No-argument front door. Call this when a user asks for tax / accounting help but you don't yet know WHAT they want or WHERE. Returns the two scoping questions to ask plus the available intents and jurisdictions. Once you have an intent, call start(intent, jurisdiction). Use this instead of callin...
Part of the OpenAccountants server.
Free to start. No card required.
AI agents invoke start_help to trigger processes or run actions in OpenAccountants. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
start_help can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"start_help": {
"limits": [
{
"counter": "start_help_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full OpenAccountants policy for all 13 tools.
These attack patterns abuse exactly the kind of access start_help gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
No-argument front door. Call this when a user asks for tax / accounting help but you don't yet know WHAT they want or WHERE. Returns the two scoping questions to ask plus the available intents and jurisdictions. Once you have an intent, call start(intent, jurisdiction). Use this instead of calling start with empty arguments.. It is categorised as a Execute tool in the OpenAccountants MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenAccountants MCP server in PolicyLayer and add a rule for start_help: 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 OpenAccountants. Nothing to install.
start_help is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_help 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 start_help. 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.
start_help is provided by the OpenAccountants MCP server (pypi:openaccountants-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 OpenAccountants tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.