AI agents call get_broadband 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 retrieves factual broadband availability information from Ofcom data for a given postcode. It performs a read-only query with no side effects, no data modification, and no external command execution. The data returned is public infrastructure information. Blast radius is minimal: even if an AI misuses this tool, it can only retrieve pre-existing public data about broadband availability.
From the tool's definition Tool description states 'Return Ofcom broadband availability and speeds for a postcode' — a query operation that retrieves public infrastructure data with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Return Ofcom broadband availability and speeds 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_broadband: 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_broadband 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_broadband 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_broadband. 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_broadband 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 →