overleaf-mcp
npm
v1.1.0
Published by sahithreddy — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
MCP server connecting Claude to Overleaf — automated LaTeX resume editing, compilation, and job tailoring without copy-paste
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 11 = 89. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −10 | capability blast radius (critical) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
This server (without client built-ins) exposes a complete data-exfiltration chain: overleaf_download_pdf → overleaf_read_file → overleaf_open_project. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.
Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.
Location: flow overleaf_download_pdf → overleaf_read_file → overleaf_open_project
In the server's implementation (`dist/tools/latex.js:5`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ; import { exec } from "child_process"; import { promisify } from "util"; const execAsync = promisify(exec); // Ensure T
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/latex.js
Tool "overleaf_write_file" can write, overwrite or delete files (keyword "write_file" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool overleaf_write_file
Tool "overleaf_edit_file" can write, overwrite or delete files (keyword "edit_file" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool overleaf_edit_file
Tool "overleaf_write_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool overleaf_write_file
Tool "overleaf_edit_file" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool overleaf_edit_file
Each tool and what it can reach — statically extracted from the published source.
overleaf_read_fileingests untrusted inputreads sensitive dataoverleaf_download_pdfingests untrusted inputoverleaf_edit_filewrites filesoverleaf_open_projectnetwork egressoverleaf_write_filewrites filesats_scoreno sensitive capabilitycompile_latexno sensitive capabilitygenerate_cover_letterno sensitive capabilityget_cached_resumeno sensitive capabilitylist_latex_filesno sensitive capabilitylist_templatesno sensitive capabilityopen_pdfno sensitive capabilityoverleaf_compileno sensitive capabilityoverleaf_list_projectsno sensitive capabilityoverleaf_loginno sensitive capabilityoverleaf_logoutno sensitive capabilityoverleaf_push_fileno sensitive capabilitypingno sensitive capabilityread_latexno sensitive capabilityswitch_templateno sensitive capabilitytailor_resumeno sensitive capabilitywrite_latexno sensitive capabilityCross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.1.0 latest |
B 89/100 | 6 | 1.13.0 | 2026-09-07 |
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan overleaf-mcp --online
Independent packages implementing the same tool, scanned with the same engine. Compare all 6 side by side →
MCP server for Overleaf projects
A minimal, auditable MCP server for editing Overleaf projects via Git
MCP server for Overleaf with tracked-changes support, via the Socket.IO web API (not the Git bridge).
MCP server that lets AI assistants read Overleaf projects, parse LaTeX document structure, and push section-level edits back via Git.
MCP server for Overleaf integration - read LaTeX files, analyze document structure, and manage Overleaf projects via Git
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development
Servidor MCP para el tiempo oficial de España (API pública OpenData de AEMET). Predicción, observación y avisos como herramientas MCP tipadas.
A standalone MCP stdio bridge for Affinity by Canva's local MCP SSE server.