AI Skill Hub 推荐使用:RepoPrompt社区版 是一款优质的MCP工具。AI 综合评分 7.5 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
RepoPrompt社区版 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
RepoPrompt社区版 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/repoprompt/repoprompt-ce
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"repoprompt---": {
"command": "npx",
"args": ["-y", "repoprompt-ce"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 RepoPrompt社区版 执行以下任务... Claude: [自动调用 RepoPrompt社区版 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"repoprompt___": {
"command": "npx",
"args": ["-y", "repoprompt-ce"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
A free, open-source native macOS app and agent orchestrator for context engineering.
RepoPrompt CE helps coding agents understand your codebase before they act. It assembles focused, reviewable context from files, CodeMaps, repository structure, and Git diffs, then hands that context to AI tools and CLI agents.
RepoPrompt CE also builds an agent harness around its bundled MCP server. Connect MCP-compatible clients and CLI agents to search repositories, inspect files, curate context, run agent sessions, and orchestrate work through a shared native macOS interface.
RepoPrompt CE is the free, open-source community edition of RepoPrompt. It is a native macOS workspace for context engineering, agent orchestration, and local development.
Maintainers track release signing, Sparkle metadata, dependency pins, and third-party notices in docs/open-source-readiness.md.
- Context engineering: Build dense, reviewable prompts with the files and repository details an AI model actually needs. - Codebase orientation: Combine file trees, selected file contents, line slices, CodeMaps, and Git diffs. - Context Builder: Let an agent explore the repository, identify relevant files, and curate context within a token budget. - Agent orchestration: Run and coordinate CLI-backed coding agents from the native macOS app. See docs/worktrees.md for app-managed worktrees and .worktreeinclude local file copying. - MCP server and CLI integration: Connect external MCP-compatible tools and CLI agents to RepoPrompt CE's repository context and agent harness. - Multi-root workspaces: Work across related repositories, packages, and documentation folders in one workspace. - Reviewable handoffs: Inspect and refine selected context before sending it to another model or agent.
For development and quick evaluation, double-click Launch RepoPrompt CE.command in Finder.
The launcher builds RepoPrompt CE from source, opens the debug app, and keeps a small terminal window available for rebuild, status, and stop controls.
The debug launcher uses an available Apple Development: signing identity. If your Mac does not have one, run the same debug app from Terminal with explicit ad-hoc signing:
ALLOW_ADHOC_SIGNING=1 ./conductor app relaunch
Ad-hoc debug builds use in-memory secure storage, so saved API keys and secure permission changes do not persist across launches. For persistent debug Keychain storage, pass a stable Apple Development identity explicitly:
SIGN_IDENTITY="Apple Development: Your Name (TEAMID)" ./conductor app relaunch
For a stable locally signed app under /Applications, use the local production installer below. Its self-signed identity is separate from the debug launcher's Apple Development signing path.
Note: If you use the debug app to modify RepoPrompt CE itself, validation flows that launch the app or run live smoke checks may rebuild and relaunch it. Expect the debug app to restart while those checks run.
| Key | Action |
|---|---|
r | Rebuild and relaunch |
s | Show app status |
x | Stop the app |
q | Close the launcher without stopping the app |
For a release-mode app under /Applications, install Python 3 and double-click Install RepoPrompt CE Local Production.command in Finder. The Finder launcher uses the coordinated developer daemon.
The installer builds RepoPrompt CE from source and replaces any existing /Applications/RepoPrompt CE.app using a dedicated self-signed certificate trusted only on your Mac. macOS may ask you to approve the certificate.
The resulting app is local-only. It is not notarized and should not be copied to another Mac or redistributed.
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
总体来看,RepoPrompt社区版 是一款质量良好的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | repoprompt-ce |
| 原始描述 | 开源MCP工具:Community edition of RepoPrompt: a native macOS context engineering app for AI c。⭐185 · Swift |
| Topics | ai-agentscoding-agentscontext-engineering |
| GitHub | https://github.com/repoprompt/repoprompt-ce |
| License | Apache-2.0 |
| 语言 | Swift |
收录时间:2026-06-07 · 更新时间:2026-06-07 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端