rejestr-io-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HTTP_HOST | No | Adres nasłuchu dla MCP_TRANSPORT=http | 127.0.0.1 |
| MCP_HTTP_PORT | No | Port nasłuchu dla MCP_TRANSPORT=http | 8000 |
| MCP_TRANSPORT | No | stdio lub http | stdio |
| REJESTR_IO_API_KEY | Yes | Klucz API rejestr.io | |
| MCP_HTTP_AUTH_TOKEN | No | Opcjonalny token uwierzytelniający (bearer) dla transportu HTTP | |
| REJESTR_IO_BASE_URL | No | Bazowy adres API | https://rejestr.io/api/v2/ |
| REJESTR_IO_DOWNLOAD_DIR | No | Katalog zapisu plików PDF | ./downloads |
| REJESTR_IO_CACHE_MAX_SIZE | No | Maks. liczba wpisów w cache | 512 |
| REJESTR_IO_CACHE_TTL_SECONDS | No | TTL cache w pamięci (sekundy) | 300 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_organizationsA | Search organizations in the Polish National Court Register (KRS) by name, registry numbers, legal form, PKD codes, status flags, address, and pagination. |
| get_organizationA | Get basic data for an organization by KRS number or NIP (e.g. '12345' or 'nip1234567890'). |
| get_organization_krs_chapterB | Get one KRS chapter (general, branches, shares, mentions, liabilities, or transformations) for an organization. 'branches', 'liabilities', and 'transformations' require a Premium+ plan. |
| get_organization_beneficial_ownersA | Get the beneficial owners (CRBR) of an organization by KRS number or NIP. Requires a Premium+ plan. |
| get_organization_relationsA | Get an organization's current or historical relations with other organizations and people in the KRS. |
| get_organization_krs_extractA | Download a KRS extract (odpis) PDF for an organization. 'current' requires Premium+, 'full' requires Biznes plan. Saves the PDF to the downloads directory and returns its absolute path; pass return_base64=True to also receive the file content inline. |
| list_organization_krs_entriesB | List all KRS entries (wpisy) recorded for an organization. |
| get_personA | Get current data for a person appearing in the KRS by their person id. |
| get_person_relationsA | Get a person's current or historical relations with organizations recorded in the KRS. |
| list_organization_financial_documentsA | List financial document groups (by accounting period) available in the KRS for an organization. Requires a Premium+ plan. |
| get_organization_financial_documentA | Get one financial document for an organization by document id. format='pdf' (default) requires Premium+ and saves the file to the downloads directory, returning its absolute path (pass return_base64=True to also receive the content inline). format='json' requires a Biznes plan and returns the parsed document content directly, at a higher per-request cost. |
| get_account_balanceA | Get the current rejestr.io API account balance in PLN. Free — does not consume account balance. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool targets a distinct resource-action pair: searching, retrieving organization data, chapters, entries, extracts, persons, relations, financial documents, and account balance. Even similar-looking tools like get_organization_krs_chapter, list_organization_krs_entries, and get_organization_krs_extract are clearly differentiated by their descriptions.
Tool names consistently follow a verb_noun pattern, primarily using get_ and list_ with resource-specific suffixes. The naming is predictable and makes the hierarchy of resources clear, e.g., get_organization, get_person, get_organization_relations, get_person_relations.
Twelve tools is well-scoped for a registry lookup server. Each tool addresses a meaningful part of the KRS data surface without unnecessary duplication or bloat, and the small utility tool for account balance earns its place.
The tool set provides thorough read-only coverage of the Polish National Court Register domain: search, basic data, KRS chapters, entries, extracts, beneficial owners, relations, financial documents, and persons. Because this is a read-only registry API, create/update/delete operations are not expected, so there are no obvious gaps.