Deploy a web app to VTP. WARNING: Deployment is a production action. Redeployment replaces the running app. Ensure the code is correct and the configuration preserves existing connections and volumes before deploying. Deployment happens asynchronously - this tool returns immediately and the app b...
AI agents invoke deploy to trigger actions in Myvtp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a complex external operation (application deployment to production infrastructure) whose effects depend entirely on what code and configuration the AI agent provides. While deployment itself isn't inherently destructive (blue-green strategy preserves old version), it is an Execute action that modifies live production state and can cause service interruption if misconfigured.
From the tool's definition Tool name 'deploy' with description stating it 'Deploy[s] a web app to VTP' and explicitly warns 'Redeployment replaces the running app' and triggers asynchronous server-side build operations whose effects depend on code/configuration arguments.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Deploy a web app to VTP. WARNING: Deployment is a production action. Redeployment replaces the running app. Ensure the code is correct and the configuration preserves existing connections and volumes before deploying. Deployment happens asynchronously - this tool returns immediately and the app builds server-side. Use get_deploy_status to monitor build progress. For redeploying, the previous version stays live until the new build completes (zero-downtime blue-green deployment). Prerequisites: 1. Call detect_framework first and fix any validation errors or warnings 2. Call get_deployment_guide for framework-specific configuration 3. Run the build locally (e.g. npm run build) and fix any errors — never deploy code that has not built successfully 4. Create a vtp.md file in the project root (alongside vtp.yaml). This becomes the app. It is categorised as a Execute tool in the Myvtp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Myvtp MCP server in PolicyLayer and add a rule for 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.
deploy is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the 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 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.
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.
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 →