MCP App Store
by KeenEthics
Datapublica icon

Datapublica MCP Server for Claude and ChatGPT

By Datapublica

Overview

Datapublica connects Claude to structured Danish business data. Search companies and people, inspect company profiles, financials, filings, ownership and relationships, and explore company history, capital events, and investments. For broader research, screen, rank and compare companies or analyze trends across the available dataset with validated, read-only SQL. Combine financial performance, industries, geography, ownership and other supported data while preserving reporting periods, currencies and financial scope. A Datapublica account is required. Your plan and usage limits apply. The connector reads data and does not modify company records. Coverage is limited to supported Danish business data.

How to connect

  1. Claude: Open the Datapublica listing in the Claude connectors directory and choose Connect. Claude listing Datapublica exposes 24 tools here.
  2. ChatGPT: Open the Datapublica listing in the ChatGPT app directory and choose Connect. ChatGPT listing Datapublica exposes 39 tools here.

Tools

delete_alert

ChatGPT
Use this only when the user asks to delete an alert. It stops the daily checks and removes the alert and its results. A page alert's saved search stays on its page; a SQL alert's query is removed with it.

execute_sql

ChatGPT
Use this to run validated custom, read-only DuckDB SQL that may scan the full active Datapublica dataset and return bounded results. Appropriate for company screening, rankings, comparisons, aggregations, trends, and analyses combining registry, financial, ownership, people, industry, geography, risk, Gazelle, capital, and investment data. Do not use unvalidated SQL, write statements, or repeated entity lookups when one analytical query is more appropriate. Select cvr_number when presenting individual companies and construct links from the contract templates without extra entity lookups; never invent links for aggregate-only results.

expand_portfolio_relations

ChatGPT
Use this after loading a company, person, or participant portfolio when the user wants additional relationships around a visible graph node. Supply the visible node identifiers so the result can extend the existing graph. Do not use for the initial graph, entity search, or ordinary profile lookup.

find_similar_companies

ChatGPT
Use this when the user wants companies similar to one to five known Danish companies and you have their CVR numbers. Rank by business activity, products and services, and customer types, with optional deterministic filters. Results contain rank but no similarity score and are a candidate pool rather than an exhaustive market list.

get_company

ChatGPT
Use this when you already have a stable identifier for one Danish company and need its complete company profile, including registry details, status, addresses, industries, roles, ownership, filings, financials, and available risk fields. employment exposes legal-entity CVR headcount and full-time equivalents (FTE/årsværk) with latestHeadcount, latestFte and observations, each carrying exact values or intervals, period, frequency and source. These are separate from annual-report average_employees and group figures. Latest metric periods can differ; compare matched periods and preserve missing values. Do not use to find an unknown company or compare multiple companies; use search_companies or SQL instead. The result includes Datapublica navigation links; destinations do not imply records or paid access in every section.

get_company_annual_report_sections

ChatGPT
Use this when the user asks for curated narrative sections from one identified company’s XBRL annual report, covering business and development, risks and material matters, or commitments and security. This is not the complete annual report: boilerplate and cross-scope duplicates are suppressed, contentPlain is capped at 20,000 characters, isTruncated marks excerpts, and there is no pagination. A section’s financialScope can be report_wide; sourceReportUrl can be null; PDF-only filings return no sections; and availableReports[].locked is always false for token-authenticated calls. Supply financialScope when no scoped numeric annual filing can provide a default. Do not use it for numeric financial comparisons or full-report retrieval. A resolved CVR adds Datapublica overview and financials links; preserve sourceReportUrl as claim evidence.

get_company_capital_events

ChatGPT
Use this when the user asks about capital increases, reductions, funding events, subscription prices, implied valuations, provenance, or attributed investors for one identified company. Do not use for recent investment activity across many companies; use get_investment_feed instead. A resolved CVR adds Datapublica overview and investments links; preserve event source URLs as evidence.

get_company_gazelle

ChatGPT
Use this when the user asks whether one identified company is or was a Børsen Gazelle, or whether it meets Datapublica’s computed Gazelle screening criteria. Keep official awards separate from computed estimates. Do not describe a computed result as an official award. A resolved CVR adds Datapublica overview and Gazelle links.

get_company_portfolio

ChatGPT
Use this when the user wants an ownership or relationship graph around one identified company, including connected companies, people, and registry participants. Do not use when ordinary company-profile fields are sufficient. Use expand_portfolio_relations only to extend an already loaded graph. The resolved company root adds Datapublica overview and ownership links; construct links for other companies only from explicit company CVRs, never person, participant, or node IDs.

get_company_properties

ChatGPT
Use this when the user asks which Danish properties one company owns. Includes properties held directly and through subsidiaries, with the ownership chain, effective share, address, use, areas, latest valuation and latest sale for each, portfolio totals, and former holdings with their disposal sale and buyers. Lists are capped by limit while totals and formerPropertyCount cover every holding; listsTruncated marks a capped list, and SQL gives complete lists. Effective shares can be ranges because CVR reports ownership in bands. Do not use for a company's ownership graph; use get_company_portfolio instead. The result adds Datapublica overview and properties links for the company; link individual properties as https://datapublica.dk/properties/{bfe}.

get_company_property_trades

ChatGPT
Use this when the user asks which properties one company bought or sold. Returns each registered trade the company took part in directly, with its side (buyer or seller), share, the property, price, dates, method, and counterparties. Prices cover the whole sale; propertyCount above 1 means several properties.

get_company_timeline

ChatGPT
Use this when the user asks how one identified company changed over time, including registry, role, ownership, auditor, and filing events. Do not use for the company’s current profile or cross-company event analysis. Events with a resolved CVR add Datapublica overview and timeline links; preserve filing/report URLs as event evidence.

get_investment_feed

ChatGPT
Use this when the user asks for recent published capital or investment events across Danish companies. It returns complete publication days and can optionally include unpriced capital changes. Do not use for the full capital history of one company; use get_company_capital_events instead.

get_participant

ChatGPT
Use this when you have a stable participant identifier and need the registry bundle for an unresolved participant identity. Do not use for resolved companies or people.

get_participant_portfolio

ChatGPT
Use this when the user wants the ownership and relationship graph for one unresolved registry participant. Do not use for resolved companies or people.

get_participant_timeline

ChatGPT
Use this when the user asks for chronological registry activity involving one unresolved participant identity. Do not use for the participant’s relationship graph.

get_person

ChatGPT
Use this when you have a stable resolved-person identifier and need that person’s roles, ownership, auditor relationships, or related companies. Person profiles do not contain contact details. Do not use a display name as the identifier; call search_people first when necessary.

get_person_portfolio

ChatGPT
Use this when the user wants the ownership and company-relationship graph for one resolved person. Do not use for a chronological history or an unresolved registry name.

get_person_properties

ChatGPT
Use this when the user asks which Danish properties one person owns. Accepts a resolved person identifier from search_people or a property owner's personId (ejf_ identifiers are owners known only from the property register). Includes properties held directly and through companies, with effective share, address, use, areas, latest valuation and latest sale, totals, and former holdings, with lists capped like get_company_properties. Owners with name and address protection cannot be looked up.

get_person_property_trades

ChatGPT
Use this when the user asks which properties one person bought or sold. Accepts the same identifiers as get_person_properties and returns each direct trade with side, share, the property, price, dates, method, and counterparties. Prices cover the whole sale; propertyCount above 1 means several properties.

get_person_timeline

ChatGPT
Use this when the user asks how a resolved person’s company roles, ownership, or other registry activity changed over time. Do not use for the current relationship graph; use get_person_portfolio instead.

get_property

ChatGPT
Use this when you have one property's BFE number and need its full record: address, municipality, main use, land and floor areas, plot ratio, BBR buildings, units and technical installations, cadastral parcels, condominiums of a divided main property, current and previous owners with shares, public valuations by year, sales with prices, buyers and sellers, and a combined history. Sale prices cover the whole sale; propertyCount above 1 means the price covers several properties. Owners with name and address protection appear as type protected without identity. Geometry is omitted unless includeGeometry is true.

get_property_at_address

ChatGPT
Use this when you have a DAR address identity, such as a company's registered_address_identity from search_companies, and need the property that holds that address. A floor and door resolve to the condominium or building on leased land holding them, otherwise the main property. Returns the property's BFE number, kind, and address; follow with get_property for details.

get_property_companies

ChatGPT
Use this when the user asks which companies are or were registered at one property's addresses (CVR beliggenhedsadresse), including condominiums inside it. Pages of rows with a next cursor; tab current lists open registrations and previous lists ended ones. Registration at an address does not imply ownership.

get_property_ownership

ChatGPT
Use this when the user asks who ultimately owns or controls one property. Returns an ownership graph from the property's registered owners up through owning companies, people, and registry participants. Do not use for the property's own facts; use get_property instead.

get_sql_contract

ChatGPT
Use this before advanced analysis across the full active Datapublica dataset. It provides the tables, fields, relationships, semantic rules, domains, examples, and schemaVersion required to author custom read-only SQL for screening, rankings, comparisons, aggregations, trends, and multi-domain analysis. Do not use it to retrieve company records or execute SQL. The root contract also provides machine-readable company-link templates.

get_sql_contract_module

ChatGPT
Use this when the root SQL contract uses modular delivery and an analysis requires this declared data domain or one of its dependencies. Modules cover company registry data, people and ownership, financials and filings, risk and signals, classifications and geography, and capital and investments. Pass the exact schemaVersion from the root contract.

list_alert_filter_values

ChatGPT
Use this to find the values a page alert's option filter takes, such as municipality codes, postal codes, industries, legal forms, building uses or transfer methods, before creating or changing a page alert. Returns each value with its label from the page's current data.

list_alerts

ChatGPT
Use this to see all the user's alerts (search agents), including those made on Datapublica's pages: each alert's kind, name, what it searches (a page's filters with a readable filterSummary and companyQuery, or a SQL alert's sql, keyColumns and description), the url where the user opens it, whether it is active, its status (ok, seeding, too_broad, failed, unavailable, or broken when a SQL alert's query no longer runs as defined, with the error) and its matches at the last daily run, plus how many SQL alerts the plan allows. Check it before creating an alert, and to find an alertId.

list_followed_entities

ChatGPT
Use this to see which companies, people, registry participants and properties the user follows in Datapublica, grouped by their lists, and how many more of each type their plan allows. Check it before offering to follow an entity, so you skip entities already followed, and to find a listId when the user names a list. Followed entities notify the user when they change.

search_companies

ChatGPT
Use this when the user names a Danish company, supplies a partial company name or CVR identifier, or when you need a stable company identifier before calling another company tool. Returns candidate companies and stable identifiers. Do not use for people, unresolved registry participants, or broad cross-company screening; use the matching search tool or SQL instead. Each valid company CVR has one compact Datapublica overview URL.

search_companies_semantically

ChatGPT
Use this when the user describes the kind of Danish company they want by business activity, products, services, or customer types, such as SaaS companies or manufacturers serving hospitals. Do not put geography, financials, size, or status in the query; request a large enough candidate pool and filter the returned fields afterward. Results contain rank but no similarity score and are not exhaustive.

search_participants

ChatGPT
Use this when the target is a registry participant that is not resolved as a company or person, or when the company and person searches cannot represent the registry identity. Do not use as the first choice when the target is clearly a company or resolved person.

search_people

ChatGPT
Use this when the user names a person associated with Danish companies and you need a resolved person identifier before retrieving details, history, or relationships. Do not use for companies or unresolved registry participants.

search_properties

ChatGPT
Use this when the user names a Danish address or BFE number and you need the property's stable BFE number before calling another property tool. Returns up to 50 matching properties with kind (sfe main property, condominium, or bpfg building on leased land), address, main use, and up to two current owner names. Misspelled street or town words are corrected. Do not use it to screen or rank many properties; use SQL instead.

submit_feedback

ChatGPT
Use this to tell the Datapublica team about a problem you hit with these tools so they can fix it: a tool returned wrong, missing or inconsistent data; a tool failed in a way you could not work around; a tool description or the SQL contract misled you; or the task needed a capability the tools lack. Report only after trying reasonable alternatives, and once per distinct problem. Never use it for tasks that went well, for problems outside Datapublica, or to request data. Write the minimum needed to reproduce the problem and leave out personal data that the problem does not depend on. Include meta.requestId values from the affected responses. The report is stored under the user's account for the Datapublica team, returns no data, and is limited to 10 per account per day. Tell the user that you sent it.

translate_to_sql

ChatGPT
Use this only as a fallback when a complex Danish or English analytical question cannot be converted confidently into SQL from the active contract. It can translate screening, ranking, comparison, aggregation, trend, and multi-domain questions, but consumes natural-language credits and does not execute the result. The question text is sent to OpenAI under API terms with storage disabled and is not used for model training; see the Datapublica privacy policy.

unfollow_entity

ChatGPT
Use this only when the user asks to stop following a company, person, registry participant or property. Removes it from the named list, or from every list holding it when listId is omitted.

validate_sql

ChatGPT
Use this after authoring or modifying custom DuckDB SQL and before execution. It validates full-dataset analytical queries against the active schema, read-only safety rules, semantic domains, financial scope, currency rules, and plan access without running them.

execute_sql

Claude

expand_portfolio_relations

Claude

find_similar_companies

Claude

get_company

Claude

get_company_annual_report_sections

Claude

get_company_capital_events

Claude

get_company_gazelle

Claude

get_company_portfolio

Claude

get_company_timeline

Claude

get_investment_feed

Claude

get_participant

Claude

get_participant_portfolio

Claude

get_participant_timeline

Claude

get_person

Claude

get_person_portfolio

Claude

get_person_timeline

Claude

get_sql_contract

Claude

get_sql_contract_module

Claude

search_companies

Claude

search_companies_semantically

Claude

search_participants

Claude

search_people

Claude

translate_to_sql

Claude

validate_sql

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/datapublica-dk"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/datapublica-dk)