Create a new environment variable for a project
AI agents use vercel_create_env_var to create or update resources in Vercel — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vercel environment.
Creating environment variables is a Write operation as it modifies project configuration in a reversible manner. Severity is high because environment variables often contain secrets, API keys, database credentials, or other sensitive configuration that could impact application security, deployment behavior, or data access if set to malicious values by a compromised agent.
From the tool's definition Tool name is vercel_create_env_var and description states 'Create a new environment variable for a project' — this creates and modifies configuration data reversibly.
Documented attack patterns abuse exactly the kind of access vercel_create_env_var gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Vercel, and nothing reaches the server without passing your rules. This is the rule we recommend for vercel_create_env_var:
{
"version": "1",
"default": "deny",
"tools": {
"vercel_create_env_var": {
"limits": [
{
"counter": "vercel_create_env_var_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}vercel_create_env_var stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a new environment variable for a project. It is categorised as a Write tool in the Vercel MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vercel MCP server in PolicyLayer and add a rule for vercel_create_env_var: 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.
vercel_create_env_var 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 vercel_create_env_var 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_env_var. 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_env_var is provided by the Vercel MCP server (xiayeai/vercel-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Vercel, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Vercel tools catalogued and risk-classified — across an index of 43,000+ MCP servers.