Debug tool: List ALL accounts with their types and subtypes to help diagnose account detection issues
AI agents call debug_accounts to retrieve information from Wave Accounting MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and displays account information for diagnostic purposes. It performs a read-only operation that retrieves data about accounts (types and subtypes) without creating, modifying, deleting, or executing any transactional changes. Even though it accesses financial system data (Wave Accounting), the action itself is purely informational retrieval, making it a Read category tool with low severity.
From the tool's definition Tool name is 'debug_accounts' and description states 'List ALL accounts' - a retrieval operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access debug_accounts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Wave Accounting MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for debug_accounts:
{
"version": "1",
"default": "deny",
"tools": {
"debug_accounts": {}
}
}debug_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.
Debug tool: List ALL accounts with their types and subtypes to help diagnose account detection issues. It is categorised as a Read tool in the Wave Accounting MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Wave Accounting MCP Server MCP server in PolicyLayer and add a rule for debug_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 Wave Accounting MCP Server. Nothing to install.
debug_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 debug_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 debug_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.
debug_accounts is provided by the Wave Accounting MCP Server MCP server (vinnividivicci/wave_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Wave Accounting MCP Server, 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.
9 Wave Accounting MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.