WebPT MCP server for AI agents
Let Claude, ChatGPT or your own agent read WebPT: 3 typed functions through one MCP server. No WebPT API key needed.
- Site
- webpt.com
- Functions
- 3
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just WebPT
An MCP server for WebPT 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/webptEvery site
One MCP server for WebPT 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 3
getPageReads one webpt.com page as title, meta description, headings and body text, and flags a retired URL WebPT redirected to its homepage.Arguments
Name Type Required argswebptGetPageArgsYes type webptGetPageArgs = string | { url: string };Returns
webptPageinterface webptHeading { level: number; text: string; } interface webptPage { requestedUrl: string; url: string; redirected: boolean; redirectedToHome: boolean; title: string; description: string | null; h1: string | null; headings: webptHeading[]; text: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/webpt/getPageCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.webpt.getPage("/pricing");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.webpt.getPage("/pricing"))curl -X POST https://api.bowmark.ai/v1/sites/webpt/getPage \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":"/pricing"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.webpt.getPage("/pricing");listPagesLists pages from WebPT's own sitemap (~2,000: products, pricing, blog, webinars, downloads, guides, customers, podcast), optionally one section.Arguments
Name Type Required sectionstringNo limitnumberNo Returns
webptPageRef[]interface webptPageRef { url: string; path: string; section: string; slugTitle: string; lastModified: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/webpt/listPagesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.webpt.listPages({ section: "products" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.webpt.listPages({"section": "products"}))curl -X POST https://api.bowmark.ai/v1/sites/webpt/listPages \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"section":"products"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.webpt.listPages({ section: "products" });searchPagesFinds WebPT pages whose URL matches the query's words (online scheduling, billing, Medicare…), ranked by how many words match; among equal matches…Arguments
Name Type Required querystringYes sectionstringNo limitnumberNo Returns
webptPageRef[]interface webptPageRef { url: string; path: string; section: string; slugTitle: string; lastModified: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/webpt/searchPagesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.webpt.searchPages({ query: "billing" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.webpt.searchPages({"query": "billing"}))curl -X POST https://api.bowmark.ai/v1/sites/webpt/searchPages \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"billing"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.webpt.searchPages({ query: "billing" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/webpt/<function> - OpenAPI
/v1/sites/webpt/openapi.json