Structured risk score (0-100) with named level (lav/moderat/høy/kritisk) and component breakdown for a Norwegian COMPANY's financial health. Combines distress classification, BRREG status, age, capital signals and other factors into one comparable score. Returns blocked_enk error for sole-proprie...
Part of the Firmaradar server.
Free to start. No card required.
AI agents call firmaradar_get_risk_score to retrieve information from Firmaradar without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though firmaradar_get_risk_score only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"firmaradar_get_risk_score": {}
}
}See the full Firmaradar policy for all 31 tools.
These attack patterns abuse exactly the kind of access firmaradar_get_risk_score gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Structured risk score (0-100) with named level (lav/moderat/høy/kritisk) and component breakdown for a Norwegian COMPANY's financial health. Combines distress classification, BRREG status, age, capital signals and other factors into one comparable score. Returns blocked_enk error for sole-proprietorships (ENK). SCOPE: Company financial health only. NOT a personal credit check on owners or officers. For full KYC pre-screening, combine with firmaradar_get_aml_score (PEP/sanctions on key persons). Requires a one-time pre-screening-disclaimer confirmation. If this returns HTTP 403 with error_code kundebekreftelse_required or disclaimer_required, the agent may call firmaradar_confirm_risk_score_disclaimer to confirm on the user's behalf (per OAuth user, audit-logged). The confirmation is per account, not per call, and is permanent. Alternatively the user can confirm manually at https://firmaradar.no/minbedrift/utvidelser/risikoscoring — both paths write to the same audit table.. It is categorised as a Read tool in the Firmaradar MCP Server, which means it retrieves data without modifying state.
Register the Firmaradar MCP server in PolicyLayer and add a rule for firmaradar_get_risk_score: 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 Firmaradar. Nothing to install.
firmaradar_get_risk_score is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the firmaradar_get_risk_score 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 firmaradar_get_risk_score. 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.
firmaradar_get_risk_score is provided by the Firmaradar MCP server (https://mcp.firmaradar.no/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 31 Firmaradar 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.