Gmail MCP Server Expose Gmail’s full API as a single SSE “tool server” endpoint for your AI agents. What it does Spins up an MCP Trigger that streams Server‑Sent Events to LangChain/N8N AI Agent nodes. Maps 20+ common Gmail operations (search, send, reply, draft, label & thread management, mark read/unread, delete, etc.) to ai_tool connections, so agents can invoke them with a simple JSON payload. Why you’ll love it Agent‑ready: Plug the SSE URL into any N8N Agent or any other AI tool that uses MCP and start reasoning over email immediately. Extensible: Add more GmailTool operations or swap credentials without touching your agent logic. How to use Import the workflow (n8n ≥ v1.88). Set up a gmailOAuth2 credential and select it on the GmailTool nodes. Open the Gmail MCP Server node, copy the SSE URL, and paste it into your AI agent’s “Tool Server” field.
Tags
Related workflows
See all General Automation→Using the Merge Node - Merge by Key
This is an example of how you can make Merge by Key work. The “Data 1” and “Data 2” nodes simply provide mock data. You can replace them with your own data sources. Then the “Convert Data” nodes are important. They make sure that the different array items are actually different items in n8n. After that, you have then the merge with the merged data.
Write JSON to Disk (Binary)
The “Write Binary File” expects binary data. The JSON data is, however, JSON ;) There should really be a node that allows moving data around between both of them. For now, it can be done with a Function-Node. At least till a proper one is in place. The first node is example data, wich you can customize or replace. The second node named “Make Binary” is the important one with the custom code which makes the data binary and writes it to the correct location.
Webhook returning XML
Receives data from an incoming HTTP Request (set up to use respond to webhook node) Create dummy data Convert JSON to XML which gets returned Respond to Webhook which returns the data and the content type of the data