Return a unified diff comparing original and anonymized text.
AI agents call diff_anonymization 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.
This tool performs a comparison operation that produces a formatted diff output. It has no side effects on any data; it merely queries or derives a result from existing text. The act of comparing two versions and returning the difference is a retrieval/read operation, not a write, execute, or destructive action.
From the tool's definition Tool name 'diff_anonymization' and description 'Return a unified diff comparing original and anonymized text' indicate it retrieves and displays a comparison of two text versions.
Attacks that exploit this kind of access
Return a unified diff comparing original and anonymized text. 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 diff_anonymization: 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.
diff_anonymization 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 diff_anonymization 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 diff_anonymization. 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.
diff_anonymization 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 →