Bennington Marine MCP server for AI agents
Let Claude, ChatGPT or your own agent read Bennington Marine: 1 typed function through one MCP server. No Bennington Marine API key needed.
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Bennington Marine
An MCP server for Bennington Marine 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/benningtonEvery site
One MCP server for Bennington Marine 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
searchLists Bennington's pontoon/tritoon model series (S, SX, Q, QX, L, R Bowrider) with their published length, beam, engine and seating specs, read off…Arguments
Name Type Required args{ model?: string }No Returns
{ models: BenningtonModel[]; warnings: string[] }interface BenningtonModel { slug: string; name: string; url: string; lengthOverall: string | null; beam: string | null; specText: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/bennington/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.bennington.search({ model: "s" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.bennington.search({"model": "s"}))curl -X POST https://api.bowmark.ai/v1/sites/bennington/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"model":"s"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.bennington.search({ model: "s" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/bennington/<function> - OpenAPI
/v1/sites/bennington/openapi.json