High Risk →

crow_tax_calculate

Run the full tax calculation and return a summary with audit trail.

How to control crow_tax_calculate ↓

What crow_tax_calculate does on Crow

AI agents invoke crow_tax_calculate to trigger actions in Crow. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

High Risk

Why crow_tax_calculate needs a policy

This tool executes a tax calculation workflow, which is a non-trivial computational operation. While not destructive or financial in itself, executing unvalidated tax calculations could produce incorrect audit trails, misleading financial records, or compliance violations if misused by an agent without proper input validation. The 'audit trail' component suggests state mutation.

From the tool's definition Tool name 'crow_tax_calculate' combined with description 'Run the full tax calculation and return a summary with audit trail' indicates execution of a computational process with potential side effects (audit trail generation).

Documented attack patterns abuse exactly the kind of access crow_tax_calculate gives an agent:

How to control crow_tax_calculate

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_tax_calculate:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "crow_tax_calculate": {
      "limits": [
        {
          "counter": "crow_tax_calculate_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

crow_tax_calculate stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Crow — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about crow_tax_calculate

What does the crow_tax_calculate tool do? +

Run the full tax calculation and return a summary with audit trail. It is categorised as a Execute tool in the Crow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on crow_tax_calculate? +

Register the Crow MCP server in PolicyLayer and add a rule for crow_tax_calculate: 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.

What risk level is crow_tax_calculate? +

crow_tax_calculate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit crow_tax_calculate? +

Yes. Add a rate_limit block to the crow_tax_calculate 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.

How do I block crow_tax_calculate completely? +

Set action: deny in the PolicyLayer policy for crow_tax_calculate. 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.

What MCP server provides crow_tax_calculate? +

crow_tax_calculate 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.

Enforce policy on every Crow tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.