US Census Bureau MCP server for AI agents

Let Claude, ChatGPT or your own agent read US Census Bureau: 1 typed function through one MCP server. No US Census Bureau API key needed.

Functions
1
Sign-in
Not needed
Works with
MCP, HTTP, Node, Python

Connect

Just US Census Bureau

An MCP server for US Census Bureau 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/census_api
Every site

One MCP server for US Census Bureau and every other site Bowmark covers. Your agent looks up what it needs and calls it.

https://api.bowmark.ai/mcp
Set it up in your client

Both 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 1
  • validateAddressValidates and standardizes a US street address against the Census Geocoder (geocoding.geo.census.gov locations/onelineaddress): whether it matches a…

    Arguments

    NameTypeRequired
    addressstringYes

    Returns ValidateAddressResult

    interface AddressMatch {
      matchedAddress: string;
      street: string;
      city: string;
      state: string;
      zip: string;
      latitude: number;
      longitude: number;
    }
    
    interface ValidateAddressResult {
      input: string;
      valid: boolean;
      ambiguous: boolean;
      matches: AddressMatch[];
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/census_api/validateAddress

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.census_api.validateAddress({ address: "350 Fifth Avenue, New York, NY 10118" });

Use it from code