Scan inputs/literature/ for new PDFs and register them in literature_metadata.
AI agents use scan_literature to create or update resources in Metis Public Health — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Metis Public Health environment.
This tool scans a directory for PDF files and registers/writes their metadata into a tracking store (literature_metadata). It creates new records but does not delete, execute code, or involve financial actions. The blast radius is low — worst case it registers unintended files into a metadata index, which is reversible.
From the tool's definition 'Scan inputs/literature/ for new PDFs and register them in literature_metadata'
Attacks that exploit this kind of access
Scan inputs/literature/ for new PDFs and register them in literature_metadata. It is categorised as a Write tool in the Metis Public Health MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Metis Public Health MCP server in PolicyLayer and add a rule for scan_literature: 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_literature is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the scan_literature 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_literature. 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_literature 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 →