search_states
AI agents call search_states to retrieve information from SQLite Geography Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite having an empty description, the tool name 'search_states' and the context of sibling read-only tools (all prefixed with 'get_') indicate this performs a query or search operation over geographical state/province data. There is no indication of mutation, deletion, code execution, or financial operations. The verb 'search' in context of a geography database suggests read-only retrieval.
From the tool's definition Tool name 'search_states' combined with sibling tools (get_all_regions, get_cities_in_country, get_countries, etc.) that are all read-only queries.
Attacks that exploit this kind of access
search_states. It is categorised as a Read tool in the SQLite Geography Server MCP Server, which means it retrieves data without modifying state.
Register the SQLite Geography Server MCP server in PolicyLayer and add a rule for search_states: 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 SQLite Geography Server. Nothing to install.
search_states 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 search_states 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 search_states. 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.
search_states is provided by the SQLite Geography Server MCP server (pdichone/mcp-course-code). 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 →