TheStreet MCP server for AI agents
Let Claude, ChatGPT or your own agent read TheStreet: 2 typed functions through one MCP server. No TheStreet API key needed.
- Site
- thestreet.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just TheStreet
An MCP server for TheStreet 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/thestreetEvery site
One MCP server for TheStreet 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
commentCountReads how many reader comments a TheStreet article has, by its numeric article id (the number at the end of a thestreet.com article URL).Arguments
Name Type Required articleIdstringNumeric id at the end of a thestreet.com article URL; a full URL works too.Yes Returns
CommentCountinterface CommentCount { articleId: string; count: number; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/thestreet/commentCountCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.thestreet.commentCount({ articleId: "3245809" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.thestreet.commentCount({"articleId": "3245809"}))curl -X POST https://api.bowmark.ai/v1/sites/thestreet/commentCount \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"articleId":"3245809"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.thestreet.commentCount({ articleId: "3245809" });sectionsLists TheStreet's site sections and topics.Arguments
None.
Returns
TheStreetSectionsinterface TheStreetSection { id: number; title: string; url: string; children: TheStreetSection[]; } interface TheStreetSections { sections: TheStreetSection[]; // primary navigation topics: TheStreetSection[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/thestreet/sectionsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.thestreet.sections({});import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.thestreet.sections({}))curl -X POST https://api.bowmark.ai/v1/sites/thestreet/sections \ -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.thestreet.sections({});
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/thestreet/<function> - OpenAPI
/v1/sites/thestreet/openapi.json