AI agents call gov.fair-market-rent to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a straightforward data retrieval operation against a public housing reference dataset. It accepts parameters (FIPS code, state code, year) and returns rent information—typical of a search/get operation with no side effects. No capability to modify data, execute code, delete records, or move money. Classification as Read is appropriate.
From the tool's definition Tool retrieves HUD Fair Market Rents data by geographic area (county FIPS or state) and optional year. Description indicates querying/fetching public reference data with no modification, deletion, or financial transaction capability.
Attacks that exploit this kind of access
HUD Fair Market Rents by area (Efficiency–4BR). Pass a 5-digit county FIPS or a 2-letter state, optional year. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for gov.fair-market-rent: 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 Mcp. Nothing to install.
gov.fair-market-rent 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 gov.fair-market-rent 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 gov.fair-market-rent. 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.
gov.fair-market-rent is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →