List all Actual Budget accounts with current balances
AI agents call crow_actual_accounts to retrieve information from Crow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query that retrieves financial account information and balances. While the data is sensitive (financial account details), the tool itself performs no write, execute, or destructive operations. It is categorized as Read rather than Financial because it only queries/lists existing data without moving money, creating transactions, or committing financial obligations.
From the tool's definition Tool name 'crow_actual_accounts' and description 'List all Actual Budget accounts with current balances' indicates retrieval of financial account data without modification or deletion.
Documented attack patterns abuse exactly the kind of access crow_actual_accounts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for crow_actual_accounts:
{
"version": "1",
"default": "deny",
"tools": {
"crow_actual_accounts": {}
}
}crow_actual_accounts 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.
List all Actual Budget accounts with current balances. It is categorised as a Read tool in the Crow MCP Server, which means it retrieves data without modifying state.
Register the Crow MCP server in PolicyLayer and add a rule for crow_actual_accounts: 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 Crow. Nothing to install.
crow_actual_accounts 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 crow_actual_accounts 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 crow_actual_accounts. 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.
crow_actual_accounts is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, 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.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.