Create a Vercel deployment. Pass deployment_id to redeploy an existing commit, or project_id + git_ref to deploy fresh from git. Set force_new=true to skip the build cache (needed after env var changes or when serverless function surfaces change).
AI agents invoke vercel_create_deployment to trigger actions in UnClick. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | |
target | string | — | 'production' (default) or 'preview'. |
api_key | string | — | |
git_ref | string | — | Branch or SHA to deploy. Defaults to 'main'. |
team_id | string | — | |
force_new | boolean | — | Skip build cache. Default false. |
project_id | string | — | Deploy fresh from the project's linked git repo. |
deployment_id | string | — | Redeploy the git source of this existing deployment. |
Parameters from the server's own tool schema.
This tool initiates a deployment to Vercel, which runs build processes, executes code, and publishes services to production infrastructure. While it creates a new deployment (Write-like), the primary risk is that it triggers external execution of build pipelines and potentially overwrites live production environments.
From the tool's definition 'Create a Vercel deployment' and 'deploy fresh from git' — triggers an external deployment operation on Vercel infrastructure
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
Create a Vercel deployment. Pass deployment_id to redeploy an existing commit, or project_id + git_ref to deploy fresh from git. Set force_new=true to skip the build cache (needed after env var changes or when serverless function surfaces change). It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
vercel_create_deployment accepts 8 parameters: name, target, api_key, git_ref, team_id, force_new, project_id, deployment_id. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for vercel_create_deployment: 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 UnClick. Nothing to install.
vercel_create_deployment 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 vercel_create_deployment 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 vercel_create_deployment. 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.
vercel_create_deployment is provided by the UnClick MCP server (@unclick/mcp-server). 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 →