Submit a Norwegian VAT return (MVA-melding) in Apier's SANDBOX — a zero-risk, fully simulated environment that NEVER contacts a real government system. No Altinn, Maskinporten, Skatteetaten, or NAV call is ever made; every response is built from in-code synthetic fixtures, so nothing you do here ...
Risk signalsAccepts raw HTML/template content (payload)
Part of the Mcp server.
Free to start. No card required.
AI agents may call submit_vat_return to permanently remove or destroy resources in Mcp. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call submit_vat_return in a loop, permanently destroying resources in Mcp. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"submit_vat_return"
]
}See the full Mcp policy for all 13 tools.
These attack patterns abuse exactly the kind of access submit_vat_return gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Submit a Norwegian VAT return (MVA-melding) in Apier's SANDBOX — a zero-risk, fully simulated environment that NEVER contacts a real government system. No Altinn, Maskinporten, Skatteetaten, or NAV call is ever made; every response is built from in-code synthetic fixtures, so nothing you do here files a binding return. The tool has two modes, chosen by whether you supply an approval_token. Call it WITHOUT an approval_token to PREVIEW: it runs the same precondition checks a live filing would (company exists, system-user authorised, scopes delegated, deadline in the future, payload shape) and returns the dry-run verdict, filing NOTHING. Call it WITH an approval_token — a single-use sandbox approval token a human operator obtains out-of-band from the sandbox approval-token route — to FILE the mock return: the sandbox validates the token and returns a signed sandbox receipt (altinn_receipt_id, audit_log_id, an HMAC-SHA256 signature) carrying an explicit not-a-real-government-response marker. This demonstrates the staged, human-gated, audited execution story end to end with no binding write. The action is permanently fixed to mva_melding (VAT) — this tool cannot submit any other filing type. Use only the reserved synthetic sandbox org numbers. Required scope: read:actions (the same read scope as the dry-run validator — the tool never holds or needs a write or act scope, because the human approval gate, not the agent, authorises the mock filing). Failure modes: VALIDATION_FAILED on a non-9-digit org_number, an oversized payload, or a malformed approval_token; AUTH_EXPIRED_TOKEN from the route when a supplied token does not validate.. It is categorised as a Destructive tool in the Mcp MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP server in PolicyLayer and add a rule for submit_vat_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 Mcp. Nothing to install.
submit_vat_return is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the submit_vat_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.
Set action: deny in the PolicyLayer policy for submit_vat_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.
submit_vat_return is provided by the MCP server (https://www.apier.no/api/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 Mcp 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.