Scan all registered project folders for activity. Refreshes CLAUDE.md for each.
AI agents use update_all_projects 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 reads project metadata and writes updates to CLAUDE.md files across multiple projects. While it modifies files, the changes appear to be refreshes/regenerations of documentation rather than irreversible deletions, making it Write rather than Destructive.
From the tool's definition Tool description states it 'Refreshes CLAUDE.md for each' project, indicating modification of files. The verb 'scan' and 'refresh' imply reading and then writing back updated state.
Attacks that exploit this kind of access
Scan all registered project folders for activity. Refreshes CLAUDE.md for each. 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 update_all_projects: 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.
update_all_projects 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 update_all_projects 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 update_all_projects. 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.
update_all_projects 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 →