{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_765t97a293ab","handle":"ai-code-review-mcp","url":"https://wellknown.network/agents/ai-code-review-mcp","links":{"self":"https://wellknown.network/agents/ai-code-review-mcp/record.json","html":"https://wellknown.network/agents/ai-code-review-mcp","markdown":"https://wellknown.network/agents/ai-code-review-mcp/record.md","api":"https://wellknown.network/api/v1/agents/ai-code-review-mcp","status":"https://wellknown.network/api/v1/agents/ai-code-review-mcp/status","claim":"https://wellknown.network/agents/ai-code-review-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ai-code-review-mcp/claim.json","badge":"https://wellknown.network/agents/ai-code-review-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:ai-code-review-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ai-code-review-mcp","summary":"MCP 服务器，为 AI 编码助手提供本地代码质量审查工具","description":"# ai-code-review-mcp \n \n一个基于 MCP（Model Context Protocol）的代码质量审查服务器，为 AI 编码助手（如 OpenCode、Claude Desktop、Cursor 等）提供本地代码分析能力。 \n \n## 特性 \n \n- **文件分析** — 检测函数复杂度、行数统计、代码风格问题 \n- **Diff 审查** — 审查 git 未提交的变更，发现调试代码和潜在密钥泄露 \n- **项目扫描** — 一键扫描整个项目的代码质量概况 \n- **质量评分** — 为每个文件/项目计算 A-D 等级的质量评分 \n- **多语言支持** — Python 深度分析（AST）+ 通用质量检查（JS/TS/Java/Go/Rust 等） \n- **配套 Skill** — 提供标准化的代码审查工作流提示词 \n \n## 快速开始 \n \n### 安装 \n \n```bash \npip install ai-code-review-mcp \n``` \n \n### 配置 OpenCode \n \n在项目的 `opencode.json` 中添加： \n \n```json \n{ \n  \"$schema\": \"https://opencode.ai/config.json\", \n  \"mcp\": { \n    \"code-review-mcp\": { \n      \"type\": \"local\", \n      \"command\": [\"ai-code-review-mcp\"], \n      \"enabled\": true \n    } \n  } \n} \n``` \n \n### 配置 Claude Desktop \n \n在 `claude_desktop_config.json` 中添加： \n \n```json \n{ \n  \"mcpServers\": { \n    \"code-review-mcp\": { \n      \"command\": \"ai-code-review-mcp\" \n    } \n  } \n} \n``` \n \n### 安装配套 Skill \n \n将 `skill/` 目录复制到你的项目中： \n \n```bash \ncp -r skill/ .opencode/skills/code-review/ \n``` \n \n或者复制到全局目录： \n \n```bash \ncp -r skill/ ~/.config/opencode/skills/code-review/ \n``` \n \n## 提供的工具 \n \n### `analyze_file` — 分析单个文件 \n \n分析文件的代码质量、复杂度和行数统计。 \n \n``` \n帮我分析 src/main.py 的代码质量 \n``` \n \n返回内容： \n- 语言类型 \n- 代码行数 / 注释行数 / 空白行数 \n- 问题列表（函数过长、复杂度过高、参数过多等） \n- 质量评分（A/B/C/D） \n \n### `review_diff` — 审查 git 变更 \n \n审查当前仓库中未提交的变更（staged + unstaged）。 \n \n``` \n审查一下当前未提交的代码变更 \n``` \n \n检测内容： \n- 硬编码的密钥或密码 \n- 遗留的 `print()` / `console.log()` 调试语句 \n- 新增的 TODO/FIXME 标记 \n- 过长的代码行 \n \n### `check_project` — 扫描项目概况 \n \n扫描整个项目的代码质量。 \n \n``` \n扫描一下项目整体代码质量 \n``` \n \n返回内容： \n- 文件总数和总行数 \n- 语言分布统计 \n- 问题最多的前 10 个文件 \n- 项目整体质量评分 \n \n## 使用 uvx 运行（无需安装） \n \n如果你使用 [uv](https://github.com/astral-sh/uv)，可以直接运行： \n \n```json \n{ \n  \"mcp\": { \n    \"code-review-mcp\": { \n      \"type\": \"local\", \n      \"command\": [\"uvx\", \"ai-code-review-mcp\"], \n      \"enabled\": true \n    } \n  } \n} \n``` \n \n## 从源码运行 \n \n```bash \ngit clone https://github.com/AlanNiew/code-review-mcp.git \ncd code-review-mcp \npip install -e . \n``` \n \n然后在配置中使用： \n \n```json \n{ \n  \"mcp\": { \n    \"c…","publisher":null,"homepage":"https://github.com/AlanNiew/code-review-mcp","repository":"https://github.com/AlanNiew/code-review-mcp","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp","code-review","code-quality","ai","coding-assistant"],"pricing":null,"endpoints":[{"url":"pypi:ai-code-review-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"code.review","name":"Code Review","confidence":1,"provenance":"derived"},{"slug":"code.generation","name":"Code Generation","confidence":0.75,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"},{"slug":"productivity.tasks","name":"Tasks & To-do","confidence":0.745,"provenance":"derived"}],"categories":["code","dev","productivity"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"ai-code-review-mcp","registry":"pypi","observedAt":"2026-09-09T08:22:39.311Z","publishedAt":"2026-04-16T02:35:21.067282Z","latestVersion":"0.1.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ai-code-review-mcp","url":"https://pypi.org/project/ai-code-review-mcp/","firstSeenAt":"2026-09-09T08:21:34.110Z","fetchedAt":"2026-09-09T08:21:34.110Z","normalizedAt":"2026-09-09T08:21:34.110Z"}]},"firstSeenAt":"2026-09-09T08:21:34.110Z","updatedAt":"2026-09-09T08:22:39.311Z"}