Isap MCP server

mcp-isap

Installation (one command)

Published on npm + MCP Registry (io.github.matematicsolutions/mcp-isap). Run without cloning:

npx -y @matematicsolutions/mcp-isap

MCP client configuration (stdio):

{ "mcpServers": { "mcp-isap": { "command": "npx", "args": ["-y", "@matematicsolutions/mcp-isap"] } } }

(Building from source - below.)

MCP server for Polish legislation - Dziennik Ustaw (Journal of Laws, DU) + Monitor Polski (MP) via the official Sejm ELI API (api.sejm.gov.pl/eli).

Why

mcp-saos (general courts) + mcp-nsa (administrative) + mcp-eu-sparql (EU) cover the case-law side. mcp-isap adds legislation - statutes, regulations, official announcements, international agreements. This closes the triad:

STATUTE + CASE LAW + EU LAW
   ↓         ↓          ↓
  ISAP    SAOS+NSA   EUR-Lex
   ↓         ↓          ↓
        law firm asks about GDPR
        → 4 connectors in parallel
        → 4 citation sections in the panel

Coverage: 96,000+ acts from 1918 to today. Full ELI support (European Legislation Identifier).

Tools

search by title fragment / year / publisher / act type / in-force status. publisher: DU (Dziennik Ustaw) or MP (Monitor Polski).

• searchacts(title?, year?, publisher?, type?, inforce?, limit?) -

Returns title, type, status, entry into force, keywords, links to HTML/PDF text and the ISAP page.

• getact(eli)** - act details by ELI (DU/2018/1000).

tags), paginated at 5000 characters per page. Iterate page while structuredContent.pagination.hasmore is true, or pass searchtext (e.g. "Art. 118.") to get the fragment around the first hit in one call. structuredContent.textversion says whether this is a consolidated text or the wording as promulgated - Sejm ELI serves the original wording for base acts, so for the law in force fetch the newest consolidated-text announcement listed in consolidatedtexteli. Acts published only as PDF return the textunavailableusepdf error with links, never prose standing in for the provision.

• getacttext(eli, page?, searchtext?)** - the act's plain text (no HTML

Every response includes structuredContent.citations with fields: title, url (ISAP UI), eli, displayaddress (Dz.U. 2018 poz. 1000), publisher, year, documenttype, status, in_force, promulgation.

Patron reads this field automatically and renders it in the UI panel as the section "Polish legal acts (Dz.U. / M.P. - Sejm ELI)".

Stack

• Node 18+ (built-in fetch)
• @modelcontextprotocol/sdk
• Stdio transport
• 500 ms throttle between requests (2 req/s)
• No scraping - pure REST JSON API

Build + run

npm install
npm run build
node dist/index.js

Wiring into Patron

In patron/backend/mcp-servers.json:

{
  "name": "isap",
  "transport": "stdio",
  "command": "node",
  "args": ["C:/Users/<YOUR-USER>/mcp-isap/dist/index.js"],
  "enabled": true
}

Smoke test

echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"s","version":"0"}}}
{"jsonrpc":"2.0","method":"notifications/initialized"}
{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"get_act","arguments":{"eli":"DU/2018/1000"}}}' \
  | node dist/index.js

Should return the Personal Data Protection Act of 10 May 2018, status IN_FORCE, a link to ISAP and a structured citation.

Lineage

API contract derived from legal-data-hunter/sources/PL/DziennikUrzedowy (Python + REST, MIT). TS implementation from scratch - no source code imported.

License

Shortened. The full README is on GitHub.