census
Census — US Census Bureau
The official US Census Bureau data: decennial census, American Community Survey (ACS), economic census, population estimates, housing characteristics, geographic boundaries. National, state, county, place, tract, block-group, and ZCTA-level. Free, no key required for public datasets.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
Why this matters for AI agents
Demographics, housing characteristics, economic activity, geographic identifiers — Census is the authoritative source. If an agent is computing per-capita rates, comparing metros, looking up population, or working with FIPS codes, this is where it goes.
Common flows:
Population for an area. ACS 1-year or 5-year estimates by state/county/place.
Housing characteristics. Median home value, occupancy, units, age — all in ACS.
Geographic ID lookup. Place name → FIPS code → boundary geometry.
Economic Census every 5 years for industry-level economic activity.
Pair with FRED for time-series macro and BLS for labor.
Related MCP server: Open Census MCP Server
Auth
Most Census APIs are free and unauthenticated, with light rate limits (~500 calls/day per IP). For higher rates, get a key at https://api.census.gov/data/key_signup.html and pass via _apiKey.
Datasets worth knowing
Dataset | Cadence | Geography |
Decennial Census (PL, DHC) | 10-year | Block-level and up |
ACS 5-year | Annually-rolling | Tract/BG (5-year smoothing) |
ACS 1-year | Annually | Places ≥65k population |
Population Estimates Program (PEP) | Annually | County-level |
Economic Census | 5-year | Industry × geography |
ACS 5-year is what you usually want for current demographics — it's available at finer geographies than 1-year and updates yearly with rolling 5-year smoothing.
Common pitfalls
Year-of-coverage vs release year. ACS 5-year 2018-2022 was released in 2023. Don't conflate.
Margins of error. ACS includes MOE for every estimate. At small geographies (block group, small tract), MOEs can be larger than the estimate. Always carry MOE through to the user.
Geography hierarchy. State (
01) → County (01001) → Tract (01001020100) → Block Group. The 11-digit tract code is state(2) + county(3) + tract(6).Place vs MSA. "Denver" can mean the City and County of Denver, OR the Denver-Aurora-Lakewood Metropolitan Statistical Area (very different boundaries and populations). Disambiguate per use case.
Population estimates lag the decennial. Between censuses, PEP estimates are extrapolated and revised. The Census Bureau revises previous PEPs each year as they reconcile with births/deaths/migration data.
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"census": {
"url": "https://gateway.pipeworx.io/census/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/census/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Census data" })The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- -licenseNot gradedqualityNot gradedmaintenanceEnables AI agents to query and retrieve public statistical data from Data Commons through search and observation tools. Provides access to demographic, economic, and other statistical indicators for analysis and research.
- AlicenseAqualityFmaintenanceEnables natural language queries of U.S. Census Bureau data, translating plain English questions into proper API calls and returning demographic, economic, and housing statistics with proper statistical interpretation and context.320MIT
- FlicenseNot gradedqualityDmaintenanceEnables access to U.S. Census Bureau data including demographics, population, income, and housing statistics. Users can query specific variables, search datasets, and retrieve geographic FIPS codes across various surveys like the American Community Survey and Decennial Census.1
- FlicenseNot gradedqualityDmaintenanceProvides access to the US Census Bureau API, allowing AI agents to retrieve demographic data and population statistics across thousands of datasets. It enables users to search for datasets, discover variable codes, and query specific geographic data like states and counties.
Related MCP Connectors
FCC broadband availability, coverage analysis, and digital divide data for US geographies.
Access US federal award, recipient, agency, and spending analytics data from USAspending.gov.
Housing Intel MCP — Meta-pack that chains FRED, BLS, ATTOM, and HUD APIs
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pipeworx-io/mcp-census'
If you have feedback or need assistance with the MCP directory API, please join our Discord server