Bowmark AI MCP server for AI agents
Let Claude, ChatGPT or your own agent read Bowmark AI: 2 typed functions through one MCP server. No Bowmark AI API key needed.
- Site
- bowmark.ai
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Bowmark AI
An MCP server for Bowmark AI 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/bowmarkEvery site
One MCP server for Bowmark AI 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
getOverviewReads Bowmark AI's public product overview, API and MCP endpoints, and published pricing.Arguments
None.
Returns
BowmarkOverviewinterface BowmarkOverview { name: string; description: string; website: string; apiUrl: string | null; mcpUrl: string | null; pricing: { price: string; currency: string; description: string } | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/bowmark/getOverviewCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.bowmark.getOverview();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.bowmark.getOverview())curl -X POST https://api.bowmark.ai/v1/sites/bowmark/getOverview \ -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.bowmark.getOverview();listDocumentationLists Bowmark AI's published agent-facing documentation pages from its public llms.txt index.Arguments
None.
Returns
BowmarkDocumentation[]interface BowmarkDocumentation { title: string; url: string; description: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/bowmark/listDocumentationCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.bowmark.listDocumentation();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.bowmark.listDocumentation())curl -X POST https://api.bowmark.ai/v1/sites/bowmark/listDocumentation \ -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.bowmark.listDocumentation();
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/bowmark/<function> - OpenAPI
/v1/sites/bowmark/openapi.json