Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-brreg Look up organisation number 923609016 and tell me who chairs the board."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server for Enhetsregisteret, the Norwegian Central Coordinating Register for Legal Entities.
Gives an AI agent direct access to the Norwegian company register: look up an organisation number, search by name or industry, list companies registered in a municipality this month, or read the registered board of a company.
Every Norwegian developer, analyst or salesperson eventually needs the same thing — company data from Brønnøysund — and ends up writing the same fetch wrapper. This is that wrapper, exposed as tools an agent can call directly.
Unlike a lot of public-data projects, there is no local copy and no scheduled harvest here. Enhetsregisteret is an official, documented, unauthenticated API that answers fast, so the server queries it live. The data you get is the register as it stands right now.
Related MCP server: mcp-cvr-dk
Tool | What it does |
| Search by name, industry code (NACE), municipality or legal form |
| Full register record for one organisation number |
| Companies entered into the register within a recent date window |
| Registered roles — chair, board members, general manager |
Filters accept comma-separated values, so municipalityNumber: "3103,3105" covers several municipalities in one call and organisationForm: "AS,ENK" covers several legal forms.
git clone https://github.com/DimaVasilenko-Intune/mcp-brreg.git
cd mcp-brreg
npm install
npm run build
claude mcp add brreg -- node "$(pwd)/dist/server.js"Any MCP client works — it is a plain stdio server:
{
"mcpServers": {
"brreg": {
"command": "node",
"args": ["/absolute/path/to/mcp-brreg/dist/server.js"]
}
}
}Once connected, an agent can answer things like:
"Which limited companies were registered in Moss in the last 30 days?"
"Look up organisation number 923609016 and tell me who chairs the board."
"Find bakeries in Fredrikstad that have no website registered."
Enhetsregisteret at data.brreg.no — public, free and unauthenticated. No API key is needed and this server sends none. The register is maintained by Brønnøysundregistrene; this project only reshapes what it publishes.
A note on personal data: get_roles returns the names of people holding registered roles. That information is public by law and already served by the register to anyone who asks — this server does not widen access to it. If you build something on top, the usual rules about processing personal data still apply to you.
npm run dev # run from source
npm run build # compile to dist/MIT © Dima Vasilenko
Full register record for a single Norwegian organisation number.
| Name | Required | Description | Default |
|---|---|---|---|
| orgnr | Yes | Nine-digit Norwegian organisation number |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It implies a read-only retrieval by stating 'Full register record' but does not disclose error behavior, authorization requirements, or rate limits. It is not contradictory, but the transparency is minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence of eight words. Every word earns its place: 'Full register record' sets expectations for the return payload, and 'single Norwegian organisation number' uniquely identifies the input.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With one parameter and no output schema, the description adequately conveys that the tool returns the complete registered company data for a given org number. It could expand on the record's structure, but the low complexity and explicit 'full record' wording make it largely sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already fully describes the only parameter (orgnr) with a pattern and description. The description repeats the phrase 'Norwegian organisation number' but adds no new semantic detail beyond the schema, so it meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Full register record for a single Norwegian organisation number' clearly states the verb (get/return), resource (company record), and scope (single Norwegian organisation number). It distinguishes from siblings like search_companies and list_recent_registrations, which serve different lookup flows.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates this tool is for retrieving one company by a known Norwegian organisation number, which provides clear context on when to use it. It doesn't explicitly mention alternatives, but the 'single ... organisation number' prerequisite effectively guides the agent away from search or list tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Registered roles for a company — board members, chair, general manager and similar, as published in the public register.
| Name | Required | Description | Default |
|---|---|---|---|
| orgnr | Yes | Nine-digit Norwegian organisation number |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It adds the context that data comes from the public register, which is useful, but it does not disclose what happens for invalid org numbers, whether the result is a list or object, or any access requirements. It is a read operation implied by 'registered', but not explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, front-loading the core purpose with useful context ('public register'). There is no wasted content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple single-parameter getter, the description provides adequate context about the data source and content. However, without an output schema, it does not explain the return structure or potential error conditions, leaving some ambiguity for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already fully documents the single parameter 'orgnr' with a description and pattern. The tool description does not add any additional parameter semantics beyond what the schema provides. Baseline of 3 applies due to high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool returns registered roles for a company (board members, chair, general manager, etc.), which is a specific verb+resource. It distinguishes itself from sibling tools like get_company (which presumably returns company-level data) and search_companies (search).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when needing role information from the public register, but does not explicitly state when to use this versus siblings or when not to use it. There are no exclusion conditions or alternative tool references.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Companies entered into the register within a recent date window, optionally filtered by municipality and legal form. Useful for tracking new business activity in an area.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Look-back window, default 30 | |
| limit | No | Default 50 | |
| toDate | No | YYYY-MM-DD | |
| fromDate | No | YYYY-MM-DD. Overrides days when given | |
| organisationForm | No | Legal form code, comma-separate for several. Default "AS,ENK" | |
| municipalityNumber | No | Municipality number, comma-separate for several, e.g. "3103,3105" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses that results are within a date window and can be filtered, but does not mention read-only nature, default behaviors, pagination, or ordering. For a listing tool, basic safety is implied but not explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with the main purpose. No wasted words. Every phrase contributes meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and six optional parameters, the description gives adequate context for a listing tool. It explains the core purpose and filters, but doesn't mention defaults or return structure. However, schema covers parameter defaults, so the description is sufficiently complete for the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% coverage with descriptions for all parameters. Description adds context by tying 'recent date window' to date parameters and 'municipality and legal form' to filters, but does not add meaning beyond schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Title 'List newly registered companies' and description 'Companies entered into the register within a recent date window' clearly states the verb (list) and resource (company registrations). It distinguishes from siblings by focusing on recent registration dates rather than general search or specific company details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description provides clear context: 'Useful for tracking new business activity in an area.' This implies when to use the tool. However, it does not explicitly mention alternatives or exclusions (e.g., when not to use vs search_companies).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Enhetsregisteret by name, industry code, municipality or legal form. Returns registered companies with address, industry and contact details where the register has them.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Company name, full or partial | |
| limit | No | Default 20 | |
| industryCode | No | NACE code, e.g. "10.710" for bakeries | |
| organisationForm | No | Legal form code, e.g. "AS", "ENK", "ANS". Comma-separate for several | |
| municipalityNumber | No | Municipality number, e.g. "3103" for Moss. Comma-separate for several |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description notes that it returns companies 'where the register has them,' which is a helpful caveat about data completeness. However, it does not disclose whether the search is read-only (though that's implied), any rate limits, or how results are ordered/paginated. Since there are no annotations, the description carries the full burden, but it provides only limited behavioral detail beyond the basic return value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loading the core action in the first sentence and the return value in the second. No redundant or filler content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the essential purpose and return fields, but for a tool with five optional parameters and no output schema, it could specify more about result behavior (e.g., default limit, accessibility of search). However, the schema supplies parameter constraints, so the description is adequate for selecting and invoking the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema descriptions cover all parameters with examples and constraints (e.g., limit maximum, comma-separation for organisationForm and municipalityNumber). The tool description only repeats the search criteria from the schema (name, industry code, municipality, legal form) without adding new semantic meaning, so it meets the baseline but doesn't enrich parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches Enhetsregisteret by name, industry code, municipality, or legal form, and returns registered companies with address, industry, and contact details. This distinguishes it from sibling tools like get_company, which implies a direct lookup, and list_recent_registrations, which focuses on new entries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when searching for companies by these criteria, but it does not explicitly state when to prefer this over get_company or list_recent_registrations, nor does it mention exclusion criteria. For example, it doesn't say 'use get_company for exact organization numbers' or 'use list_recent_registrations for newly registered companies.' Thus, usage guidance is present but implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0get_companyget_roleslist_recent_registrationssearch_companiesEach tool targets a distinct aspect of the register: searching by criteria, fetching full company details, listing recent registrations, and retrieving roles. There is no functional overlap; search_companies and list_recent_registrations differ by query type and purpose.
All tool names follow a consistent verb_noun pattern: search_companies, get_company, list_recent_registrations, get_roles. The verbs are action-oriented and the nouns are clear, making the pattern predictable and easy to infer.
With 4 tools, the server is well-scoped for a public company register API. Each tool serves a distinct common use case without unnecessary bloat, and the count is neither too sparse nor overwhelming.
The tool set covers the essential read operations for the domain: discovery (search and recent registrations), detailed lookup (get_company), and related structured data (get_roles). Since the register is public and read-only, no create/update/delete is expected. The surface is complete for typical consumer needs.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Brønnøysund Register Centre (BRREG) MCP — Norway's official business register.
CompanyLens is a remote MCP server giving AI agents instant access to official company registry data across 19 jurisdictions in Europe, the Americas, and Asia-Pacific. Eighteen read-only tools let you search companies and people, look up officers and beneficial owners, map corporate networks through shared directors, screen names against the UK disqualified directors register, find every company at a registered address, and pull filing history — all from a single connector. Visit our website: https://companylens.io
Hosted MCP server for real-world data: business registries, sanctions, companies, domains, crypto.
Nordic company intelligence: look up companies, AI summaries, scores and signals via MCP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/DimaVasilenko-Intune/mcp-brreg'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
