chatwoot-mcp
Provides read-only analytics and reporting tools for Chatwoot, including listing accounts, retrieving conversation volumes by inbox, daily resolved conversation volumes, and native reports.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@chatwoot-mcpshow me the resolved conversation volume for each inbox"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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, plus Node-first read-only tools for clearer agent workflows.
For recent conversation audit requests like "last 7 days all conversations summary per inbox", agents should use get_recent_resolved_conversation_summaries_by_inbox. It returns cached resolved conversations grouped by account/inbox with each Chatwoot conversation ID and a compact transcript summary. If the user names an account, brand, inbox, product, or channel, call list_available_chatwoot_scope first and pass selected account_id and/or inbox_ids.
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_KEYTool parity notes are tracked in docs/PORTING_CHECKLIST.md.
Related MCP server: Umami MCP Server
Transports
Default mode is stdio:
npm run build
npm startHTTP mode:
npm run build
npm run start:httpLegacy SSE compatibility mode uses the same HTTP server:
npm run start:sseRoutes 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:httpWindows PowerShell:
npm install
Copy-Item .env.example .env
npm run build
npm run start:httpShadow Testing
Run locally with a non-production port/path:
PORT=3010
BASE_PATH=/node-mcpThen 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.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/md-riaz/chatwoot-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server