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/nympheon/grok-mcp/agents-mdgit clone --depth 1 https://github.com/nympheon/grok-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/nympheon/grok-mcp/agents-md)<a href="https://agentmods.dev/instructions/nympheon/grok-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/nympheon/grok-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 5.1 | $0.02486 | $0.02486 |
| Opus 5 | $0.01243 | $0.01243 |
| Sonnet 5 | $0.00497 | $0.00497 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
grok-MCP AGENTS.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 5d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GrokMCP 维护指南
修改 Worker 前先阅读本文件。GitHub 仓库 nympheon/grok-MCP 的 main 分支是
唯一源码事实来源;Cloudflare Workers Builds 是现有 grokmcp Worker 的常规部署
入口。本项目不是本地 stdio 软件包,也不是多用户服务。
不可破坏的运行契约
- Worker/service 名:
grokmcp; - 公开路由:
GET /healthz; - MCP 路由:
/t/<MCP_URL_TOKEN>/mcp; - 中文管理路由:
/admin/t/<ADMIN_URL_TOKEN>; - Durable Object 类名:
GrokState; - Durable Object 稳定对象名:
single-user; - SQLite 初始迁移标签:
v1; - MCP 表面:只能有
x_search、web_search; - MCP wire revision:仅
2026-07-28,每个请求返回一个 JSON 响应; - 默认模型:Worker 变量
GROK_X_SEARCH_MODEL,当前为grok-4.6; - xAI 输出文本:只接受当前 REST 结构
output[].content[].output_text.text。
不要恢复旧 initialize/session 传输、SSE、顶层 xAI output_text 兼容分支、原始
帖子列表或账号管理 MCP 工具。成功结果同时提供 structuredContent 和内容相同的
JSON 文本块是当前有意设计,不是旧协议兼容层。
源码职责
src/worker.ts:在读取请求体前完成 URL token 鉴权,负责公开/管理/MCP 路由、 Host/Origin 检查、表单解析和请求体限制。绝不能记录请求 URL 或请求体。src/admin.ts:生成简体中文、无脚本、不可缓存的控制面。所有运行时值必须经过 HTML 转义;错误只按ToolErrorCode映射,不得显示原始上游错误。src/mcp.ts:定义两个搜索工具、输入 schema、outputSchema和 handler。不得加入 登录、状态、回调、退出或其他账号工具。src/grokState.ts:管理 SQLite、加密 OAuth 尝试/token、刷新串行化、退出顺序和 搜索调用。迁移和加密数据格式属于持久契约。src/cryptoVault.ts:使用 AES-256-GCM、每条记录独立 96 位 IV 和用途绑定 AAD。 既有用途字符串不能随意修改。src/oauth.ts:实现当前公共 Grok CLI/Hermes 兼容 native client 的 PKCE 与 token 交换。client ID 是公开兼容依赖,不是 secret,但上游可能随时调整。src/xaiClient.ts:验证 xAI search 契约、限制响应并解析当前 wire 结构。上游 参数变化时,必须同步更新 schema、运行时验证、fixture、测试和 README。src/urlAuth.ts:解析固定形状 token 路径并比较 SHA-256 摘要,不能改回提前退出的 明文字符串比较。scripts/secrets.mjs:只服务首次部署或主动轮换,原子创建/迁移权限为0600的 本地文件。除明确 URL 命令外不得打印任何值。
Secret 与状态
生产环境必须有三个独立 Worker secret:
MCP_URL_TOKEN:保护 ChatGPT MCP 连接;ADMIN_URL_TOKEN:保护登录、状态、URL 恢复和退出;TOKEN_ENCRYPTION_KEY:加密 OAuth 行,绝不能打印、提交或写入日志。
.secrets.local 只用于首次部署或明确轮换,必须被 Git 忽略。常规升级不得重新生成
并上传三个值。npm run deploy 有意不提供 secrets 文件,Cloudflare 会校验所需名称
并保留远端值;npm run deploy:with-secrets 只允许首次部署或经确认的主动轮换。
轮换某个 URL token 只应使对应 URL 失效。轮换 TOKEN_ENCRYPTION_KEY 会让现有 OAuth
密文不可读,随后必须重新登录。除非包含经过验证的数据迁移,不得重命名
GrokState、删除 v1 SQLite 迁移、改变 single-user 对象名或既有 AAD 用途字符串。
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.
- 5d ago First seen · 200 lines · 2,486 tokens per session scan A 5c5cca16da89
grok-MCP AGENTS.md is an instructions file published in the GitHub repository nympheon/grok-MCP (1 stars, last pushed 24d ago), licensed MIT. It adds 2,486 tokens to every session, about $0.0124 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
vibesdk AGENTS.md
AGENTS.md instructions for cloudflare/vibesdk, covering agents.md, tooling, verification, frontend ui and frontend data fetching.
vibesdk CLAUDE.md
Claude Code instructions for cloudflare/vibesdk, covering claude.md, communication style, project overview, key architectural patterns and common development tasks.
grok-cli AGENTS.md
Instructions for superagent-ai/grok-cli, covering agents.md, cursor cloud specific instructions, quick reference, known issues and environment.
pi-xai-oauth AGENTS.md
AGENTS.md instructions for BlockedPath/pi-xai-oauth, covering agents.md — ai agent operations manual for pi-xai-oauth, project overview, key commands (exact, copy-paste ready), architecture & boundaries (must / must not) and file structure & wayfinding.
munkel CLAUDE.md
Claude Code instructions for limehq/munkel, covering claude.md, monorepo layout, commands, macos development specifics and deploy.
cloudbox AGENTS.md
Instructions for acoyfellow/cloudbox, covering cloudbox agent guide, canonical commands, deploy model, cloudflare account boundaries and required production secrets.