AI agents call get_crime to retrieve information from Homedata without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves crime data without side effects. It is a read-only operation that fetches public crime statistics. The data returned is informational only and does not permit modification of records, execution of code, financial transactions, or destructive operations. Severity is low because misuse would only result in exposure of publicly available crime statistics.
From the tool's definition Tool description states 'Return data.police.uk crime counts and categories for a postcode' — it retrieves and returns existing crime statistics from a public data source with no modification, creation, deletion, or execution capabilities.
Attacks that exploit this kind of access
Return data.police.uk crime counts and categories for a postcode. It is categorised as a Read tool in the Homedata MCP Server, which means it retrieves data without modifying state.
Register the Homedata MCP server in PolicyLayer and add a rule for get_crime: 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 Homedata. Nothing to install.
get_crime 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 get_crime 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 get_crime. 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.
get_crime is provided by the Homedata MCP server (wehomemove/homedata-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 →