Get secret key from environment variables
AI agents call get_secret_key to retrieve information from Bybit MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
While this is technically a Read operation (retrieval without side effects), it retrieves a highly sensitive credential (secret key) used for API authentication. Exposure of this key to an unauthorized agent would allow complete account compromise and unauthorized trading. The high severity reflects the critical nature of the data being accessed, even though the operation itself is non-destructive.
From the tool's definition Tool name: 'get_secret_key'; description: 'Get secret key from environment variables'. The tool retrieves a secret key from environment variables without modifying or deleting it.
Attacks that exploit this kind of access
Get secret key from environment variables. It is categorised as a Read tool in the Bybit MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Bybit MCP Server MCP server in PolicyLayer and add a rule for get_secret_key: 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 Bybit MCP Server. Nothing to install.
get_secret_key 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_secret_key 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_secret_key. 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_secret_key is provided by the Bybit MCP Server MCP server (kondisettyravi/mcp-bybit-node). 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 →