# Ärikratt (remote · arikratt.ee)

Estonian companies, EMTAK, grants and tenders from public registers.

- Trust score: 40/100 (low)
- Change this week: −48
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- remote · `arikratt.ee`: 40/100 (this document), [markdown](https://verifymcp.io/servers/ee-arikratt-arikratt/arikratt.md), [page](https://verifymcp.io/servers/ee-arikratt-arikratt/arikratt)

## Channel facts

- Endpoint: `https://arikratt.ee/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-24.

- **Endpoint Security**: 100/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 0/100
  - Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
- **Schema Quality & AI Usability**: 0/100
  - Schema blocked by authentication: the endpoint requires auth we don't have to read it.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Tool Safety**: 0/100
  - Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Capabilities**: 0/100
  - Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

**Unverified: 6 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the Ärikratt MCP server?

Ärikratt is a hosted endpoint at https://arikratt.ee/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ee-arikratt-arikratt 'https://arikratt.ee/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ee-arikratt-arikratt": {
      "url": "https://arikratt.ee/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ee-arikratt-arikratt": {
      "type": "http",
      "url": "https://arikratt.ee/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ee-arikratt-arikratt]
url = "https://arikratt.ee/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ee-arikratt-arikratt": {
      "type": "remote",
      "url": "https://arikratt.ee/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ee-arikratt-arikratt --url 'https://arikratt.ee/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ee-arikratt-arikratt:
    url: "https://arikratt.ee/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ee-arikratt-arikratt": {
      "Transport": "http",
      "Url": "https://arikratt.ee/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ee-arikratt-arikratt -t streamable-http -u 'https://arikratt.ee/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ee-arikratt-arikratt": {
      "type": "http",
      "url": "https://arikratt.ee/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-24 (score 40, −51)

- [security regression] Endpoint reachability: reachable → behind authorisation
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → unverified
- [security regression] Stability: 0.90 → unverified
- [security] Authorization: The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-10-23 (score 91, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 90, 0)

- [functional] New tool “browse_catalog”
- [functional] New tool “describe_datasets”

### 2026-10-20 (score 90, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 89, 0)

- [security] Tool “get_company” rewrote its description, which is the text the model reads
- [security] Tool “region_stats” rewrote its description, which is the text the model reads
- [cosmetic] “get_company” reworded the description of “sections”

### 2026-10-18 (score 89, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 88, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (21)

### `describe_datasets` (~111 tokens)

Describe datasets

List dataset IDs, English names, per-surface status and licences within 8000 bytes. Pass dataset_id for full rights, exclusions, attribution, clocks and coverage. Summary reports datasets_total and truncated if the registry outgrows the budget. Free metadata; no data rows. Snapshot readiness is independent of legal eligibility. Use source_metadata for acquisition evidence and get_company for company data. Do not look up natural persons.

Input parameters:

- `dataset_id`: Stable dataset ID for full detail; omit for a bounded summary

Output parameters:

- `datasets` (array)
- `datasets_total` (integer)
- `reviewed_at` (string)
- `schema_version`
- `truncated` (boolean)

### `browse_catalog` (~267 tokens)

Browse catalogs

Free paginated catalogs with attribution, source clocks and partial coverage. Follow next_offset; envelope trimming preserves continuation. legal_search: state statutes/regulations, literal FTS5, exact RT ID or title/ID plus §; title, section path and RT link per passage. Tallinn-date validity is checked; new redactions need a snapshot refresh. No vectors, generation, attachments or municipal/individual acts. Medicines: no documents, company joins or clinical inference. IP: no person names, addresses, designers or representatives; organization codes require a legal-entity match. Courts: 2020+ validated metadata only; no names, prose, charges or company/person links. Property: identifiers, addresses, energy labels, parcel links and public state assets; no private owners or quarantine. Ships: open entries and active non-FIE organization observations, not proven current ownership; no mortgages. Inspect dates/status; EHR freshness and ship currentness may be unknown. Use describe_datasets for exclusions. Do not look up natural persons.

Input parameters:

- `kind` (string, required): Current legal passages, packages, safe IP filings, name-free courts or qualified property
- `limit` (integer)
- `offset` (integer)
- `query` (string): Approved metadata or identifier; empty browses all rows

Output parameters:

- `coverage` (object)
- `kind`
- `next_offset` (integer|null)
- `offset` (integer)
- `rows` (array)
- `snapshot_id` (string)
- `source_clocks` (object)
- `sources` (array)
- `status`
- `total` (integer)
- `truncated` (boolean)

### `source_metadata` (~106 tokens)

Source metadata

Licence, attribution and distribution evidence for one source. Current policy checks differ from acquisition rights: unresolved means no retained grant evidence; retained_copy requires an older licensed copy. Includes exact recorded distribution URLs, acquisition/source clocks and transformation codes. Old snapshots return empty acquisitions. Truncated results include acquisitions_total. Use get_company for legal-entity figures. Do not look up natural persons.

Input parameters:

- `source_key` (string): Source key, e.g. stat, emta or ariregister

Output parameters:

- `acquisitions` (array)
- `acquisitions_total` (integer)
- `as_of` (string|null)
- `disclaimer` (string|null)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `truncated` (boolean|null)

### `search_companies` (~283 tokens)

Search companies

Search active legal entities by current or former name or registry code. Set include_inactive for other statuses. County aliases and cursor pagination are supported; unknown counties error. Use get_company for a full company profile, or find_companies to filter by county, Estonian Classification of Economic Activities (EMTAK), revenue or employees. Do not look up natural persons.

Input parameters:

- `county`: County name or alias (Harju, Harjumaa, Harju maakond). Valid: Ida-Viru maakond, Lääne-Viru maakond, Harju maakond, Hiiu maakond, Jõgeva maakond, Järva maakond, Lääne maakond, Põlva maakond, Pärnu maa…
- `cursor`: Opaque cursor from a previous next_cursor for the next page
- `emtak`: Estonian Classification of Economic Activities (EMTAK) code or prefix
- `include_inactive` (boolean): Include liquidated, bankrupt, and deleted companies. Default false.
- `limit` (integer): At most 25 companies
- `query` (string, required): Company name or 8-digit registry code

Output parameters:

- `as_of` (string|null)
- `companies` (array|null)
- `disclaimer` (string|null)
- `next_cursor` (string|null)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `row_count` (number|null)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `truncated` (boolean|null)

### `get_company` (~526 tokens)

Company profile

Company profile with latest accounts (all years via sections), eight EMTA quarters, tax debt, pledges, aid, licences, notices and legal-entity owners. State taxes are net of refunds; labour taxes are separate, not wages. on_list false means not on the EMTA debt list ≥100 € as of snapshot_date. Unknown applies only when that list was not observed. Optional sections add the extras named on sections. Observed ownership and permits do not prove current ownership or validity. Contracts show at most 25 rows; fees have unverified periods and must not be summed. Shared-board results have at most 20 companies. Procurement ceilings are not spend; buyer seat is not delivery location. Distress is an indicator, not a finding; respect methodology changes. Missing older data may be empty or null. Use company_procurement for award pages, check_counterparty for status/debt/filing checks, search_companies for a name, or watch_companies for changes across codes. board lists current officers of one commercial company (name, role, start date; not indexed). not_published means withheld or unavailable, not an empty board. Do not look up natural persons, personal codes or personal contact details.

Input parameters:

- `registry_code` (string, required): 8-digit commercial register code
- `sections`: Optional extras: ships (open ship register entries, observed/historical owner entry in the register, may not be current owner; CC BY-SA 4.0; old snapshots empty), permits (ET/EN/RU kind/status labels…

Output parameters:

- `activities` (array|null)
- `activities_total` (number|null)
- `announcements` (array|null)
- `as_buyer` (object|null): Public legal-entity buying across all retained history; registered seat, not delivery location. Old snapshots return null.
- `as_of` (string|null)
- `board` (object): Current officers of one company. status published means the company is in scope: members lists current officers and may be empty. status not_published means an excluded legal form, an Article 21 obje…
- `de_minimis` (object|null)
- `de_minimis_total` (number|null)
- `disclaimer` (string|null)
- `distress` (object|null)
- `distress_trend` (object|null)
- `distress_trend_total` (number|null)
- `financials` (object|array|null)
- `financials_total` (number|null)
- `found` (boolean|null)
- `grants` (array|null)
- `grants_total` (number|null)
- `history` (array|null)
- `history_total` (number|null)
- `holdings` (array|null)
- `licences` (array|null)
- `majority_foreign_owned` (boolean|null)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `owners` (array|null)
- `owners_coverage` (string|null): not_in_source_securities_register when an Aktsiaselts or European company (SE) has no owner edges: shareholders are in the Nasdaq CSD securities register, not Business Register open data. Omitted oth…
- `owners_coverage_note` (string|null): Sentence explaining owners_coverage. Omitted when owners_coverage is omitted.
- `peers` (object|null)
- `permits` (array|null)
- `permits_total` (number|null)
- `pledges` (object|null)
- `procurement_wins` (object|null)
- `profile` (object|null)
- `registry_code` (string|null)
- `report_status` (object|null)
- `ships` (array)
- `ships_note` (string)
- `ships_status` (string)
- `ships_total` (integer)
- `similar` (array|null)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `state_aid` (object|null)
- `state_contracts` (object)
- `successions` (array|null)
- `successions_total` (number|null)
- `tax` (array|null)
- `tax_debt` (object|null)
- `tax_debt_history` (object|null)
- `tax_debt_history_total` (number|null)
- `truncated` (boolean|null)
- `unnamed_foreign_owner_count` (integer|null)

### `check_counterparty` (~129 tokens)

Check a counterparty

Check one legal entity: status, tax debt, last filed report, overdue days, dated insolvency and enforcement notices, and distress components with evidence and methodology version. on_list false means not on the EMTA debt list ≥100 € as of snapshot_date. Unknown applies only when that list was not observed and is undated. Distress is an indicator, not a finding or credit decision. Use get_company for the wider financial profile, or risk_signals to scan companies for one signal. Do not look up natural persons.

Input parameters:

- `registry_code` (string, required): 8-digit commercial register code

Output parameters:

- `as_of` (string|null)
- `disclaimer` (string|null)
- `distress` (object|null)
- `flags` (object|null)
- `found` (boolean|null)
- `insolvency_announcements` (array|null)
- `legal_form` (string|null)
- `name` (string|null)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `registry_code` (string|null)
- `report` (object|null)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `status` (string|null)
- `tax_debt` (object|null)
- `truncated` (boolean|null)

### `funding_overview` (~151 tokens)

Funding overview

European Union funding allocations from active source project-key records by period, fund and period, programme, implementing body and project region, plus the top 20 verified legal-entity beneficiaries. Private, redacted and unmatched recipients appear only in aggregates. Missing regions remain null; project geography is not legal seat. Intermediary status is unknown. Awarded support, project budget, co-financing and paid project costs have separate coverage counts; paid cost is not support paid; no absorption ratio is available. State Shared Service Centre (RTK) attribution accompanies results. Truncated lists retain totals; older snapshots return available=false. Use open_calls for opportunities or get_company for company grants. Do not look up natural persons.

Output parameters:

- `absorption` (null)
- `absorption_reason` (string)
- `as_of` (string|null)
- `available` (boolean)
- `beneficiaries` (array)
- `beneficiaries_total` (integer)
- `coverage` (object)
- `disclaimer` (string|null)
- `funds` (array)
- `funds_total` (integer)
- `implementing_bodies` (array)
- `implementing_bodies_total` (integer)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `periods` (array)
- `periods_total` (integer)
- `programmes` (array)
- `programmes_total` (integer)
- `regions` (array)
- `regions_total` (integer)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `totals` (object|null)
- `truncated` (boolean|null)
- `universe` (string)

### `compare_companies` (~127 tokens)

Compare companies

Compare up to four legal entities for one year: accounts, tax debt, distress and revenue percentile. on_list false with snapshot_date means not on the EMTA debt list ≥100 € as of that date. Unknown applies only when the list was not observed; a missing tax_debt object is undated and is not absence. Use find_companies to discover codes, or sector_stats for industry medians. Do not look up natural persons.

Input parameters:

- `registry_codes` (array, required): One to four 8-digit registry codes
- `year`: Financial year. Defaults to the snapshot year.

Output parameters:

- `as_of` (string|null)
- `companies` (array|null)
- `disclaimer` (string|null)
- `missing` (array|null)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `partial` (boolean|null)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `truncated` (boolean|null)
- `year` (number|null)

### `find_companies` (~427 tokens)

Find companies

Find up to 50 legal entities by county, Estonian Classification of Economic Activities (EMTAK), revenue, employees or observed Register of Economic Activities (MTR) activity. Can exclude companies with current tax debt (`no_tax_debt`). Licence presence is not proof of compliance. Sort by metric and direction; default revenue descending, missing values last. At most 40 candidate pages or 80 tax-debt checks, subject to distinct-code allowance; no continuation cursor. Check result completeness. Missing source data can yield an empty list. English activity labels include attribution and disclose broader-label fallbacks. Use search_companies for a name, or get_company for a listed code. Do not look up natural persons or personal contact details.

Input parameters:

- `county`: County name or alias. Valid: Ida-Viru maakond, Lääne-Viru maakond, Harju maakond, Hiiu maakond, Jõgeva maakond, Järva maakond, Lääne maakond, Põlva maakond, Pärnu maakond, Rapla maakond, Saare maakon…
- `dir` (string)
- `emtak`: Estonian Classification of Economic Activities (EMTAK) code or prefix
- `licence_activity`: Exact Register of Economic Activities (MTR) activity string from sector_stats. Observed source presence, not verified licence validity; submitted and suspended records included.
- `limit` (integer): At most 50 companies
- `max_employees`: Maximum average employees
- `max_revenue`: Maximum annual revenue, EUR
- `min_employees`: Minimum average employees
- `min_revenue`: Minimum annual revenue, EUR
- `no_tax_debt`: Keep only companies with no current tax debt
- `sort` (string)
- `year`: Financial year, or latest: each active company’s latest non-null revenue filing since the latest complete year

Output parameters:

- `as_of` (string|null)
- `companies` (array|null)
- `disclaimer` (string|null)
- `excluded_unit_uncertain` (object|null): Companies left out of this revenue ranking because revenue is null and monetary_null_reason is unit_uncertain. count is the filtered total; companies lists at most 20 with registry_code and name, and…
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `row_count` (number|null)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `truncated` (boolean|null)
- `year`

### `sector_stats` (~459 tokens)

Sector statistics

Medians, percentiles and company counts for a sector under the Estonian Classification of Economic Activities (EMTAK 2025), optionally by county and year. Older codes use the snapshot crosswalk. Licence counts suppress n < 5 and use current sector/county denominators, independent of year. Presence is not compliance. Legal acts are incomplete, capped at 10 per group. Optional sections add quarterly figures, national gross wages, filing coverage, benchmarks, vacancies, technology adoption, insolvency, tourism, macro context and upcoming laws. Labour taxes are not wages. Filing absence means not in the dated data, not proven non-filing. Official benchmarks describe broader national populations, not company percentiles. Preserve source periods, units, coverage and classification caveats; missing data stays null or empty. Bills are not law and detected deadlines are not compliance verdicts. Truncated lists retain totals and sources. Use legal_calendar for upcoming changes, region_stats for a place, or compare_companies for named firms. Do not look up natural persons.

Input parameters:

- `county`: County name or alias, optional. Valid: Ida-Viru maakond, Lääne-Viru maakond, Harju maakond, Hiiu maakond, Jõgeva maakond, Järva maakond, Lääne maakond, Põlva maakond, Pärnu maakond, Rapla maakond, Sa…
- `emtak` (string, required): Estonian Classification of Economic Activities (EMTAK) 2025 code or division. Estonian Classification of Economic Activities (EMTAK) 2008 codes are resolved via the snapshot crosswalk.
- `quarterly_form` (string): Quarterly legal-form group: OÜ, AS, other retained legal forms. Independent of annual-account year.
- `sections`: Opt-in context sections; omitted or [] returns pre-integration core only. Available: ai_adoption, bankruptcies, economy, job_vacancies, official_benchmarks, quarterly, report_coverage, tourism, upcom…
- `year`: Year

Output parameters:

- `acts` (array|null)
- `acts_universal` (array|null)
- `ai_adoption` (object|null): Opt-in: returned only when sections includes ai_adoption.
- `as_of` (string|null)
- `bankruptcies` (object|null): Opt-in: returned only when sections includes bankruptcies.
- `company_count` (number|null)
- `company_count_national` (number|null)
- `disclaimer` (string|null)
- `economy` (array): Opt-in: returned only when sections includes economy.
- `employees_total` (number|null)
- `emtak` (string|null)
- `emtak_note` (object|null)
- `emtak_requested` (string|null)
- `found` (boolean|null)
- `histogram` (array|null)
- `job_vacancies` (object|null): Opt-in: returned only when sections includes job_vacancies.
- `label` (string|null)
- `level` (string|null)
- `licence_count` (number|null)
- `licence_prevalence` (array)
- `licence_prevalence_note` (string|null)
- `licence_prevalence_total` (integer)
- `median_revenue` (number|null)
- `median_revenue_reason` (string|null)
- `official_benchmarks` (object): Opt-in: returned only when sections includes official_benchmarks. EM001 enterprise statistics by persons-employed size class, not company percentiles; empty rows on old snapshots.
- `official_benchmarks_url` (string): Full-data URL; returned only when sections includes official_benchmarks.
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `partial` (boolean|null)
- `percentiles` (object|null)
- `quarterly` (object): Opt-in: returned only when sections includes quarterly. Eight latest quarters from a fixed 12-quarter complete-reporting legal-entity cohort. Current geography/classifier. Small cells excluded before…
- `report_coverage`: Opt-in: returned only when sections includes report_coverage.
- `revenue_sum` (number|null)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `tourism` (object|null): Opt-in: returned only when sections includes tourism. TU110 annual county totals and normalized TU121 national monthly arrivals; independent periods, null means not reported. Cost is not revenue/prof…
- `trend` (array|null)
- `truncated` (boolean|null)
- `upcoming_changes` (object): Opt-in: returned only when sections includes upcoming_changes.
- `wages` (object|null): Opt-in: returned only when sections includes wages. Official aggregate context; source gaps remain null, periods and classification are independent of company report year. Lists may be truncated.
- `year` (number|null)

### `event_series` (~244 tokens)

Observed corporate events

Monthly observed legal-entity notice publications and registry relationships, separately. Notice counts are not unique insolvencies: notices are deduplicated across entities, but proceeding stages remain separate. Relationships count unordered company pairs by kind. Coverage and unmatched counts are national; older coverage is incomplete. County and sector filters use current classifications and overlap. Official Announcements attribution accompanies results. Old snapshots return empty rows; truncated results retain rows_total. Do not look up natural persons.

Input parameters:

- `county`: Current snapshot county. Valid: Ida-Viru maakond, Lääne-Viru maakond, Harju maakond, Hiiu maakond, Jõgeva maakond, Järva maakond, Lääne maakond, Põlva maakond, Pärnu maakond, Rapla maakond, Saare maa…
- `emtak`: Current snapshot Estonian Classification of Economic Activities (EMTAK) prefix, 1–5 digits.
- `year`: Calendar year; defaults to snapshot year, which is partial.

Output parameters:

- `as_of` (string|null)
- `disclaimer` (string|null)
- `kind_first_month` (object|null)
- `note` (string)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `partial_year` (boolean)
- `reason` (string)
- `rows` (array)
- `rows_total` (integer)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `truncated` (boolean|null)
- `year` (integer)

### `legal_calendar` (~150 tokens)

Legal calendar

Upcoming laws, legislative bills and European Union deadlines in separate dated layers. Bills are not law. Universal changes are separate from title-derived sector matches. Bill stages and committees are included; direct law links and measure lifecycle remain unverified. Deadline detections are not compliance or transposition verdicts. Sources, licences, totals and truncation are reported; older snapshots return empty layers. Use sector_stats for sector benchmarks and a calendar preview. Do not look up natural persons.

Input parameters:

- `emtak`: Optional Estonian Classification of Economic Activities (EMTAK) code/division, 2–5 digits; title-derived matches only.
- `limit` (integer): Rows per layer and scope; envelope may trim further.

Output parameters:

- `as_of` (string|null)
- `available` (boolean)
- `bills` (object)
- `disclaimer` (string|null)
- `emtak` (string|null)
- `eu_deadlines` (object)
- `future_laws` (object)
- `notice` (string)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `truncated` (boolean)

### `economy_context` (~154 tokens)

Economic context

National context: real gross domestic product (GDP) annual growth, month-end registered unemployed counts and annualised volume-weighted contractual interest rates on new and amended euro loans to Estonian resident non-financial corporations. Growth uses chain-linked, unadjusted, revisable volume accounts, not flash estimates; unemployment is a count, not a rate; interest is not outstanding-loan interest. The official corporate aggregate includes sole proprietors with 10+ employees. Each series includes observation periods, units, basis, cadence and source licences, with up to eight observations. Old snapshots return empty rows; truncated results retain totals. Use region_stats for counties or sector_stats for company benchmarks. Do not look up natural persons or household credit data.

Output parameters:

- `as_of` (string|null)
- `disclaimer` (string|null)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `rows` (array)
- `rows_total` (integer)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `truncated` (boolean|null)

### `region_stats` (~431 tokens)

Regional statistics

County medians, employment and aid; omit county for all counties: report_coverage counts are per-county, land is national. Optional sections add quarterly figures, filing coverage, labour market, public buying, energy labels, land, property, construction, municipal acts, municipality rankings and tourism. Small cells are suppressed. Labour taxes are not wages; registered unemployment is a count, not a rate. Filing absence is not proven non-filing. Buying uses registered seat and all retained history, independent of year; ceilings are not spend. Energy labels cover certified buildings, not all buildings or verified current validity. Property stock counts registered apartment-property units, not dwellings. Transactions are dated aggregates: respect frozen periods and never pool medians. Construction is separate national context. Municipal topics are incomplete relevance indicators. Guest-night cost is not revenue; national tourism does not establish county seasonality. Preserve dates, units and nulls. county_brief keeps those figures; code region_report. Truncated lists keep totals. Use sector_stats for an industry. Do not look up natural persons, owners or parcel records.

Input parameters:

- `county`: County name or alias. Omit for every county. Valid: Ida-Viru maakond, Lääne-Viru maakond, Harju maakond, Hiiu maakond, Jõgeva maakond, Järva maakond, Lääne maakond, Põlva maakond, Pärnu maakond, Rapl…
- `quarterly_form` (string): Quarterly legal-form group: OÜ, AS, other retained legal forms. Independent of annual-account year.
- `sections`: Opt-in context sections; omitted or [] returns pre-integration core only. Available: energy_labels, labour_market, land, municipal_acts, municipalities_ranked, national_construction, property_market,…
- `year`: Year

Output parameters:

- `aid` (object|null)
- `as_of` (string|null)
- `bankruptcies` (object|null)
- `company_count` (number|null)
- `company_count_reason` (string|null)
- `counties` (array|null)
- `counties_compare` (array|null)
- `county` (string|null)
- `county_brief` (object|null): Compact county figures from the report note: tax-debt company count and share, bounded aid sum and decision count, procurement win count and value, 30-day bankruptcy notice count, and median wage ver…
- `delta_pct` (number|null)
- `delta_pct_reason` (string|null)
- `demography` (array|null)
- `disclaimer` (string|null)
- `employees_total` (number|null)
- `employees_total_reason` (string|null)
- `employees_unit` (string|null)
- `energy_labels` (object|null): Opt-in: returned only when sections includes energy_labels.
- `excluded_unit_uncertain` (object|null): Companies left out of this revenue ranking because revenue is null and monetary_null_reason is unit_uncertain. count is the filtered total; companies lists at most 20 with registry_code and name, and…
- `found` (boolean|null)
- `gross_wage` (object|null)
- `labour_market` (object|null): Opt-in: returned only when sections includes labour_market. Official aggregate context; source gaps remain null, periods and classification are independent of company report year. Lists may be trunca…
- `land` (object|null): Opt-in: returned only when sections includes land. Aggregate cadastral context, independently dated. National scope when county is omitted.
- `largest` (array|null)
- `median_revenue` (number|null)
- `median_revenue_reason` (string|null)
- `median_revenue_unit` (string|null)
- `median_series` (array|null)
- `municipal_acts` (object|null): Opt-in: returned only when sections includes municipal_acts. Current municipal regulations: derived title-keyword relevance, not a complete compliance checklist. Null for older snapshots.
- `municipalities` (array|null)
- `municipalities_ranked` (array|null): Opt-in. Same active-company municipality rows as municipalities, ordered by company_count descending then name. median_revenue is null when median_revenue_n < 5.
- `national_construction` (array|null): Opt-in: returned only when sections includes national_construction.
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `open_call_count` (number|null)
- `partial` (boolean|null)
- `property_market` (object|null): Opt-in: returned only when sections includes property_market.
- `property_stock` (object|null): Opt-in: returned only when sections includes property_stock. Registered apartment-property units (korteriomand), not physical dwellings. Source Last-Modified date; RIK kinnistusraamat (Kris.xml), CC…
- `public_buying` (object|null): Opt-in: returned only when sections includes public_buying.
- `quarterly` (object|null): Opt-in: returned only when sections includes quarterly. Eight latest quarters from a fixed 12-quarter complete-reporting legal-entity cohort. Current geography/classifier. Small cells excluded before…
- `report_coverage`: Opt-in: returned only when sections includes report_coverage.
- `report_note_code` (string|null): County report code. region_report marks a county response; the figures are in county_brief.
- `sectors` (array|null)
- `share_pct` (number|null)
- `share_pct_reason` (string|null)
- `slug` (string|null)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `tourism` (object): Opt-in: returned only when sections includes tourism. TU110 annual county totals and normalized TU121 national monthly arrivals; independent periods, null means not reported. Cost is not revenue/prof…
- `transactions` (object|null)
- `truncated` (boolean|null)
- `unemployment` (object|null)
- `wage_municipalities` (array|null)
- `year` (number|null)
- `year_label` (string|null)

### `open_calls` (~348 tokens)

Open funding calls

Open funding calls from the Estonian Business and Innovation Agency (EIS), Agricultural Registers and Information Board (PRIA), and Environmental Investment Centre (KIK). Pass a company profile or registry_code for matching calls, with reasons, rules, co-financing share, budget and size bands. Explicit profile fields override the company profile. This tool does not draft or submit applications. Use procurement_notices for public tenders. Do not look up natural persons.

Input parameters:

- `county`: County name or alias. Valid: Ida-Viru maakond, Lääne-Viru maakond, Harju maakond, Hiiu maakond, Jõgeva maakond, Järva maakond, Lääne maakond, Põlva maakond, Pärnu maakond, Rapla maakond, Saare maakon…
- `deadline_within_days`: Keep calls whose deadline is within this many days
- `emtak`: Estonian Classification of Economic Activities (EMTAK) code. Matched on the division when the call has rules.
- `provider`: Funder, for example the Estonian Business and Innovation Agency (EIS)
- `registry_code`: 8-digit registry code; resolves Estonian Classification of Economic Activities (EMTAK), county and size band from the snapshot. Explicit emtak/county/size_band override it per dimension.
- `size_band`: Company size band: e:0-9, e:10-49, e:50-249, e:250+, e:unknown.

Output parameters:

- `as_of` (string|null)
- `calls` (array|null)
- `calls_total` (number|null)
- `disclaimer` (string|null)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `profile` (object|null)
- `row_count` (number|null)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `truncated` (boolean|null)
- `unknown_scope_count` (number|null): Calls dropped by an EMTAK filter because the source named no sector. Zero when the caller did not filter by EMTAK.

### `procurement_notices` (~351 tokens)

Procurement notices

Public procurement notices filtered by buyer, Common Procurement Vocabulary (CPV), value, deadline or open status. Notice types distinguish calls for tender from awards. Estimates may be incomplete or repeated; estimates and award ceilings are not spend or payments. Text uses contains matching. Global sorting supports issued date, deadline or value, with missing values last. Keep sort and direction unchanged across cursor pages. Total counts all matches; row_count counts the returned page. Legal entities and authorities only. Use company_procurement for a company's awards, or open_calls for grants. Do not look up natural persons.

Input parameters:

- `buyer`: Buyer name or registry code
- `cpv`: Common Procurement Vocabulary (CPV) code prefix
- `cursor`: Opaque cursor from a previous next_cursor for the next page
- `days`: Published within this many days
- `deadline_within_days`: Keep notices whose submission deadline is within this many days (0..3650)
- `dir` (string): Sort direction; reuse with the cursor
- `include_null_value` (boolean): When min/max value filters are set, also keep notices with no estimated value
- `limit` (integer): At most 25 notices
- `max_value_eur`: Maximum estimated value in EUR (finite, 0..1e15)
- `min_value_eur`: Minimum estimated value in EUR (finite, 0..1e15)
- `open_only` (boolean): Keep open contract notices (cn-*) with deadline on/after today; exclude award notices
- `query`: Title or buyer text (contains match on folded title/authority)
- `sort` (string): Global sort key; missing values last

Output parameters:

- `as_of` (string|null)
- `disclaimer` (string|null)
- `next_cursor` (string|null)
- `notices` (array|null)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `row_count` (number|null)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `truncated` (boolean|null)

### `procurement_stats` (~159 tokens)

Procurement market statistics

Compare legal-entity buyer and Common Procurement Vocabulary (CPV) markets across retained history. Notices, procedure folders and observed notice-lots are separate; revisions remain separate lots. Includes tender-count coverage, single-tender share with known denominator, observed winner coverage and year/buyer/category tables. Rates below five observations are withheld. Indicators are not findings, corruption scores or expenditure. Estonian Public Procurement Register attribution accompanies results. Tables have up to 50 rows; truncated results retain totals. Old snapshots return available=false and empty tables. Use procurement_notices for individual notices and open tenders. Do not look up natural persons.

Input parameters:

- `buyer`: Buyer name or registry-code contains match
- `cpv`: Common Procurement Vocabulary (CPV) prefix

Output parameters:

- `as_of` (string|null)
- `available` (boolean)
- `buyers` (array)
- `buyers_total` (integer)
- `by_year` (array)
- `by_year_total` (integer)
- `cpv` (array)
- `cpv_total` (integer)
- `disclaimer` (string|null)
- `note` (string)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `summary` (object|null)
- `truncated` (boolean|null)

### `company_procurement` (~142 tokens)

Company procurement awards

Paginated public-procurement awards for one legal-entity winner. Includes single-winner and shared lots; attributable totals are in get_company sections procurement_wins. Dated context includes repeat-pair procedure counts and exact-date tax-debt evidence: observations, not findings. Cursor pagination supports truncated pages. Sole proprietors are withheld. Use procurement_notices for open notices, or get_company for a win summary. Do not look up natural persons.

Input parameters:

- `cursor`: Opaque cursor from a previous next_cursor for the next page
- `limit` (integer): At most 25 awards
- `registry_code` (string, required): 8-digit commercial register code

Output parameters:

- `as_of` (string|null)
- `available` (boolean|null)
- `dedupe_key`
- `disclaimer` (string|null)
- `found` (boolean|null)
- `framework_flag_note` (string|null)
- `next_cursor` (string|null)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `registry_code` (string|null)
- `row_count` (number|null)
- `rows` (array|null)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `truncated` (boolean|null)
- `value_note` (string|null)

### `risk_signals` (~390 tokens)

Risk signals

Legal entities matching tax debt, bankruptcy, liquidation, enforcement, restructuring or distress signals. Use cursor pagination for company lists. kind=tax_debt_trend returns observed monthly debt stock, joined/left observations and latest active-cohort sector/county incidence: top 10 by incidence rate. Estonian Classification of Economic Activities (EMTAK) and county filters affect incidence rows only; both return separate aggregates. Sector codes map to two-digit divisions; shorter prefixes match divisions. Trends have no cursor; newest months are retained with totals and truncation flags. Baselines and gaps are excluded. Absence is not debt-free; scheduled and disputed amounts remain separate. Amounts withheld below 100 EUR or source-suppressed differ from zero or no published list. Estonian Tax and Customs Board (EMTA) attribution accompanies results; old snapshots return empty lists. Use check_counterparty for one code. Do not look up natural persons.

Input parameters:

- `county`: County name or alias. Valid: Ida-Viru maakond, Lääne-Viru maakond, Harju maakond, Hiiu maakond, Jõgeva maakond, Järva maakond, Lääne maakond, Põlva maakond, Pärnu maakond, Rapla maakond, Saare maakon…
- `cursor`: Opaque cursor from a previous next_cursor for the next page
- `emtak`: Estonian Classification of Economic Activities (EMTAK) code or prefix
- `kind`: tax_debt_trend (national months; county/emtak filter incidence), tax_debt, bankruptcy, liquidation, enforcement, restructuring, distress_high, or distress_moderate
- `limit` (integer): At most 25 signals

Output parameters:

- `as_of` (string|null)
- `cohort` (string|null)
- `cohort_as_of` (string|null)
- `disclaimer` (string|null)
- `end` (string|null)
- `hint` (string): Trend incidence ranking and county/emtak filter guidance for fetching omitted rows.
- `incidence` (array): Top incidence rates across counties and sectors, or rows selected by county/emtak. Both filters select separate aggregate rows, not a county-sector intersection. Months remain national.
- `incidence_cohort` (string|null)
- `incidence_top_n` (integer): Actual number of incidence rows returned, ranked by share_pct descending, unknown rates last; at most 10 and possibly fewer under the 8,000-byte envelope.
- `incidence_total` (integer): Number of incidence rows matching county/emtak filters, or all rows when unfiltered, before top-N selection.
- `missing_days` (integer)
- `months` (array)
- `months_returned` (integer): Number of returned months; newest months are retained in chronological order.
- `months_total` (integer): Number of months in the full national history before size budgeting.
- `months_truncated` (boolean): True when oldest months were omitted to fit the 8,000-byte envelope.
- `next_cursor` (string|null)
- `note` (string|null)
- `observed_days` (integer)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `row_count` (number|null)
- `scope` (string|null)
- `signals` (array|null)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `start` (string|null)
- `threshold_eur` (integer)
- `truncated` (boolean|null)

### `watch_companies` (~182 tokens)

Watch companies

Typed changes for a bounded list of legal-entity registry codes: name, status, capital, succession, tax debt and distress. Returns companies needing attention, with filing status and current tax debt. on_list false with snapshot_date means not on the EMTA debt list ≥100 € as of that date. Unknown applies only when the list was not observed and is not assurance of absence. Use check_counterparty for one code, or get_company sections tax_debt_history or distress_trend for deeper history. Do not look up natural persons.

Input parameters:

- `cursor`: Opaque cursor from a previous next_cursor for the next page
- `registry_codes` (array, required): One to fifty 8-digit legal-entity registry codes
- `since`: Opaque change cursor (event id) or previous snapshot_id. Omit for the full typed change list in this snapshot.

Output parameters:

- `as_of` (string|null)
- `disclaimer` (string|null)
- `next_cursor` (string|null)
- `omitted_sections` (array): Sections removed to fit the response budget, including default sections. Request one named section to retrieve it. Present only when truncated.
- `requested` (number|null)
- `row_count` (number|null)
- `rows` (array|null)
- `since` (string|null)
- `snapshot_id` (string|null)
- `source_details` (string|null): Full attribution and acquisition evidence: source_metadata(key).
- `sources` (array|null)
- `truncated` (boolean|null)

### `submit_feedback` (~271 tokens)

Submit data feedback

Use only when the user explicitly asks to report missing or wrong data. Stores one masked feedback record for human review; sends nothing externally. Include only the reported data problem, never conversation history, personal data or credentials. Omit request_context and agent unless essential to reproduce that problem; their documented size limits and masking apply. At most 20 reports per credential per Tallinn calendar day and five per rolling minute. Returns feedback_id and status=received. Use get_company to retrieve company data. Do not look up natural persons.

Input parameters:

- `agent` (string): Optional client identifier needed to reproduce the reported problem; omit by default. At most 100 characters, masked; no personal data or credentials.
- `kind` (string, required)
- `message` (string, required): Feedback text; no personal data
- `registry_codes`: Up to 10 known legal-entity registry codes; omit codes absent from the snapshot
- `request_context`: Optional minimal reproduction details only; omit by default. No conversation history, personal data or credentials. Text: at most 2000 characters. JSON: at most 50 nodes, depth 4, 49 keys per object,…
- `tool` (string): Tool this feedback refers to

Output parameters:

- `feedback_id` (string)
- `status` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ee-arikratt-arikratt/arikratt#diagnostics

## Score history

- 2026-10-24: 40
- 2026-10-23: 91
- 2026-10-22: 90
- 2026-10-21: 90
- 2026-10-20: 90
- 2026-10-19: 89
- 2026-10-18: 89
- 2026-10-17: 88
- 2026-10-16: 88
- 2026-10-15: 87
- 2026-10-14: 87
- 2026-10-13: 86
- 2026-10-12: 86
- 2026-10-11: 85
- 2026-10-10: 85
- 2026-10-07: 84
- 2026-10-05: 84
- 2026-10-04: 83
- 2026-10-03: 83
- 2026-10-02: 79
- 2026-10-01: 79
- 2026-09-30: 78
- 2026-09-29: 78
- 2026-09-28: 77
- 2026-09-27: 77
- 2026-09-26: 77

## Common questions

### What is the Ärikratt MCP server?

Ärikratt is an MCP server listed in the public MCP registry as ee.arikratt/arikratt. Estonian companies, EMTAK, grants and tenders from public registers. This page covers its hosted endpoint (https://arikratt.ee/mcp).

### Is the Ärikratt MCP server safe to use?

Ärikratt scores 40 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Ärikratt MCP server expose?

Ärikratt exposes 21 tools: describe_datasets, browse_catalog, source_metadata, search_companies, get_company, and 16 more. Their descriptions and schemas cost roughly 5,408 tokens of context every time the server is loaded.

### Does the Ärikratt MCP server require authentication?

Yes. Ärikratt asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Ärikratt MCP server still maintained?

Ärikratt is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://arikratt.ee/mcp
- Authorisation metadata: https://arikratt.ee/.well-known/oauth-protected-resource/mcp
- Website: https://arikratt.ee/en/mcp
- Changelog RSS feed: https://verifymcp.io/servers/ee-arikratt-arikratt/arikratt.xml
- Changelog JSON feed: https://verifymcp.io/servers/ee-arikratt-arikratt/arikratt.json
- HTML version of this page: https://verifymcp.io/servers/ee-arikratt-arikratt/arikratt