AI agents call vercel_env to retrieve information from Access without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although this tool only retrieves data (Read category), the severity is elevated to 'high' because: (1) environment variable names often leak sensitive information about infrastructure, API integrations, and configuration patterns even when values are redacted; (2) in a credential store context, this exposes the attack surface and dependencies of a Vercel project; (3) an agent with unrestricted access could map an…
From the tool's definition Tool description states 'List all environment variables configured for a Vercel project' and 'Returns variable names and targets but redacts secret values.' This is a read/retrieval operation with no modification capability.
Attacks that exploit this kind of access
List all environment variables configured for a Vercel project, grouped by target environment (production, preview, development). Returns variable names and targets but redacts secret values. It is categorised as a Read tool in the Access MCP Server, which means it retrieves data without modifying state.
Register the Access MCP server in PolicyLayer and add a rule for vercel_env: 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 Access. Nothing to install.
vercel_env 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 vercel_env 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_env. 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_env is provided by the Access MCP server (scottpedia0/access). 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 →