Model Context Protocol (MCP) server that lets AI assistants read Overleaf projects, parse LaTeX document structure, and push section-level edits back via Git. Compatible with Claude Desktop, Cursor, Windsurf, and any MCP client.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
mjyoo2
Source: github_topic
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
OVERLEAF_GIT_TOKEN"": "YOUR_OVERLEAF_GIT_TOKEN"OVERLEAF_GIT_TOKEN_FILEPrefer over inlining the token in the Claude Desktop JSON if your config file is backed up or synced.OVERLEAF_PROJECTS_CONFIGIf projectName is omitted, the default entry is used. To put projects.json somewhere other than the standard location, point =/absolute/path/projects.json at it from the env block.OVERLEAF_PROJECT_ID"": "YOUR_OVERLEAF_PROJECT_ID",OVERLEAF_PROJECT_NAME1. Env vars (single project) — OVERLEAF_PROJECT_ID + OVERLEAF_GIT_TOKEN. Optional: for the display name.XDG_CONFIG_HOMEmacOS / Linux ~/.config/overleaf-mcp/projects.json (or $/overleaf-mcp/projects.json if set)Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
8/8 tools missing one or more hints — list_projects (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_files (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); read_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +5 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
2 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 2 high severity in production deps — @modelcontextprotocol/sdk@1.0.0 (high), @modelcontextprotocol/sdk@1.0.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Your fixes are re-checked automatically. Claim the listing and we tell you when the grade moves, and reach you directly if we find anything urgent.
[](https://m8ven.ai/mcp/mjyoo2-overleafmcp-peq9eb)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check