pr-roast-mcp
pr-roast-mcp
用于吐槽你的拉取请求的 MCP 服务器。提供极其诚实且幽默的代码审查。
安装
claude mcp add pr-roast -- uv run --directory /path/to/pr-roast-mcp pr-roast-mcp或者添加到你的 MCP 配置中:
{
"mcpServers": {
"pr-roast": {
"command": "uv",
"args": ["run", "--directory", "/path/to/pr-roast-mcp", "pr-roast-mcp"],
"env": {
"ANTHROPIC_API_KEY": "sk-ant-..."
}
}
}
}要求:已认证的 gh CLI,以及 ANTHROPIC_API_KEY 环境变量。
Related MCP server: MCP Git/PR Assist
使用方法
询问 Claude:
"Roast my latest PR" (吐槽我最新的 PR)
"Roast PR #89" (吐槽 PR #89)
"Roast https://github.com/owner/repo/pull/123" (吐槽 https://github.com/owner/repo/pull/123)
"List my open PRs so I can pick one to roast" (列出我打开的 PR,以便我选择一个进行吐槽)
工具
roast_pr
吐槽特定的拉取请求。
参数 | 类型 | 描述 |
| string | PR 编号、 |
roast_my_prs
列出你的 PR 以便选择一个进行吐槽。
参数 | 类型 | 默认值 | 描述 |
| string | 当前仓库 |
|
| string | "open" | PR 状态:"open"、"closed" 或 "merged" |
功能说明
通过
ghCLI 获取 PR 元数据和差异发送给 Claude Haiku 进行吐槽
返回带有严重程度评级(🔥 到 🔥🔥🔥🔥🔥)的极其诚实的审查
结尾总是包含一个真诚的赞美
输出示例
🔥🔥🔥 代码审查:"Initiative Bonus"
你的测试非常详尽。简直是令人怀疑的详尽。一个 POST 端点写了 156 行代码?你基本上是在写一篇关于 HTTP 状态码的论文。
那个
selectChain辅助函数简直是魔法咒语 —— 没人知道为什么.select()会返回它自己。加个注释解释一下你正在模仿的 Supabase API 吧。新增 849 行,删除 7 行。比例是 121:1。对于一个“额外功能”来说,这太臃肿了。
严重程度:🔥🔥🔥 (修复迁移描述并简化模拟后即可合并)
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables automated GitHub Pull Request reviews using local Ollama, Cursor CLI, or Gemini CLI as AI providers. Supports customizable review prompts, comprehensive PR analysis, and optional auto-posting of reviews to GitHub.105MIT
- -licenseNot gradedqualityNot gradedmaintenanceEnables Git and GitHub pull request operations through Claude AI, including repository management, branch operations, commits, and PR creation/commenting. Streamlines development workflows by providing Git commands and GitHub API integration through natural language interactions.
- FlicenseNot gradedqualityDmaintenanceEnables multi-agent code review with P0/P1/P2 severity scoring by orchestrating locally installed AI CLIs (Claude, Codex) to perform parallel analysis, deterministic scoring, and consensus-building on git diffs.2
- AlicenseNot gradedqualityDmaintenanceConnects Claude to GitHub Pull Requests to fetch and filter code diffs for AI-assisted reviews. It enables listing open PRs and analyzing changes while automatically excluding binary and asset files to focus on relevant code.21MIT
Related MCP Connectors
AI code review for GitHub PRs with an MCP autofix loop for Claude Code and Cursor
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Agentic code review, no signup to try: reality gates + frontier-model review, with veto.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/anisha-agarwal/pr-roast-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server