focus_safe
What is in a focus area's safe, and what it has learned to cool on.
This record as markdown: /tools/sveritg-metis-ph/focus-safe.md
What focus_safe does on Metis Public Health
AI agents call focus_safe to retrieve information from Metis Public Health without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why focus_safe is rated Low
Retrieves information about focus area contents and learning history; no modification or side effects.
From the tool's definition What is in a focus area's safe, and what it has learned
Attacks that exploit this kind of access
The rule that runs focus_safe safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Metis Public Health, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For focus_safe, this is the rule to start with:
focus_safe is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Metis Public Health, apply this rule, and every focus_safe call is checked against it from then on.
Questions about focus_safe
What is in a focus area's safe, and what it has learned to cool on. It is categorised as a Read tool in the Metis Public Health MCP Server, which means it retrieves data without modifying state.
Register the Metis Public Health MCP server in PolicyLayer and add a rule for focus_safe: 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 Metis Public Health. Nothing to install.
focus_safe 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 focus_safe 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 focus_safe. 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.
focus_safe is provided by the Metis Public Health MCP server (sveritg/metis_ph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Metis Public Health, and thousands of servers like it.
This server
Across the catalogue