AI agents call get-state to retrieve information from Addressr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves state information (name and abbreviation) from provided URLs, consistent with query/lookup operations on address data. The operation has no side effects and returns read-only data, matching the 'Read' category. Severity is low due to minimal blast radius — retrieving state details poses no risk of data loss, unwanted modifications, or downstream harmful effects.
From the tool's definition Tool name 'get-state' and description 'Get full state details by URL' indicate a retrieval operation. No modification, deletion, execution, or financial operation is described.
Attacks that exploit this kind of access
Get full state details by URL. Follow the canonical link from search results to retrieve state name and abbreviation. It is categorised as a Read tool in the Addressr MCP Server, which means it retrieves data without modifying state.
Register the Addressr MCP server in PolicyLayer and add a rule for get-state: 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 Addressr. Nothing to install.
get-state 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-state 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-state. 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-state is provided by the Addressr MCP server (mountain-pass/addressr-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 →