write the full content of a file to the project. - filePath: Path to the file (required) - content: Content to write to the file (required) -
• write_section — Write the content of a specific section to the project. - filePath: Path to the file (required) - sectionTitle: Title of the section (required) -

What it needs from you

Configuration is passed through the environment: OVERLEAF_PROJECT_ID, OVERLEAF_GIT_TOKEN, YOUR_OVERLEAF_PROJECT_ID, YOUR_OVERLEAF_GIT_TOKEN, PROJECT_ID. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. OverleafMCP's toolset — list_projects, list_files, read_file and 5 more — is a fair guide to whether it matches your workflow. It is maintained by mjyoo2; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.