AI agents call get_withdrawable_amount to retrieve information from Bybit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries financial account data (withdrawable balance for a specific coin) but does not move money, execute trades, modify account settings, or delete data. It is a passive read operation with no side effects. While it operates in a financial domain, it performs no financial action—merely data retrieval. Severity is low because misuse only exposes information, not capital.
From the tool's definition Tool name 'get_withdrawable_amount' and description 'Get withdrawable amount for a coin' indicate a query operation that retrieves account information without modifying state or executing transactions.
Attacks that exploit this kind of access
Get withdrawable amount for a coin. It is categorised as a Read tool in the Bybit MCP Server, which means it retrieves data without modifying state.
Register the Bybit MCP server in PolicyLayer and add a rule for get_withdrawable_amount: 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. Nothing to install.
get_withdrawable_amount 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_withdrawable_amount 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_withdrawable_amount. 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_withdrawable_amount is provided by the Bybit MCP server (johnnywic/bybit-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 →