Borrowing it
Nothing to install: this file belongs to valda/grok-mcp-server. 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/valda/grok-mcp-server/main/AGENTS.mdgit clone --depth 1 https://github.com/valda/grok-mcp-serverWrote 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/valda/grok-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/valda/grok-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/valda/grok-mcp-server/agents-md/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.
<a href="https://agentmods.dev/instructions/valda/grok-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/valda/grok-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01406 | $0.01406 |
| Opus 5.5 | $0.00562 | $0.00562 |
| Sonnet 5.5 | $0.00281 | $0.00281 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
grok-mcp-server 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 2mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
Grok API プロキシ MCP サーバー。claude.ai の Web 版から接続し、xAI の Grok モデルに質問できる。 Next.js App Router の Route Handlers として OAuth 2.1 認証フロー + MCP エンドポイントを実装。 デプロイ先は Vercel Serverless。
Commands
npm run dev— 開発サーバー起動（http://localhost:3000）npm run build— プロダクションビルドnpm run build:cli— CLI バンドルビルド（dist/cli.js生成）npm test— Vitest でユニット・インテグレーションテスト実行npx tsc --noEmit— 型チェック
Environment Variables
| 変数 | 用途 |
|---|---|
JWT_SECRET |
JWT 署名鍵（必須） |
XAI_API_KEY |
xAI API キー（必須、ツール呼び出し時に必要） |
AUTHORIZE_PASSWORD |
OAuth 認可画面のパスワード（必須、未設定時は認可ブロック） |
BASE_URL |
サーバーの公開URL（任意。未設定時は VERCEL_PROJECT_PRODUCTION_URL → VERCEL_URL → http://localhost:3000 の順にフォールバック） |
Architecture
共通モジュール（lib/）
lib/xai.ts— xAI Responses API 呼び出し（callXai()、モデル定数）lib/tools.ts—X_SEARCH_TOOL定義とhandleXSearchCall()ハンドラ
Remote 版（app/api/mcp/route.ts）と stdio 版（cli/index.ts）の両方から利用。
stdio MCP サーバー（cli/index.ts）
@modelcontextprotocol/sdkのMcpServer+StdioServerTransportを使用- OAuth 不要、
XAI_API_KEY環境変数のみ npx grok-mcp-serverで実行可能- tsup で
dist/cli.jsにバンドル
OAuth 2.1 フロー（app/api/oauth/）
Client → /.well-known/oauth-authorization-server (メタデータ取得)
→ /api/oauth/register (Dynamic Client Registration)
→ /api/oauth/authorize GET (同意画面表示)
→ /api/oauth/authorize POST (認可コード JWT 発行 → redirect)
→ /api/oauth/token (認可コード → アクセストークン JWT 交換、PKCE 検証)
- 認可コード・アクセストークン・クライアント登録情報はすべて ステートレス JWT（jose ライブラリ）
client_idは署名付き JWT で、登録情報（redirect_uris,client_name）を内包する（サーバー側状態なし）Mcp-Session-Idはアクセストークンをそのまま流用（独立したセッション JWT は廃止済み）- JWT ユーティリティは
app/api/oauth/jwt.tsに集約（signClientRegistration,verifyClientRegistration,signAuthorizationCode,signAccessToken,signRefreshToken,verifyJwt）
MCP エンドポイント（app/api/mcp/route.ts）
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.
- 2mo ago First seen · 83 lines · 1,406 tokens per session scan A 7ff55ad1f6a8
grok-mcp-server AGENTS.md is an instructions file published in the GitHub repository valda/grok-mcp-server (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,406 tokens to every session, about $0.0056 per session on Opus 5.5. 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.
grok-mcp-server AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| grok-mcp-server AGENTS.mdvalda/grok-mcp-server | Instructions file | 0 | 5mo ago | MIT | A | 1,406 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |