Consult Gemini for a second opinion or additional perspective
AI agents call consult_gemini to retrieve information from HRFCO Service without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves analytical perspective or advice from Gemini (presumably a separate AI model) without modifying any underlying hydrological data or triggering external operations. It reads existing data and returns an opinion. While the exact behavior depends on Gemini's capabilities, the tool itself is presented as a query mechanism.
From the tool's definition Tool description states 'Consult Gemini for a second opinion or additional perspective' - the verb 'consult' indicates data retrieval and querying rather than modification or execution of external operations. No side effects or state changes are mentioned.
Attacks that exploit this kind of access
Consult Gemini for a second opinion or additional perspective. It is categorised as a Read tool in the HRFCO Service MCP Server, which means it retrieves data without modifying state.
Register the HRFCO Service MCP server in PolicyLayer and add a rule for consult_gemini: 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 HRFCO Service. Nothing to install.
consult_gemini 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 consult_gemini 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 consult_gemini. 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.
consult_gemini is provided by the HRFCO Service MCP server (kwenhwang/hrfco-service). 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 →