MIL — Machine Intelligence Layer MCP Server

Retrieve machine-readable intelligence for a Swedish company by organisation number. Returns current attribute values, resolved knowledge, signals, events, provenance, and data freshness. All values include confidence and source evidence. Unknown or missing data is returned explicitly — never invented.

Retrieve the change history for a Swedish company — attribute_changed events showing when values were first observed and what changed. Optionally filter by attribute key. Returns temporal bounds (effective_from) and evidence for each event.

Search for company attribute change events across companies. Use this to find companies where a specific attribute recently changed, or to monitor for changes in a particular dimension (e.g. employee count drops). Returns events with company identifiers, previous/new values, and temporal bounds.

Resolve up to 50 companies in one call. Every requested identifier appears in the result with an explicit status (resolved, not_found or invalid_organisation_number), so absence is never signalled by omission.

Search and discover Swedish companies without knowing their organisation number. Filter by company name (partial match), industry code, or presence of active distress signals. Returns compact summary cards — each card includes the organisation_number needed to call get_company for full intelligence. All parameters are optional; omit all to browse all companies in the dataset. Discovery flow: (1) call search_companies to find a company, (2) use the returned organisation_number to call get_company for full intelligence.

Find active warning signals for a company. Signals are deterministic rules over register facts and filed annual reports — no AI scores. Examples: vat_registration_lost, f_tax_lost, employee_band_decline, liquidation_in_progress, bankruptcy_proceeding, revenue_decline_yoy, negative_equity. Each signal includes its rule, severity (low, medium, high), supporting facts and detected_at.

Fetch the register identity of one Swedish company by the id that search returned (its organisationsnummer): name, legal form, industry (SNI), registration date, municipality, status, sources and freshness. Free (Basic). Verified and Intelligence (VAT/F-tax, history, annual reports, signals) are paid via get_company.

Find companies related to the given company by evidence MIL holds: industry_cluster (same SNI classification) and address_cluster (same registered postal code). Relation types MIL has no source data for, such as board_member and ownership, are reported as unavailable with a reason rather than as an empty result.

Search Swedish companies by name or organisationsnummer (10 or 12 digits, dashes allowed). Also accepts simple discovery such as 'restaurants in Trelleborg', 'construction companies in Malmö', 'IT companies in Lund', or 'companies in Trelleborg' (also Swedish 'restauranger i Malmö'). Industries resolve through official English/Swedish SNI descriptions and business aliases, e.g. 'computer repair'/'datorreparation' and 'dining'/'restaurangverksamhet'. Known counties such as Skåne and explicit municipality names use registered administrative geography. Unrecognized or ambiguous wording falls back to name search. Locality is the registered locality, not nearby workplaces. Signal-filtered discovery is refused in free search; use paid find_distress_signals for a known company. Returns up to 10 results, each with an id to pass to fetch and a citable URL. Free (Basic identity only).