Satish G used Grok Bot to prepare Blender payloads and send them from its VM through a tailcat connection. This workflow is listed under blender, remote-tools, agent-integration.
The Blender MCP add-on served the receiving port and minted the connection token, while a tailcat process on the VM sent payloads prepared by Bot. He used this arrangement in place of the separate Blender Lab MCP server, then asked Bot to generate explanatory diagrams.
How it went
He shared two Bot-generated diagrams as learning resources, including one explaining the listener, connection token and relay path.
Save ideas in this browser. Upvotes count across the board.
A builder pattern for selling Grok Bot work: give each client a studio+client@mail.grokbot.com tag and a routine that only accepts requests from approved contacts.
With Grok Bot’s own inbox live, a GTM builder sketched an always-on pipeline: Firecrawl monitors prospects, then the bot drafts client outreach for human send.
A builder shipped a Karpathy-inspired shared-spine memory for Grok Bot—one wiki, permanent bidirectional links, short/medium/long-term as tags (never copies), with a nightly tidy job.