get_consent_ledger
AI agents call get_consent_ledger 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 'get_' prefix strongly suggests a read operation that retrieves stored consent ledger data without modification. This aligns with the Read category (retrieves or queries data; no side effects). Given the context of a research/health companion managing user data locally, a consent ledger is most likely a log or record that tracks user permissions—querying it would be a non-destructive retrieval.
From the tool's definition Tool name 'get_consent_ledger' uses the 'get' verb, which by convention indicates a retrieval operation. The description is empty, so categorization relies on naming patterns observed across sibling tools.
Attacks that exploit this kind of access
get_consent_ledger. 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 get_consent_ledger: 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.
get_consent_ledger 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 get_consent_ledger 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 get_consent_ledger. 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.
get_consent_ledger 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 →