Retrieve all environment variables from your Rails application running on Hatchbox via SSH. This tool connects to your server and reads environment variables directly from the running puma process, providing a complete view of your application
AI agents call getEnvVars to retrieve information from Langfuse Observability without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read category tool because it retrieves data (environment variables) without side effects or modifications. However, severity is rated high because environment variables often contain sensitive secrets such as API keys, database credentials, authentication tokens, and other confidential configuration data that could enable lateral movement or privilege escalation if disclosed to an AI agent or attacker.
From the tool's definition The tool "retrieves...environment variables from your Rails application" and "reads environment variables directly from the running puma process, providing a complete view of your application." This is explicitly a retrieval operation with no modification…
Attacks that exploit this kind of access
Retrieve all environment variables from your Rails application running on Hatchbox via SSH. This tool connects to your server and reads environment variables directly from the running puma process, providing a complete view of your application. It is categorised as a Read tool in the Langfuse Observability MCP Server, which means it retrieves data without modifying state.
Register the Langfuse Observability MCP server in PolicyLayer and add a rule for getEnvVars: 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 Langfuse Observability. Nothing to install.
getEnvVars 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 getEnvVars 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 getEnvVars. 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.
getEnvVars is provided by the Langfuse Observability MCP server (langfuse-observability-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 →