smry MCP server for AI agents
Let Claude, ChatGPT or your own agent read smry: 2 typed functions through one MCP server. No smry API key needed.
- Site
- smry.ai
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just smry
An MCP server for smry 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/smry_aiEvery site
One MCP server for smry 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
listDocPagesLists smry's public documentation pages from its first-party index, providing a no-argument discovery door for a bare smry.ai request.Arguments
None.
Returns
SmryDocLink[]interface SmryDocLink { title: string; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/smry_ai/listDocPagesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.smry_ai.listDocPages();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.smry_ai.listDocPages())curl -X POST https://api.bowmark.ai/v1/sites/smry_ai/listDocPages \ -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.smry_ai.listDocPages();readArticleReads a public article through smry's clean reader and returns its source metadata plus a saved full-text file or bounded preview.Arguments
Name Type Required urlstringYes Returns
SmryArticleinterface smry_aiSavedFile { id: string; name: string; contentType: string; bytes: number; url: string; expiresAt: string; keepUntil?: string | null; } interface SmryArticle { sourceUrl: string; readerUrl: string; title: string | null; publisher: string | null; blocks: number | null; characters: number; file: smry_aiSavedFile | null; preview: string | null; truncated: boolean; warnings: string[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/smry_ai/readArticleCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.smry_ai.readArticle({ url: "<url>" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.smry_ai.readArticle({"url": "<url>"}))curl -X POST https://api.bowmark.ai/v1/sites/smry_ai/readArticle \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"url":"<url>"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.smry_ai.readArticle({ url: "<url>" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/smry_ai/<function> - OpenAPI
/v1/sites/smry_ai/openapi.json