Retrieve a Dock account by id. Returns balance, status, holder info, and account coordinates (agency / account number).
AI agents call get_account to retrieve information from Mcp Ap2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves financial account information including balances and account identifiers. While it is fundamentally a Read operation (no side effects), the sensitivity of the data returned (account balance, holder information, account coordinates) elevates severity to medium. An AI agent misusing this tool could gather financial reconnaissance on accounts, though it cannot directly move money or modify accounts.
From the tool's definition The tool description explicitly states "Retrieve a Dock account by id" and lists the return values as "balance, status, holder info, and account coordinates (agency / account number)." These are all information retrieval operations with no modification or…
Documented attack patterns abuse exactly the kind of access get_account gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for get_account:
{
"version": "1",
"default": "deny",
"tools": {
"get_account": {}
}
} get_account 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 a Dock account by id. Returns balance, status, holder info, and account coordinates (agency / account number). It is categorised as a Read tool in the Mcp Ap2 MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for get_account: 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 Ap2. Nothing to install.
get_account 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_account 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_account. 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_account is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, 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.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.