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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.