Borrowing it
Nothing to install: this file belongs to vinconig/ShareLatexMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vinconig/ShareLatexMCP/master/CLAUDE.mdgit clone --depth 1 https://github.com/vinconig/ShareLatexMCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/vinconig/sharelatexmcp/claude-md)<a href="https://agentmods.dev/instructions/vinconig/sharelatexmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vinconig/sharelatexmcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02225 | $0.02225 |
| Opus 5 | $0.01112 | $0.01112 |
| Sonnet 5 | $0.00445 | $0.00445 |
| Haiku 4.5 | $0.00222 | $0.00222 |
Grade A, and why
ShareLatexMCP CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
sharelatex-mcp-server.js is a single-file MCP (Model Context Protocol) stdio server. It gives MCP clients (Claude Desktop, etc.) tools to read ShareLaTeX project files, parse LaTeX document structure, and push section-level or whole-file edits back via the instance's Git integration.
It targets ShareLaTeX @ TUM (sharelatex.tum.de) by default — a self-hosted Overleaf Server Pro deployment. This repo is a fork of mjyoo2/OverleafMCP, which targets overleaf.com; the load-bearing difference is the Git URL shape, https://<host>/git/<projectId> instead of https://git.overleaf.com/<projectId>.
It is not published to npm. Installs go through npx -y github:vinconig/ShareLatexMCP, which is why package.json must keep exactly one bin entry (sharelatex-mcp) and the script must keep its #!/usr/bin/env node shebang and executable bit.
There is no build step and no test suite — the entire runtime is the one script.
Commands
npm install # install deps (only @modelcontextprotocol/sdk)
npm start # node sharelatex-mcp-server.js
# Smoke-test the MCP protocol directly over stdio (no Claude Desktop needed)
SHARELATEX_PROJECT_ID=... SHARELATEX_GIT_TOKEN=... node sharelatex-mcp-server.js
# → should print "ShareLaTeX MCP server running on stdio" to stderr, then block on stdin
# Local iteration against Claude Desktop: point its config at the cloned script
# (see README "Local Development" for the full JSON snippets)
There are no lint/test scripts defined in package.json. See the README's "Smoke-test the MCP protocol from the shell" section for a one-liner that drives a real tools/call end to end.
Architecture
Everything lives in sharelatex-mcp-server.js, organized top to bottom as:
- Config loading (
loadProjectsConfigand helpers) — resolves which project(s) to talk to. Priority order, first match wins:SHARELATEX_PROJECT_ID+ (SHARELATEX_GIT_TOKENorSHARELATEX_GIT_TOKEN_FILE) → synthesized as a single project keyeddefault.SHARELATEX_PROJECTS_CONFIG=/path/to/projects.json(explicit path; missing/invalid file is fatal, no silent fallthrough).projects.jsonin the OS user config dir (%APPDATA%\sharelatex-mcpon Windows,$XDG_CONFIG_HOME/sharelatex-mcpor~/.config/sharelatex-mcpelsewhere)../projects.json(cwd).projects.jsonnext to the script (legacy, for clone-based installs).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 80 lines · 2,225 tokens per session scan A c82c14abbd1e
ShareLatexMCP CLAUDE.md is an instructions file published in the GitHub repository vinconig/ShareLatexMCP (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,225 tokens to every session, about $0.0111 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.