Company data for AI agents — an MCP server for six European registries

A language model asked "is this company real, active and sanctioned?" answers from its training data, which is neither current nor citable. Prometiam publishes a Model Context Protocol server, prometiam-risk-mcp, so Claude Desktop, Cursor and any MCP client answer from the official registries of Spain, France, the United Kingdom, Ireland, Poland and Norway — company search and detail, officers where the registry publishes them, corporate events, corporate insolvency notices, VAT and LEI lookup, and sanctions screening (beta) — with the record behind every answer. Agents built on other stacks call the same REST API and can load the OpenAPI specification as their tool schema.

Connect it

One command, npx -y prometiam-risk-mcp, with PROMETIAM_API_KEY set to a key from sign-up. The free tier (1,000 calls a month, no card) is enough to try it. Every tool call is one API request; batch tools count each item.

What an agent can do with it

  • Resolve a name or identifier to the official record (companies_search, company_detail, companies_lookup for up to 100 at once).
  • List officers and follow a director across companies (people_search, person_detail, directors_network) — Spain, France, the UK and Norway; Ireland and Poland are company-level.
  • Read the corporate-event history of a company (events_search, events_timeline) — Spain, France and the UK.
  • Check for corporate insolvency notices in nine markets (insolvency_check, insolvency_notices_search) and Spanish concursal proceedings (insolvency_search).
  • Screen names against sanctions and US export-control lists with a match score (sanctions_screen, sanctions_screen_batch, sanctions_changes) — beta; PEP beta and Spain only.
  • Validate a VAT number (vat_validate), look up an LEI and its parents (lei_lookup, lei_relationships), and subscribe a company to monitoring with signed webhooks (monitor_subscribe; Spain, Ireland and Poland).

Guardrails that matter

Only two tools change anything (monitor_subscribe, monitor_stop); everything else is read-only. The API returns facts and a sanctions match score, never a decision — an agent should present a hit for review, not declare a verdict. The key stays in the client's environment, never in a prompt.

Scope limits

Ireland and Poland are company-level (no officers yet); Norway has no corporate-event stream; insolvency notices are corporate only across FR, DE, GB, AT, CH, NO, FI, US and NL, with Spain on its own endpoint; monitoring is ES, IE and PL; sanctions screening is beta; PEP is beta and Spain only. No credit scores, no financial statements, no beneficial ownership outside the UK PSC register.

Read more · API reference · prometiam-risk-mcp on npm

Frequently asked questions

What is an MCP server for company data?
A Model Context Protocol server is a small program an AI client (Claude Desktop, Cursor, Continue, Cline and others) starts locally; it exposes typed tools the model can call. prometiam-risk-mcp exposes the Prometiam API as tools — company search and detail, officers, corporate events, insolvency checks, sanctions screening, VAT and LEI lookup, monitoring — so the model answers from official registry data instead of its training memory, and can show the record it used.
Which AI clients work with it?
Any client that speaks MCP over stdio: Claude Desktop, Cursor, Continue and Cline are documented in the package README. An agent built on another stack calls the REST API directly and can load the OpenAPI 3.0 specification at /openapi.json as its tool schema.
Can the agent change anything in my account?
Only through two tools, monitor_subscribe and monitor_stop, which are marked as mutating; everything else is read-only. Keep the key in the client configuration, not in a prompt, and use a key with only the scopes the agent needs.
Does a tool call count against my quota?
Yes, one request per tool call, and batch tools (companies_lookup, sanctions_screen_batch, insolvency_check) count every item as one request. The free tier is 1,000 calls a month with no card; Starter is €9.99 a month for 10,000 and Professional €29.99 for 100,000.
Is the answer a decision?
No. The API returns registry facts and, for screening, a match_score against the lists it holds. A sanctions hit is a prompt to review, not a verdict, and the agent should say so. Sanctions screening is beta; PEP screening is beta and Spain only.