AI agents call gemini_query to retrieve information from Geoseo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from Gemini/Google Search with grounding. It has no side effects on data, no code execution capability, and no destructive or financial operations. It is a straightforward read operation that fetches and returns search-grounded answers. Severity is low because misuse would only return unwanted information to the user, with no blast radius to external systems or data integrity.
From the tool's definition Tool description explicitly states 'Ask Gemini...a question; return answer + cited URLs.' The verbs 'ask' and 'return' indicate retrieval of information.
Attacks that exploit this kind of access
Ask Gemini (with Google Search grounding) a question; return answer + cited URLs. It is categorised as a Read tool in the Geoseo MCP Server, which means it retrieves data without modifying state.
Register the Geoseo MCP server in PolicyLayer and add a rule for gemini_query: 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 Geoseo. Nothing to install.
gemini_query 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 gemini_query 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 gemini_query. 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.
gemini_query is provided by the Geoseo MCP server (rachit8484/geoseo-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 →