AI Skill Hub 强烈推荐:Munin 智能体客户平台 是一款优质的MCP工具。AI 综合评分 8.0 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。
一个专为AI Agent时代设计的开源客户平台,采用MCP(模型上下文协议)优先架构。集成分析、聊天组件、CMS和CRM功能,支持私有化部署,适合需要构建AI驱动的客户管理系统和交互界面的开发者。
Munin 智能体客户平台 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。
一个专为AI Agent时代设计的开源客户平台,采用MCP(模型上下文协议)优先架构。集成分析、聊天组件、CMS和CRM功能,支持私有化部署,适合需要构建AI驱动的客户管理系统和交互界面的开发者。
Munin 智能体客户平台 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/getmunin/munin
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"munin--------": {
"command": "npx",
"args": ["-y", "munin"]
}
}
}
# 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 Munin 智能体客户平台 执行以下任务... Claude: [自动调用 Munin 智能体客户平台 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": {
"munin________": {
"command": "npx",
"args": ["-y", "munin"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Open-source, headless HubSpot alternative.
<p align="left"> <a href="https://github.com/getmunin/munin/blob/main/LICENSE"><img src="https://img.shields.io/github/license/getmunin/munin?color=3fb950&labelColor=0F1419" alt="MIT License"></a> <a href="https://github.com/getmunin/munin/commits/main"><img src="https://img.shields.io/github/last-commit/getmunin/munin?color=3fb950&labelColor=0F1419" alt="Last commit"></a> <a href="https://registry.modelcontextprotocol.io"><img src="https://img.shields.io/badge/MCP%20Registry-com.getmunin%2Fmunin-0066FF?labelColor=0F1419" alt="Listed in the MCP Registry"></a> </p>
<p align="left"> <a href="https://www.getmunin.com"><b>Website</b></a> · <a href="https://vimeo.com/1204180225?autoplay=0&utm_source=github&utm_medium=readme&utm_campaign=demo-video"><b>See it in action</b></a> · <a href="https://www.getmunin.com/en/docs/"><b>Documentation</b></a> · <a href="https://registry.modelcontextprotocol.io"><b>MCP Registry</b></a> </p>
CRM, conversations, outreach, CMS, knowledge base, and analytics on one Postgres schema — exposed as tools your agents drive, not screens you click through. Headless the way a headless CMS is: there's a thin dashboard for settings, auth, and human-in-the-loop review, but the apps themselves have no admin UI. Every action runs through MCP tools, callable from any MCP-compatible client (Claude, Cursor, ChatGPT, custom runners) — same tools, same permissions, same audit log, whether a human or an agent is driving. Munin even ships its own: an in-process, per-org agent runner that answers live conversations and works the curation queue against an LLM provider you configure — so the platform runs out of the box, with external MCP clients optional.
<p align="center"> <img src=".github/assets/dashboard.png" alt="The Munin dashboard — a thin shell over the MCP tool surface" width="100%"><br> <sub><b>The dashboard</b> — a thin shell for settings, auth, and human-in-the-loop review. No admin UI for app data; it drives the same MCP tools your agents call.</sub> </p>
<p align="center"> <img src=".github/assets/widget-demo.webp" alt="The Munin chat widget answering a customer from the knowledge base" width="100%"><br> <sub><b>The embeddable chat widget</b> — answering a live customer from the knowledge base, ready to hand off to a human and be picked back up by the agent.</sub> </p>
The same /mcp endpoint serves two distinct callers, audience-aware:
kb:*, conv:*, crm:*, cms:*, outreach:*, analytics:*.See packages/backend-core/src/control/delegated-token.controller.ts for the token-mint API. The @getmunin/sdk Node client wraps it.
| Module | Tools | What it does |
|---|---|---|
| Knowledge Base | kb_* | documents, hybrid search, audience scoping |
| Conversations | conv_* | channels, messages, handover |
| CRM | crm_* | contacts, companies, deals |
| CMS | cms_* | collections, entries, assets |
| Outreach | outreach_* | campaigns, drafts, propose-only |
| Analytics | analytics_* | page-view + search events |
These six modules aren't separate products — they share one Postgres schema, one permission model, and one audit log. Watch how they tie together:
<p align="center"> <a href="https://vimeo.com/1202399440?autoplay=0&utm_source=github&utm_medium=readme&utm_campaign=promo-video"> <img src=".github/assets/video-thumbnail.png" alt="Watch: what Munin is and how it works" width="100%"> </a> </p>
#### Knowledge Base - Markdown articles organized into spaces, each scoped to the audiences allowed to see it. - Hybrid search that blends keyword matching with meaning-based results. - Website import — crawl a public site and turn each page into an article in the background, automatically dropping articles when their source page disappears. - Full version history with restore, plus a review queue for proposed edits.
#### Conversations - One inbox across email, chat widget, voice (Threll.ai / Vapi), and SMS (Twilio / MessageBird). - Inbound and outbound — agents answer conversations and can place outbound calls. - Assignable, organized by topic, and searchable across every message. - Built-in handoff to a human, with notifications to your own systems as conversations change.
#### CRM - Contacts, companies, deals, activities, pipelines, and segments. - AI-written summaries and suggested next actions, kept separate from what people edit by hand. - Consent tracking — the lawful basis and source for each contact, required before they can be added to any outreach. - Automatic duplicate detection that proposes merges for review, plus bulk contact import.
#### CMS - Content collections with structured fields, and entries you can publish in multiple languages. - Rich content blocks for article bodies — callouts, quotes, media, and more. - Scheduled publishing and a media library for images and files. - Full version history with restore, search, and cross-references between entries. - A public content API serves your site or app, with engagement tracking built into every entry.
#### Outreach - Propose-only outbound email — campaigns, segments, and drafts for both first touches and replies. - Recipients are drawn only from contacts who have recorded consent (see CRM). - Every message waits for human approval; nothing is ever sent automatically.
#### Analytics - Captures page views and on-site searches across anything you want to measure. - CMS pages are tracked automatically; for any other page, you add a small tracking snippet. - Conversion funnels and per-visitor journeys — once someone is identified, their visits link to a CRM contact, including the anonymous ones from before. - Breakdowns by traffic source, referrer, and country, plus "what to write next" signals (popular topics, engagement, and searches that came back empty).
aiskill88点评:前瞻性地结合了MCP协议与CRM,将AI Agent的工具化能力转化为业务平台,架构先进,极具潜力。
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。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,Munin 智能体客户平台 是一款质量优秀的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 | munin |
| 原始描述 | 开源MCP工具:The customer platform for the agentic era. MCP-first, open source, self-hostable。⭐7 · TypeScript |
| Topics | MCP协议客户关系管理AI AgentTypeScript |
| GitHub | https://github.com/getmunin/munin |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-07-02 · 更新时间:2026-07-02 · License:MIT · 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