AI agents call getAccountsId to retrieve information from Mcp Upbank without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves account information without modifying, deleting, or executing any operations. It is a straightforward data query with no side effects. The blast radius of misuse is minimal—an agent could only view account details, not access funds or alter data. Severity is low because financial systems are involved, but the read-only constraint eliminates most risks.
From the tool's definition Tool name 'getAccountsId' and description 'Retrieve account' indicate a read-only retrieval operation. Server description confirms 'read-only mode' access to Up Bank API.
Documented attack patterns abuse exactly the kind of access getAccountsId gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Upbank, and nothing reaches the server without passing your rules. This is the rule we recommend for getAccountsId:
{
"version": "1",
"default": "deny",
"tools": {
"getAccountsId": {}
}
}getAccountsId is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieve account. It is categorised as a Read tool in the Mcp Upbank MCP Server, which means it retrieves data without modifying state.
Register the Mcp Upbank MCP server in PolicyLayer and add a rule for getAccountsId: 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 Mcp Upbank. Nothing to install.
getAccountsId 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 getAccountsId 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 getAccountsId. 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.
getAccountsId is provided by the Mcp Upbank MCP server (sirmews/mcp-upbank). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Upbank, 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.
13 Mcp Upbank tools catalogued and risk-classified — across an index of 43,000+ MCP servers.