chatwoot-mcp
Local Node/TypeScript MCP server for read-only Chatwoot analytics, providing tools to list accounts, scopes, cache sync status, and conversation volume metrics.
README
Chatwoot MCP
Local Node/TypeScript MCP split for read-only Chatwoot analytics.
This service is intended to replace the MCP surface of the current Python combined server after shadow testing. It does not process Chatwoot webhooks and does not generate embeddings.
Current Scope
This repo has Node/TypeScript registrations for all 66 Python MCP tools from the previous combined server.
Semantic/vector tools remain embedding-free in this repo. They call the split Python embedding service through:
EMBEDDING_SERVICE_URL=http://127.0.0.1:8000
EMBEDDING_API_KEY=YOUR_EMBEDDING_SERVICE_X_API_KEY
Tool parity notes are tracked in docs/PORTING_CHECKLIST.md.
Transports
Default mode is stdio:
npm run build
npm start
HTTP mode:
npm run build
npm run start:http
Legacy SSE compatibility mode uses the same HTTP server:
npm run start:sse
Routes are mounted under BASE_PATH:
GET ${BASE_PATH}/healthPOST/GET ${BASE_PATH}/mcpfor Streamable HTTPGET ${BASE_PATH}/ssefor legacy SSEPOST ${BASE_PATH}/messagesfor legacy SSE client messages
If MCP_API_KEY is set, Authorization: Bearer <key> is required.
Local Setup
npm install
cp .env.example .env
npm run build
npm run start:http
Windows PowerShell:
npm install
Copy-Item .env.example .env
npm run build
npm run start:http
Shadow Testing
Run locally with a non-production port/path:
PORT=3010
BASE_PATH=/node-mcp
Then compare selected tools against the live Python MCP before exposing this behind Nginx.
Nginx Notes
Use path-preserving proxying. Do not depend on rewrite-only behavior because SSE advertises the POST message URL back to clients.
location /node-mcp/ {
proxy_pass http://127.0.0.1:3010/node-mcp/;
proxy_http_version 1.1;
proxy_set_header Host $host;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
proxy_set_header Authorization $http_authorization;
proxy_buffering off;
proxy_read_timeout 3600s;
}
Production Safety
Keep the live Python MCP endpoint unchanged until:
- Every required tool has Node parity.
- Date/timezone output matches expected semantics.
- ChatGPT/Codex/Claude clients can connect to the shadow path.
- A rollback path is documented.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。