Toggle automatic Gemini consultation when uncertainty is detected
AI agents use toggle_gemini_auto_consult to create or update resources in HRFCO Service — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your HRFCO Service environment.
This tool modifies a configuration setting (enabling/disabling automatic Gemini consultation), which is a reversible write operation. It changes system behavior but does not delete data, execute arbitrary code, or have financial implications. Severity is medium because toggling this setting could affect the quality/reliability of automated responses in a hydrological monitoring context.
From the tool's definition Toggle automatic Gemini consultation when uncertainty is detected
Attacks that exploit this kind of access
Toggle automatic Gemini consultation when uncertainty is detected. It is categorised as a Write tool in the HRFCO Service MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the HRFCO Service MCP server in PolicyLayer and add a rule for toggle_gemini_auto_consult: 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.
toggle_gemini_auto_consult is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the toggle_gemini_auto_consult 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 toggle_gemini_auto_consult. 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.
toggle_gemini_auto_consult 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 →