evaluate_against_layers
AI agents call evaluate_against_layers to retrieve information from Metis Public Health without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'evaluate_against_layers' indicates a query or comparison operation rather than data creation, modification, or deletion. Without explicit description stating it modifies, deletes, executes external commands, or commits financial actions, and given the research-focused nature of the Metis server, classification as Read is most appropriate.
From the tool's definition Tool name 'evaluate_against_layers' suggests evaluation/analysis of data against criteria. The description is empty, providing no explicit functional details.
Attacks that exploit this kind of access
evaluate_against_layers. 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 evaluate_against_layers: 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.
evaluate_against_layers 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 evaluate_against_layers 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 evaluate_against_layers. 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.
evaluate_against_layers 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.
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 →