This record as markdown: /tools/2captcha/get-balance.md
What get_balance does on 2captcha
AI agents call get_balance to retrieve information from 2captcha without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_balance is rated Low
The tool only retrieves the current balance from the user's 2Captcha account. It does not modify, delete, or move funds—it simply queries and returns data. This is a straightforward Read operation with minimal risk. Severity is low because even if exposed to an AI agent, the worst outcome is information disclosure of the account balance, which has limited blast radius.
From the tool's definition Tool name is 'get_balance' and description states 'Check your 2Captcha account balance.' This is a read-only query operation that retrieves account information with no side effects.
Attacks that exploit this kind of access
The rule that runs get_balance safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 2captcha, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_balance, this is the rule to start with:
get_balance is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 2captcha, apply this rule, and every get_balance call is checked against it from then on.
Questions about get_balance
Check your 2Captcha account balance. It is categorised as a Read tool in the 2captcha MCP Server, which means it retrieves data without modifying state.
Register the 2captcha MCP server in PolicyLayer and add a rule for get_balance: 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 2captcha. Nothing to install.
get_balance 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_balance 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_balance. 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_balance is provided by the 2captcha MCP server (2captcha-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 2captcha, and thousands of servers like it.
This server
Across the catalogue