AI agents use update_app_readme to create or update resources in Myvtp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Myvtp environment.
This tool creates or modifies data (app readme/documentation) in a reversible manner without deleting data. It falls squarely into the Write category. Severity is medium because modifying documentation could mislead users about app functionality or requirements, but the change is easily correctable and doesn't affect the app's runtime behavior or data integrity directly.
From the tool's definition Tool name 'update_app_readme' and description explicitly states 'Update the readme/documentation for a deployed app.' The operation modifies app documentation reversibly.
Attacks that exploit this kind of access
Update the readme/documentation for a deployed app. Supports full markdown. Use this to set or update an app. It is categorised as a Write tool in the Myvtp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Myvtp MCP server in PolicyLayer and add a rule for update_app_readme: 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 Myvtp. Nothing to install.
update_app_readme 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_app_readme 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_app_readme. 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_app_readme is provided by the Myvtp MCP server (myvtp/mcp). 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 →