add_tracked_file
AI agents use add_tracked_file 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.
The 'add_' prefix and naming pattern consistent with sibling tools (add_glossary_term, add_journal_entry, add_memory_entry, etc.) indicates this tool creates or registers new data. Given the Metis context as a local-first research companion that indexes PDFs and maintains user data, 'add_tracked_file' likely registers files for tracking/indexing purposes.
From the tool's definition Tool name 'add_tracked_file' indicates creation or modification of file tracking state; description is empty, limiting specificity of assessment.
Attacks that exploit this kind of access
add_tracked_file. 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 add_tracked_file: 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.
add_tracked_file 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 add_tracked_file 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 add_tracked_file. 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.
add_tracked_file 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 →