A router for an unofficial Grok integration that manages multi-step Grok agent sessions. It requires a defined session flow in which the assistant starts a session, handles one task at a time, checks progress, and ends the session when finished.

Use it to start and manage Grok sessions, execute approved task steps, poll running jobs, review results, and finish the session.

It provides a prescribed way to coordinate Grok tasks and handle failed tool requests or jobs that need polling.

How zai-one/grok-build-mcp configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to zai-one/grok-build-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/zai-one/grok-build-mcp/main/.agents/skills/grok-mcp/SKILL.md

Clone the repo

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

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zai-one/grok-build-mcp/grok-mcp/github.svg)](https://agentmods.dev/skills/zai-one/grok-build-mcp/grok-mcp)

Your own site

<a href="https://agentmods.dev/skills/zai-one/grok-build-mcp/grok-mcp"><img src="https://agentmods.dev/badge/skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zai-one/grok-build-mcp/grok-mcp"><img src="https://agentmods.dev/badge/skills/zai-one/grok-build-mcp/grok-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 314 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00075	$0.00314
Opus 5	$0.00037	$0.00157
Sonnet 5	$0.00015	$0.00063
Haiku 4.5	$0.00007	$0.00031

Measured 10d ago against content hash fdc8b7faa8d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 10d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/check_ready.sh, scripts/draft_issue.py, scripts/update_mcp.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/grok-mcp/SKILL.md · 30 lines

What it actually says

grok-mcp

Unofficial — not xAI/Grok. Auth = grok login only.

Token budget protocol

grok_agent_session_begin once (goal, host_budget=small)
Loop grok_agent_session_next — execute only the card (host_cmd | mcp_tool | end)
Execute cards carry a full task; poll cards are {job_id} only
Schema / unknown-tool failure → typed consult → execute → poll → review (references/execute.md)
When done=true → grok_agent_session_end, then stop

Do not open references/* unless blocked. Do not re-plan. Do not pin a Grok CLI version.

Never

OAuth in config · dumps · parallel jobs · push/merge from the bridge

Files

What ships with it

17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago First seen · 30 lines · 75 tokens per session scan A fdc8b7faa8d2

Subscribe to this mod's changes

grok-mcp is a skill published in the GitHub repository zai-one/grok-build-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 314 once invoked, about $0.0004 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.

Building agents agent claude grok mcp model-context-protocol xai

vulnerability-triage

Reference vocabulary for interpreting vulnerability findings — detector-vs-impact distinction, severity anchoring on demonstrated evidence, the eleven-item interpretation rubric, delegation transparency, primitive-extent scaling, the disqualifier taxonomy (D-0..D-4), CVSS Achievable / Environmental framing…

provos/ironcurtain · 121 tokens

agent-browser

Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.

superagent-ai/grok-cli · 31 tokens

harness-design-fuzzing

Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2 multi-component / T3 full build), systematic input exploration, the two-coverage distinction (fuzzer-feedback vs audit)…

provos/ironcurtain · 147 tokens

memory-safety-c-cpp

Reference vocabulary for memory-safety vulnerabilities in native C/C++ code — bug-class taxonomy, common arithmetic patterns that lead to corruption, dispatch-family discipline, type-confusion idioms, use-after-free patterns, and exploitability factors. Read when analyzing, hypothesizing, designing harnesses for, or…

provos/ironcurtain · 113 tokens

gmail-query-syntax

Reference for Gmail's search query syntax — operators like is:sent, newerthan:, from:, has:attachment, label:, and how they compose. Read this when constructing a Gmail search query string for the googleworkspace.gmailsearchmessages Code Mode call, especially when filtering by sent vs received, recency, sender, or…

provos/ironcurtain · 71 tokens

email-formatting

Markdown formatting conventions for email summary documents — heading depth, list style, line length, emoji policy, and a mandatory provenance footer. Read this when producing a markdown report that summarizes one or more email messages so the output matches the project's house style.

provos/ironcurtain · 53 tokens

grok-build-mcp: Skill for Claude Code