USA.gov MCP server for AI agents
Let Claude, ChatGPT or your own agent read USA.gov: 2 typed functions through one MCP server. No USA.gov API key needed.
- Site
- usa.gov
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just USA.gov
An MCP server for USA.gov 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/usa_govEvery site
One MCP server for USA.gov 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
getPageReads one USA.gov page (e.g. /passport, /renew-adult-passport) and returns its title, intro, breadcrumb, alerts, prose sections with links, and a hub…Arguments
Name Type Required urlstringYes Returns
usa_govPageinterface usa_govLink { text: string; url: string; } interface usa_govSection { heading: string; level: number; text: string; links: usa_govLink[]; } interface usa_govCard { title: string; url: string; summary: string | null; } interface usa_govPage { url: string; title: string; description: string | null; intro: string | null; breadcrumb: string[]; alerts: string[]; sections: usa_govSection[]; cards: usa_govCard[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/usa_gov/getPageCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.usa_gov.getPage("<url>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.usa_gov.getPage("<url>"))curl -X POST https://api.bowmark.ai/v1/sites/usa_gov/getPage \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url":"<url>"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.usa_gov.getPage("<url>");listPagesLists English USA.gov pages from the site's own sitemap, optionally filtered by words in the url (e.g. passport).Arguments
Name Type Required querystringNo Returns
usa_govPageLink[]interface usa_govPageLink { title: string; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/usa_gov/listPagesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.usa_gov.listPages({ query: "passport" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.usa_gov.listPages({"query": "passport"}))curl -X POST https://api.bowmark.ai/v1/sites/usa_gov/listPages \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"passport"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.usa_gov.listPages({ query: "passport" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/usa_gov/<function> - OpenAPI
/v1/sites/usa_gov/openapi.json