io.github.howardpen9/grok-mcp

MCPcommunity
v0.2.0io.github.howardpen9UnknownUpdated 23d agonpmGitHub

Use xAI Grok as a peer reviewer + PR gate from Claude Code, Cursor, Cline and any MCP host.

讓 Claude Code、Cursor、Cline、OpenClaw 等 MCP host 透過官方 xAI Grok CLI,把 Grok 當成 code reviewer、adversary 與第二意見顧問 使用。 (npm 套件名 )是 Model Context Protocol server,將 CLI 包裝成工具,讓你的主要 agent(Claude、Cursor…)可以隨時叫 Grok 幫忙 review、挑戰、諮詢,而不用切換 session: — 結構化 diff review,附五維度評分 — 對抗式找 bug / race / security hole — 多輪諮詢(caller 自己重送 history) 市面上其他 "Grok MCP" 套件大多讓 Claude 可以「使用」Grok 的 chat / search / image 能力。 反過來:讓你的主要…

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
23d agoLast update
Package
Authorio.github.howardpen9
LicenseUnknown
Version0.2.0
Sourcemcp-registry
Trust Status
B
60/100Good
Listed in Forge index+10/10
Publisher identity verified+0/25
Publisher: run `forge publish` from the package repo to claim ownership
Ed25519 publish signature+0/10
Included automatically when the publisher runs `forge publish`
Domain verification+0/5
Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
CVE scan · clean+30/30
Static analysis · clean+20/20
npm provenance (Sigstore)+0/5
Publish from GitHub Actions with the --provenance flag
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain
Provenance
Dependencies60 resolved+ · none vulnerable
Tool surface4 tools · none privileged
Security scan✓ Cleanv0.2.0 · 20d ago
EvalsNone
IndexedJun 13, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.

About

讓 Claude Code、Cursor、Cline、OpenClaw 等 MCP host 透過官方 xAI Grok CLI,把 Grok 當成 code reviewer、adversary 與第二意見顧問 使用。 (npm 套件名 )是 Model Context Protocol server,將 CLI 包裝成工具,讓你的主要 agent(Claude、Cursor…)可以隨時叫 Grok 幫忙 review、挑戰、諮詢,而不用切換 session: — 結構化 diff review,附五維度評分 — 對抗式找 bug / race / security hole — 多輪諮詢(caller 自己重送 history) 市面上其他 "Grok MCP" 套件大多讓 Claude 可以「使用」Grok 的 chat / search / image 能力。 反過來:讓你的主要 coding agent(Claude / Cursor)請 Grok 來 review、挑戰自己的產出。換一個 model 攻擊主 agent 的盲點,能抓到單模型 loop 找不到的 bug。…

Keywords
mcp