review_return · FreeTaxUSA MCP Server MCP: Risk & Policy

WHAT IT DOES

What review_return does on FreeTaxUSA MCP Server

AI agents invoke review_return to trigger actions in FreeTaxUSA MCP Server. 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.

WHY IT NEEDS A POLICY

Why review_return needs a policy

This tool executes validation/review logic as part of a tax filing system. Although review itself is not destructive, it falls under Execute because it runs computational checks and interacts with an external tax system. The high severity reflects that misuse (e.g., reviewing a fraudulent return, or bypassing safeguards) could facilitate financial harm and tax filing violations.

From the tool's definition The tool is explicitly described as running an 'error check' before filing, which involves executing validation logic on tax return data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

review_return Rate-limited

review_return 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "review_return": {
      "limits": [
        {
          "counter": "review_return_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches FreeTaxUSA MCP Server, so you can run agents against it safely.

FAQ

Questions about review_return

What does the review_return tool do? +

[Phase 3 - Not yet implemented] Run error check and get review results before filing. It is categorised as a Execute tool in the FreeTaxUSA MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on review_return? +

Register the FreeTaxUSA MCP Server MCP server in PolicyLayer and add a rule for review_return: 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 FreeTaxUSA MCP Server. Nothing to install.

What risk level is review_return? +

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

Can I rate-limit review_return? +

Yes. Add a rate_limit block to the review_return 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 review_return completely? +

Set action: deny in the PolicyLayer policy for review_return. 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 review_return? +

review_return is provided by the FreeTaxUSA MCP Server MCP server (schwarztim/freetaxusa-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.