Medium Risk

create_report

Request an SP-API report. Report is generated asynchronously — poll with get_report until processingStatus is DONE, then fetch the reportDocumentId.

How to control create_report ↓

What create_report does on Mcp Ap2

AI agents use create_report to create or update resources in Mcp Ap2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ap2 environment.

Medium Risk

Why create_report needs a policy

This tool creates a new report document (reversible action) rather than reading existing data, executing arbitrary operations, or deleting information. The creation of reports in a payment/financial system context (AP2 server) could affect audit trails and compliance records, warranting medium severity. However, report creation alone is not financial (no money movement) or destructive (reversible).

From the tool's definition Tool name 'create_report' explicitly indicates creation of a new report resource. Description states 'Request an SP-API report' with asynchronous generation, indicating a persistent artifact is being created.

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

How to control create_report

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for create_report:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_report": {
      "limits": [
        {
          "counter": "create_report_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_report stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Mcp Ap2 — 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.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about create_report

What does the create_report tool do? +

Request an SP-API report. Report is generated asynchronously — poll with get_report until processingStatus is DONE, then fetch the reportDocumentId. It is categorised as a Write tool in the Mcp Ap2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_report? +

Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for create_report: 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 Mcp Ap2. Nothing to install.

What risk level is create_report? +

create_report is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_report? +

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

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

create_report is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Ap2 tool call.

Start from Mcp Ap2, 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.

1300 Mcp Ap2 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.