scan_pubmed_alerts
AI agents call scan_pubmed_alerts 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 retrieves alert information from PubMed (a public medical literature database). The 'scan' operation implies fetching and reviewing data with no side effects—a Read category action. However, confidence is moderate because the description is empty, leaving uncertainty about whether it might also trigger alert subscriptions or perform writes.
From the tool's definition Tool name 'scan_pubmed_alerts' indicates querying/retrieving alert data from PubMed; the 'scan' verb suggests iterating over read-only results without modification.
Attacks that exploit this kind of access
scan_pubmed_alerts. 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 scan_pubmed_alerts: 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.
scan_pubmed_alerts 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 scan_pubmed_alerts 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 scan_pubmed_alerts. 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.
scan_pubmed_alerts 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 →