Delete one or more environment variables from your Rails application on Hatchbox. This tool uses the Hatchbox API to remove environment variables, which will take effect on the next deployment. Useful for cleaning up deprecated configuration or removing sensitive data. Example response: Successfu...
AI agents call deleteEnvVars to permanently remove resources in Playwright Stealth — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes environment variables from a production Rails application via the Hatchbox API. Deletion of configuration values cannot be undone without manual restoration. While not a database deletion, it permanently removes application configuration that affects system behavior and could disrupt services if production variables are incorrectly deleted.
From the tool's definition The tool description explicitly states it "Delete[s] one or more environment variables" and "will take effect on the next deployment." The example response shows "Successfully deleted environment variables" confirming irreversible removal.
Documented attack patterns abuse exactly the kind of access deleteEnvVars gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright Stealth, and nothing reaches the server without passing your rules. This is the rule we recommend for deleteEnvVars:
{
"version": "1",
"default": "deny",
"hide": [
"deleteEnvVars"
]
}deleteEnvVars disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete one or more environment variables from your Rails application on Hatchbox. This tool uses the Hatchbox API to remove environment variables, which will take effect on the next deployment. Useful for cleaning up deprecated configuration or removing sensitive data. Example response: Successfully deleted environment variables: OLD_API_KEY, DEPRECATED_FLAG 23 environment variables remaining. Use cases: - Removing deprecated API keys or credentials - Cleaning up after feature flag removal - Removing temporary configuration values - Deleting test or staging variables from production - Removing unused third-party service configurations - Batch cleanup of multiple obsolete variables Important notes: - Changes require a deployment to take effect - Deleted variables cannot be recovered - verify before deletion - Use getEnvVars to see current variables before deletion - Requires READONLY=false in configuration - Be cautious when deleting critical variables like database URLs. It is categorised as a Destructive tool in the Playwright Stealth MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Playwright Stealth MCP server in PolicyLayer and add a rule for deleteEnvVars: 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 Playwright Stealth. Nothing to install.
deleteEnvVars is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the deleteEnvVars 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 deleteEnvVars. 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.
deleteEnvVars is provided by the Playwright Stealth MCP server (pulsemcp/mcp-servers). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright Stealth, 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.
68 Playwright Stealth tools catalogued and risk-classified — across an index of 43,000+ MCP servers.