census_demographics
Race, ethnicity, and age breakdown for a US geography. Returns counts for white, black, Asian, AIAN, NHPI, other, two-or-more, plus Hispanic/Latino total and median age. Source: ACS 5-year.
This record as markdown: /tools/io-github-blackboxfoundry-livedatalink/census-demographics.md
What census_demographics does on Livedatalink
AI agents call census_demographics to retrieve information from Livedatalink without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
msa | string | — | 5-digit Metropolitan Statistical Area code. Required for msa level. |
year | number | — | ACS 5-year endpoint year (default 2023). |
zcta | string | — | 5-digit ZIP Code Tabulation Area. Required for zcta level. |
level | string | Yes | Geography level: 'us', 'state', 'county', 'zcta' (ZIP), 'place' (city), 'tract', 'msa'. |
place | string | — | Census place FIPS (city). Required for place level. |
state | string | — | 2-letter state code (e.g. 'TX') or 2-digit FIPS. Required for state/county/place/tract levels. |
tract | string | — | 6-digit census tract code. Use '*' for all tracts in a county. |
county | string | — | 3-digit county FIPS. Use '*' for all counties in a state. Required for county/tract levels. |
Parameters from the server's own tool schema.
Why census_demographics is rated Low
Even though census_demographics only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs census_demographics safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Livedatalink, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For census_demographics, this is the rule to start with:
census_demographics is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Livedatalink, apply this rule, and every census_demographics call is checked against it from then on.
Questions about census_demographics
Race, ethnicity, and age breakdown for a US geography. Returns counts for white, black, Asian, AIAN, NHPI, other, two-or-more, plus Hispanic/Latino total and median age. Source: ACS 5-year. It is categorised as a Read tool in the Livedatalink MCP Server, which means it retrieves data without modifying state.
census_demographics accepts 8 parameters: msa, year, zcta, level, place, state, tract, county. Required: level. The full parameter table on this page comes from the server's own tool schema.
Register the Livedatalink MCP server in PolicyLayer and add a rule for census_demographics: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Livedatalink. Nothing to install.
census_demographics is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the census_demographics rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for census_demographics. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
census_demographics is provided by the Livedatalink MCP server (https://livedatalink.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Livedatalink, and thousands of servers like it.
This server
Across the catalogue