grok-mcp

grok-mcp is a cursor rule for Cursor from zai-one/grok-build-mcp. It costs 253 tokens per session, scanned A, original, MIT.

Rules for an unofficial Grok MCP orchestrator, where Grok handles delegated work and the host assistant coordinates and checks it. MCP is a way for an AI assistant to use external tools.

In plain words
What is it for?
For running Grok delegation through session cards, handling schema failures, using grok/* worktrees, and verifying changes with the project's pytest command.
Why use it?
They define how to start, run, poll, and review delegated jobs while limiting version, worktree, secret, and Git-operation risks.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

Good fit For running Grok delegation through session cards, handling schema failures, using grok/* worktrees, and verifying changes with the project's pytest command.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/zai-one/grok-build-mcp/grok-mcp
Install

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.

Clone the repo
git clone --depth 1 https://github.com/zai-one/grok-build-mcp

Made for: Cursor.

Wrote 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.

agentmods badge for grok-mcp

README.md
[![agentmods](https://agentmods.dev/badge/rules/zai-one/grok-build-mcp/grok-mcp/github.svg)](https://agentmods.dev/rules/zai-one/grok-build-mcp/grok-mcp)
Your own site
<a href="https://agentmods.dev/rules/zai-one/grok-build-mcp/grok-mcp"><img src="https://agentmods.dev/badge/rules/zai-one/grok-build-mcp/grok-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for grok-mcp

Your own site · 80×15
<a href="https://agentmods.dev/rules/zai-one/grok-build-mcp/grok-mcp"><img src="https://agentmods.dev/badge/rules/zai-one/grok-build-mcp/grok-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 253 This file is loaded in full into every session.
When invoked 253 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00253 $0.00253
Opus 5 $0.00127 $0.00127
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00025 $0.00025

Measured 7d ago against content hash 87d8ac565152, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

grok-mcp 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.

.cursor/rules/grok-mcp.mdc · 19 lines

What it actually says

grok-delegate

Grok = worker. Host = orchestrator/verifier. Unofficial; auth is grok login only.

  • Cheap loop: session_beginsession_next until donesession_end.
  • Execute card = full task (objective, project_root, correlation_id, expected_artifacts, test_commands). Poll card = {job_id} only. Never put session_id on poll.
  • Card/schema failure → typed consult → execute → poll → review.
  • Unpin is default (GROK_DELEGATE_EXPECTED_AGENT_VERSION opt-in). Mismatch warns; do not block.
  • Worktrees grok/* only. Never push/merge from the bridge. No secrets in receipts or commits.
  • If bridge_version is stale: git pull, pip install -e ., restart MCP.
  • Tests: py -3 -m pytest tests -q. No force-push, no --no-verify, no CLI version pin.

Details: AGENTS.md.

Changes

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.

  1. 7d ago First seen · 19 lines · 253 tokens per session scan A 87d8ac565152

Subscribe to this mod's changes

grok-mcp is a cursor rule published in the GitHub repository zai-one/grok-build-mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 253 tokens to every session, about $0.0013 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.