Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/amcheste/overleaf-mcp/claude-mdgit clone --depth 1 https://github.com/amcheste/overleaf-mcpWrote 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/amcheste/overleaf-mcp/claude-md)<a href="https://agentmods.dev/instructions/amcheste/overleaf-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/amcheste/overleaf-mcp/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 | $0.00492 | $0.00492 |
| Opus 5 | $0.00246 | $0.00246 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
overleaf-mcp 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 3d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overleaf MCP Server: architecture notes
Project-local context for Claude sessions. The README.md is for end users; this file is for contributors (human or AI) working on the server itself.
The write path IS git
Overleaf does not expose a public HTTP write API for project file trees. The only supported programmatic write path on a paid Overleaf account is the per-project Git remote at git.overleaf.com/<project_id>.
This server is therefore a local git client:
Claude ──MCP─► overleaf-mcp ──git-over-HTTPS──► git.overleaf.com
(cached local clone)
Every write tool (edit_file, create_file, delete_file) follows the same flow:
git pullto refresh the cached clone- Validate the target path stays inside the repo root
- Write/delete the file in the working tree
git commitwith a generated message and the configured authorgit pushto Overleaf
If you ever find yourself reaching for an "Overleaf REST API" call, stop. There isn't one. The answer is always a git operation against the cached clone.
We shell out to git via subprocess rather than using GitPython. The design goal is auditability: the dependency graph should be readable in five minutes.
GitHub mirroring is out of scope
Users who want a GitHub backup add GitHub as a second remote on their own local clone. The MCP server knows nothing about GitHub and should not grow GitHub-aware code. If this boundary ever gets tempted, push back.
Credentials never touch disk
Tokens live in the OS keychain (primary) or environment variables (fallback, for CI/power users). The config file contains project aliases + IDs only, never tokens. See src/overleaf_mcp/core/credentials.py for the resolution order.
Scope discipline
This server is deliberately single-process, single-user, stdio-transport, serial. No Redis, no job queues, no locks, no concurrent-edit handling. Those assumptions keep the code auditable and are why we can ship something meaningfully different from the existing community servers. If you find yourself adding coordination machinery, stop and re-read this section.
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.
- 3d ago First seen · 39 lines · 492 tokens per session scan A 6354718085f1
overleaf-mcp CLAUDE.md is an instructions file published in the GitHub repository amcheste/overleaf-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 492 tokens to every session, about $0.0025 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
linkedin-mcp-server AGENTS.md
AGENTS.md instructions for stickerdaniel/linkedin-mcp-server, covering claude.md, development commands, scraping rules, browser identity rules and profile safety rules.
pagespeed-insights-mcp AGENTS.md
AGENTS.md instructions for ruslanlap/pagespeed-insights-mcp, covering project rules — pagespeed-insights-mcp (mcp server), специфіка проєкту, обов'язкові практики (mcp + ts), serena + .serena/ and професійні skills тільки.
kafka-schema-reg-mcp AGENTS.md
AGENTS.md instructions for aywengo/kafka-schema-reg-mcp, covering development guidelines, prerequisites, quick setup, install dependencies and install dev dependencies (optional but recommended).
research-workflow-assistant copilot-instructions.md
Instructions for Intersect-Collaborations-LLC/research-workflow-assistant, covering research workflow assistant: global agent instructions, core identity, disclaimer & readiness gate (non-negotiable), 1. disclaimer acceptance check and 2. mcp server reachability check.
ls-mcp AGENTS.md
AGENTS.md instructions for lirantal/ls-mcp, covering agents.md, start here, documentation, prs and issues and releases.
PBP CLAUDE.md
Instructions for MadGapun/PBP, covering pbp — claude-code-memory, stand 2026-08-25 (v1.7.23 stable) — ehrliche zahlen, stand 2026-07-16 (v1.8.0-beta.6, prerelease) — hotfix #760, stand 2026-07-14 (v1.7.7) — scoring-fairness & praxis-funde and stand 2026-07-03 (v1.7.6) — alltags-fuehrung.