List all environment variables/secrets for a repl
AI agents call get_secrets to retrieve information from Replit MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation—it retrieves sensitive data (secrets/environment variables) from a repl. While classified as Read, severity is high because secrets often contain credentials, API keys, and other sensitive information that could enable further attacks if exposed to an AI agent without proper controls. The tool does not modify or delete data, so it does not qualify as Write, Execute, Destructive, or Financial.
From the tool's definition Tool name 'get_secrets' and description 'List all environment variables/secrets for a repl' indicate data retrieval without modification. No side effects mentioned.
Attacks that exploit this kind of access
List all environment variables/secrets for a repl. It is categorised as a Read tool in the Replit MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Replit MCP Server MCP server in PolicyLayer and add a rule for get_secrets: 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 Replit MCP Server. Nothing to install.
get_secrets 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_secrets 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_secrets. 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_secrets is provided by the Replit MCP Server MCP server (nova-3951/replit-mcp). 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 →