render.env_list · MCP Fullstack MCP: Risk & Policy

WHAT IT DOES

What render.env_list does on MCP Fullstack

AI agents call render.env_list to retrieve information from MCP Fullstack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

WHY IT NEEDS A POLICY

Why render.env_list needs a policy

This tool retrieves environment variables without altering them. While environment variables may contain sensitive information (credentials, API keys, secrets), the tool itself performs no side effects—it only queries/exposes data. Severity is medium rather than low because leaked environment variables could expose secrets, though the tool's primary function is informational Read access.

From the tool's definition Tool name 'render.env_list' and description 'List environment variables' indicate a retrieval operation with no modification. The verb 'list' is a classic Read operation.

Attacks that exploit this kind of access

Questions about render.env_list

What does the render.env_list tool do? +

List environment variables. It is categorised as a Read tool in the MCP Fullstack MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on render.env_list? +

Register the MCP Fullstack MCP server in PolicyLayer and add a rule for render.env_list: 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 MCP Fullstack. Nothing to install.

What risk level is render.env_list? +

render.env_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit render.env_list? +

Yes. Add a rate_limit block to the render.env_list 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.

How do I block render.env_list completely? +

Set action: deny in the PolicyLayer policy for render.env_list. 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.

What MCP server provides render.env_list? +

render.env_list is provided by the MCP Fullstack MCP server (jacobfv/mcp-fullstack). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.