Borrowing it
Nothing to install: this file belongs to KoensAU/grok-mcp-worker. 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/KoensAU/grok-mcp-worker/main/AGENTS.mdgit clone --depth 1 https://github.com/KoensAU/grok-mcp-workerWrote 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/koensau/grok-mcp-worker/agents-md)<a href="https://agentmods.dev/instructions/koensau/grok-mcp-worker/agents-md"><img src="https://agentmods.dev/badge/instructions/koensau/grok-mcp-worker/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 5.1 | $0.01130 | $0.01130 |
| Opus 5 | $0.00565 | $0.00565 |
| Sonnet 5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade B, and why
grok-mcp-worker AGENTS.md scanned grade B with 1 finding 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 6d 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
them, never commit them. `mcp.json` carries a `how` field per secret How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — install contract for grok-mcp-server
Instructions for an AI agent installing this server on a new machine or for a
new LLM client. Follow in order. mcp.json is the machine-readable companion
to this file; if the two ever disagree, mcp.json wins and this file is stale.
This deploys a copy on the installer's own Cloudflare account, billed to the installer's own xAI key. Every value below is theirs to supply — never reuse a value you've seen elsewhere.
What this is
A single-tenant MCP server wrapping xAI Grok, running as a Cloudflare Worker. Nine tools. Stateless — no Durable Objects, no KV, no session memory.
0. Prerequisites
- Node >= 18,
npx wrangler>= 4 - A Cloudflare account (Workers free tier is enough)
- An xAI API account with billing set up (console.x.ai) — image and video generation cost more than text
wrangler loginalready completed
Stop and ask the operator if any are missing. Do not create accounts on their behalf.
1. Install
npm install
2. Set secrets — the installer's own values
Prompt the operator for each value. Never write them to a file, never echo
them, never commit them. mcp.json carries a how field per secret
describing where each comes from.
wrangler secret put XAI_API_KEY
# paste your own xai-... key when prompted
printf '%s' "$(openssl rand -hex 32)" | wrangler secret put AUTH_SECRET
AUTH_SECRET is required. It gates the inbound /mcp endpoint (src/auth.ts),
dual-route: a static bearer (Authorization: Bearer <AUTH_SECRET>) for direct
clients like Claude Code, and OAuth/PKCE (stateless HMAC tokens, no KV) for the
claude.ai connector's one-click Connect. Both routes are backed by this one
secret, generated fresh for this install. The gate fails closed — if
AUTH_SECRET is unset the server returns 503 on every request, never open
access. Set it without a trailing newline (printf '%s', not echo) and
never echo the value back. MCP_PUBLIC=true is a deliberate escape hatch to
run open on purpose; leave it unset otherwise.
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.
- 6d ago First seen · 148 lines · 1,130 tokens per session scan B d1c0c706564e
grok-mcp-worker AGENTS.md is an instructions file published in the GitHub repository KoensAU/grok-mcp-worker (0 stars, last pushed 12d ago), licensed MIT. It adds 1,130 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). 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.