AI agents call how_to_deploy to retrieve information from Myvtp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches documentation or workflow instructions for deployment. It does not itself deploy, modify, or delete anything. It is a read operation returning guidance content, similar to a 'get guide' or 'fetch instructions' call.
From the tool's definition 'Get the deployment workflow for VTP' — retrieves informational/instructional content about how to deploy; no side effects implied. 'Call this FIRST when deploying an app' confirms it is a read-only prerequisite step.
Attacks that exploit this kind of access
Get the deployment workflow for VTP. Call this FIRST when deploying an app. You are responsible for analysing the user. It is categorised as a Read tool in the Myvtp MCP Server, which means it retrieves data without modifying state.
Register the Myvtp MCP server in PolicyLayer and add a rule for how_to_deploy: 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.
how_to_deploy 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 how_to_deploy 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 how_to_deploy. 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.
how_to_deploy 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.
how_to_deploy is one line of Myvtp's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →