AI agents call get_env_variable to retrieve information from Test without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data (environment variables) with no side effects or data modification. It qualifies as a Read operation. However, severity is elevated to 'medium' rather than 'low' because environment variables may contain sensitive information such as API keys, credentials, database passwords, or other secrets.
From the tool's definition Tool name 'get_env_variable' and description 'Retrieve the value of an environment variable' indicate a read-only operation that queries system state without modification.
Attacks that exploit this kind of access
Retrieve the value of an environment variable. It is categorised as a Read tool in the Test MCP Server, which means it retrieves data without modifying state.
Register the Test MCP server in PolicyLayer and add a rule for get_env_variable: 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 Test. Nothing to install.
get_env_variable 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 get_env_variable 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 get_env_variable. 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.
get_env_variable is provided by the Test MCP server (sampsonky/mcp-vulnerable-server-demo). 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 →