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/noedgeai/doc2x-mcp/agents-mdgit clone --depth 1 https://github.com/NoEdgeAI/doc2x-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/noedgeai/doc2x-mcp/agents-md)<a href="https://agentmods.dev/instructions/noedgeai/doc2x-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/noedgeai/doc2x-mcp/agents-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 | $0.00934 | $0.00934 |
| Opus 5 | $0.00467 | $0.00467 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade C, and why
doc2x-mcp AGENTS.md scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/NoEdgeAI/doc2x-mcp/main/scripts/install-skill.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/NoEdgeAI/doc2x-mcp/main/scripts/install-skill.sh | sh How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/: TypeScript source (ESM).src/index.ts: MCP server entrypoint (stdio).src/config/: runtime config parsing and defaults.src/errors/: error model and error code definitions.src/shared/: shared utilities.src/mcp/: Tool registration and result shaping.src/mcp/registerToolsShared.ts: Shared schemas, cache primitives, and atomic cache helpers.src/doc2x/: Doc2x v2 API client logic (PDF/image/convert/download/materialize).
dist/: Build output (generated bytsc). Do not edit by hand..env.example: Sample env vars;.envis gitignored.
Build, Test, and Development Commands
npm install(ornpm ci): Install dependencies.npm run build: Compile TypeScript todist/viatsc -p tsconfig.json.npm start: Run the MCP server (node dist/index.js).
Example local run:
DOC2X_API_KEY=sk-xxx npm run build && npm start
Coding Style & Naming Conventions
- TypeScript (Node.js ESM,
type: module); target Node>=18. - Prefer explicit errors and small modules; avoid over-abstraction.
- Naming:
camelCasefor variables/functions,PascalCasefor types/classes. - Formatting: keep diffs minimal; follow existing file style (no repo-wide formatter configured).
Testing Guidelines
- Test runner: Node built-in test runner via
node --test. - Available scripts:
npm run test:unitnpm run test:e2enpm run test
- Keep tests deterministic (no real network calls) and document new test entrypoints in
package.jsonscripts.
Cache & Concurrency Guidelines
- Keep cache access centralized in
src/mcp/registerToolsShared.ts. - For UID caches, prefer shared atomic helpers (
getSubmittedUidFromCache,setSubmittedUidCache,setFailedUidCache,deleteUidCache) instead of directctx.*Cachereads/writes in tool files. - For convert submit de-duplication, always go through
runConvertSubmitAtomically; do not re-implement local in-flight maps. - Failed UID cache entries must use short TTL (failed state), successful/submitted entries use default TTL.
- File signature strategy is stat-first plus digest reuse:
- use
size + mtimeMsas fast-path cache key for digest reuse - compute MD5 only on stat changes
- keep
sameSigas path/size precheck then digest confirm
- use
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.
- 4d ago First seen · 86 lines · 934 tokens per session scan C ab385e498806
doc2x-mcp AGENTS.md is an instructions file published in the GitHub repository NoEdgeAI/doc2x-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 934 tokens to every session, about $0.0047 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
mcp-pandoc AGENTS.md
Instructions for vivekVells/mcp-pandoc, covering agents.md, what this is, where things are, deeper context and commands.
agentic-resume-builder CLAUDE.md
Claude Code instructions for WtotdeD/agentic-resume-builder, covering agentic-resume-builder development guidelines, what this repo is, active technologies, package manager and validation.
fcp-sheets CLAUDE.md
Instructions for os-tack/fcp-sheets, covering fcp-sheets, project overview, architecture, key patterns and commands.
paperless-ngx-mcp-server CLAUDE.md
Claude Code instructions for cbsmiley/paperless-ngx-mcp-server, covering claude.md, project overview, common commands, architecture and entry points.
hermes-procurement-pricing-mcp AGENTS.md
AGENTS.md instructions for felix-windsor/hermes-procurement-pricing-mcp, a project described as: Secure procurement quotation comparison MCP service with document parsing, mock market pricing, anomaly detection, and Telegram/Hermes integration.
mcp-svg-marp CLAUDE.md
Claude Code instructions for koppe-pan/mcp-svg-marp, covering mcp-svg-marp tool instructions, mcp tools available, 📊 convertsvgtomarp, 🔍 analyzesvg and automatic slide creation workflow.