AI agents call getDeployments to retrieve information from Vercel without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves a list of deployment records from the Vercel API. It performs no modifications, deletions, or execution of external operations—purely informational retrieval. The blast radius of misuse is minimal, as an attacker could only view deployment metadata they may not have authorized access to, but cannot alter or delete deployments.
From the tool's definition Tool name: 'getDeployments'. Description: 'Lists deployments'. The verb 'Lists' and 'get' prefix indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Lists deployments. It is categorised as a Read tool in the Vercel MCP Server, which means it retrieves data without modifying state.
Register the Vercel MCP server in PolicyLayer and add a rule for getDeployments: 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 Vercel. Nothing to install.
getDeployments 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 getDeployments 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 getDeployments. 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.
getDeployments is provided by the Vercel MCP server (ozztec/vercel-api-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 →