TMZ MCP server for AI agents
Let Claude, ChatGPT or your own agent read TMZ: 2 typed functions through one MCP server. No TMZ API key needed.
- Site
- tmz.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just TMZ
An MCP server for TMZ 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/tmzEvery site
One MCP server for TMZ 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 2
newsSidebarReads TMZ's desktop news sidebar.Arguments
None.
Returns
TmzNewsSidebarinterface TmzItem { title: string; url: string; type: string; // "article" | "gallery" | "video" image: string | null; } interface TmzNewsSidebar { sections: { title: string; items: TmzItem[] }[]; // e.g. "Most Popular", "Hot Galleries" }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/tmz/newsSidebarCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.tmz.newsSidebar({});import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.tmz.newsSidebar({}))curl -X POST https://api.bowmark.ai/v1/sites/tmz/newsSidebar \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.tmz.newsSidebar({});searchSearches TMZ celebrity news by keyword, as the site's search box does, returning each result's headline, article url and thumbnail, one page (~12…Arguments
Name Type Required args{ query: string; page?: number }Yes Returns
TmzSearchResultinterface TmzItem { title: string; url: string; type: string; // "article" | "gallery" | "video" image: string | null; } interface TmzSearchResult { query: string; page: number; results: TmzItem[]; // ~12 per page, newest first hasMore: boolean; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/tmz/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.tmz.search({ query: "Taylor Swift" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.tmz.search({"query": "Taylor Swift"}))curl -X POST https://api.bowmark.ai/v1/sites/tmz/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"Taylor Swift"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.tmz.search({ query: "Taylor Swift" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/tmz/<function> - OpenAPI
/v1/sites/tmz/openapi.json