Seb Labs MCP server for AI agents
Let Claude, ChatGPT or your own agent read Seb Labs: 1 typed function through one MCP server. No Seb Labs API key needed.
- Site
- seblabs.dev
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Seb Labs
An MCP server for Seb Labs alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/seblabsEvery site
One MCP server for Seb Labs and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 1
demoSeb Labs' free fixed illustrative decision distribution for enterprise, finance, robotics, or handoff; it is explicitly not live model inference or a…Arguments
Name Type Required presetSeblabsDemoPresetNo type SeblabsDemoPreset = "enterprise" | "finance" | "robotics" | "handoff";Returns
SeblabsDemointerface SeblabsDemo { mode: "illustrative"; model: string; state: number; stateLabel: string; options: Array<{ label: string; probability: number }>; choice: string; note: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/seblabs/demoCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.seblabs.demo("enterprise");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.seblabs.demo("enterprise"))curl -X POST https://api.bowmark.ai/v1/sites/seblabs/demo \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"preset":"enterprise"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.seblabs.demo("enterprise");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/seblabs/<function> - OpenAPI
/v1/sites/seblabs/openapi.json