Overleaf MCP Server
An MCP server for managing Overleaf projects through Git synchronization.
에이전트 강화
게시자의 자체 명령입니다. PlugMCP 엔드포인트가 아닙니다.
Host a copy with our keys and logs.
uvx overleaf-mcp-integration==0.1.0Claude Code에는 로컬 명령용 설치 링크가 없습니다. 아래 명령을 복사해 터미널에서 실행합니다.
claude mcp add younesbensafia-overleaf-mcp-server -- uvx overleaf-mcp-integration==0.1.0터미널에서 실행합니다.
{ "mcpServers": { "younesbensafia-overleaf-mcp-server": { "command": "uvx", "args": [ "overleaf-mcp-integration==0.1.0" ] } }}claude_desktop_config.json
원격 URL인가요, 내 컴퓨터에서 실행하는 명령인가요? 두 설치 방식의 차이
PlugMCP에서 실행
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
실행게시자 제공
flowchart LR
C[MCP Client\nClaude Desktop / other MCP host] -->|Tool Call| S[Overleaf MCP Server]
S -->|Git Sync| O[Overleaf Git Remote]
S -->|Read / Write| L[Local Repo Mirror]
L -->|Commit + Push| O
O -->|Pull / Fetch| L
S -->|Tool Result| C
sequenceDiagram
participant Client as MCP Client
participant Server as Overleaf MCP Server
participant Local as Local Mirror
participant Overleaf as Overleaf Git
Client->>Server: list_files / read_file
Server->>Local: Ensure local clone
Server->>Overleaf: git pull
Overleaf-->>Server: latest content
Server-->>Client: file list / file content
Client->>Server: write_file(path, content)
Server->>Local: update file
Server->>Local: git commit
Server->>Overleaf: git push
Server-->>Client: success + metadata
uv package managerhttps://www.overleaf.com/project/69a4f7cc4eaf13bd56de5b04 → 69a4f7cc4eaf13bd56de5b04)..env - copy .env.example to .env and fill in:OVERLEAF_TOKEN=your_git_token
PROJECT_ID=your_project_id
project_idcan also be passed per tool call, butPROJECT_IDis still required by the server configuration.
The Overleaf Git token is account-wide credential material. Store it only in
the MCP client's environment or a protected .env file, and rotate it if it
is exposed.
Files in an Overleaf project are untrusted input. A .tex file or project
configuration can contain instructions aimed at the model; treat file contents
as data, not as commands. Keep OVERLEAF_ALLOWED_PROJECTS restricted to the
projects the server should be able to access:
OVERLEAF_ALLOWED_PROJECTS=project_id_a,project_id_b
The default allowlist contains only PROJECT_ID.
git clone https://github.com/younesbensafia/overleaf-mcp-server.git
cd overleaf-mcp-server
uv sync
cp .env.example .env # then edit with your token/project id
uv run overleaf-mcp
Without a checkout, run the Git version directly with:
uvx --from git+https://github.com/younesbensafia/overleaf-mcp-server overleaf-mcp
Plain uvx overleaf-mcp is appropriate only after the project is published to
PyPI.
The server listens on stdio - connect your MCP client (Claude Desktop, etc.) to it.
For a large project, call sync_project first. The initial Git clone can take
longer than an MCP client's individual tool request timeout.
read_file accepts optional zero-based offset and bounded limit line
parameters for reading large documents in chunks.
Add to ~/.config/Claude/claude_desktop_config.json:
{
"mcpServers": {
"overleaf": {
"command": "uv",
"args": ["--directory", "/path/to/overleaf-mcp-server", "run", "overleaf-mcp"],
"env": {
"OVERLEAF_TOKEN": "your_git_token",
"PROJECT_ID": "your_project_id"
}
}
}
}
PROJECT_ID in .env.project_id explicitly in tool calls.sync_project before write_file if the remote changed.uv sync.MIT - See LICENSE
MCP server for Overleaf projects. Syncs LaTeX files via Git, parses sections, equations, and citations, and exposes them to AI clients for assisted paper review, LaTeX fixes, and content generation.
{ "mcpServers": { "younesbensafia-overleaf-mcp-server": { "command": "uvx", "args": [ "overleaf-mcp-integration==0.1.0" ] } }}도구
아직 도구 목록이 없습니다. 원격 서버는 첫 상태 확인 후에 도구 목록이 생깁니다.
FAQ
이 페이지에서 Cursor, Claude Desktop, Claude Code 또는 VS Code용 stdio 설정을 복사합니다. PlugMCP 프록시가 아니라 게시자의 설치 방식을 사용합니다.
이 레코드에는 필수 환경 변수가 등록되어 있지 않습니다.
Overleaf은(는) stdio를 통해 로컬에서 실행됩니다.
마지막 확인: 2026-10-28. MCP server for Overleaf projects. Syncs LaTeX files via Git, parses sections, equations, and citations, and exposes them to AI clients for assisted paper review, LaTeX fixes, and content generation.