LegalOSS136.6ktracked
MCP Servers · Legal Research & Search · Case Law & Legal Data · Compliance & Privacy

prawo-pl-mcpMaintained

matematicsolutions/prawo-pl-mcp

Seven Polish legal databases plus three EU sources, behind four MCP tools instead of forty-two.

MCP ServersLegal Research & SearchCase Law & Legal DataCompliance & Privacylegal-datalegaltechmcpmodel-context-protocolpoland
From the maintainer

Polish legal databases each come with their own API, their own parameter names and their own pagination. We ship one MCP connector per database; this server puts ten of them behind four tools, starts a connector only when a question needs it, and returns documents in 5,000-character pages.

For lawyers and legal engineers working with Polish law in Claude, Cursor or any MCP client. Install with uvx prawo-pl-mcp - the connectors download themselves on first use. Nothing here is vendored or forked; each connector stays its own package with its own repository.

The design follows yargi-mcp, which does the same for Turkish law.

prawo-pl-mcp

One MCP server for Polish legal data.

Ten independent connectors - case law, legislation, the company register, tax rulings, public procurement, data-protection decisions, plus EU extras - behind four tools. Each connector stays a separate package with its own repository; this server spawns them on demand and translates between their conventions.

"Prawo" is Polish for "law"; the name follows yargi-mcp's move of naming a country server in its own language.

Why an aggregator

The connectors cover Polish legal data well, but as separate MCP servers, one per database - ten installs and ten config entries before the first question. yargi-mcp showed the fix for Turkish law: 16 institutions, one server. prawo-pl-mcp does the same for Poland:

  • Four tools instead of 42. pl_list_sources, pl_search, pl_get_document, pl_call - fewer tool schemas means less context spent before the LLM starts working.

  • One convention. The connectors grew organically: dateFrom here, date_from there, pages counted from 0 or from 1 depending on the repo. Here page is always 1-based and dates are always date_from/date_to (YYYY-MM-DD); the translation happens inside.

  • Nothing preinstalled. Connectors run as subprocesses via npx -y / uvx, downloaded on the first call to a given source and kept alive afterwards. A source that cannot start reports a readable error while the rest keep working.

  • Paginated documents. Full judgment and act texts are chunked at ~5000 characters per page (yargi-mcp's pattern), so a 200-page ruling does not flood the context window.

Coverage

Source idWhatInstitution / databaseConnectorRuntimesaosCase law: common courts, Supreme Court, Constitutional Tribunal + citatorSAOSmcp-saosnpxnsaCase law: administrative courts (NSA + 16 WSA)CBOSAmcp-nsanpxisapLegislation: Dziennik Ustaw + Monitor Polski, 96k+ actsSejm ELI APImcp-isapnpxkrsCompany register: extracts, history, board compositionKRS API (Ministry of Justice)mcp-krsnpxeurekaTax rulings: 550k+ individual interpretationsEUREKA (Ministry of Finance)mcp-eurekanpxkioPublic procurement: National Appeal Chamber rulingsorzeczenia.uzp.gov.plkio-orzeczenia-mcpuvxuodoGDPR enforcement: Polish DPA decisions, fines, statsorzeczenia.uodo.gov.pluodo-orzeczenia-mcpuvxeu-sparqlEU law: EUR-Lex by CELEX, CJEU by ECLI, GDPRhubCellar SPARQLmcp-eu-sparqlnpxeu-compliance14 EU regulations offline (GDPR, AI Act, DORA, NIS2...)Local SQLite corpusmcp-eu-compliancenpxlegalizeLaw-as-git: 32 jurisdictions, versioned by commitlegalize-devlegalize-mcpuvx

Polish sources are tagged group: pl, EU extras group: eu - filter with pl_list_sources(group="pl").

Tools

ToolWhat it doespl_list_sourcesCatalog of sources (no subprocess spawned). With source_id: live tool schemas of one connector.pl_searchSearch any source with normalized parameters; source-specific filters via extra.pl_get_documentFull document by identifier (judgment id, ELI, KRS number, signature...), paginated.pl_callAny native tool of any connector: citator, DPA statistics, board composition, regulation comparison...

The typical flow an LLM follows (spelled out in the server's instructions): pl_list_sourcespl_searchpl_get_document, with pl_call for the specialized tools each connector brings.

Install

Requires Python ≥ 3.11 plus the runtimes of the sources you use: Node.js ≥ 18 for npx sources, uv for uvx sources. If a runtime is missing, its sources report source_unavailable and the rest work.

Claude Code

claude mcp add pl-legal -- uvx prawo-pl-mcp

Claude Desktop / any MCP client (stdio)

{
  "mcpServers": {
    "pl-legal": {
      "command": "uvx",
      "args": ["prawo-pl-mcp"]
    }
  }
}

Remote (Streamable HTTP)

uvicorn prawo_pl_mcp.asgi:app --host 0.0.0.0 --port 8000

Open by default (public, read-only data). Set PRAWO_PL_MCP_API_KEY to require X-API-Key: <key> or Authorization: Bearer <key> on every request.

Configuration

EnvDefaultMeaningPRAWO_PL_MCP_CMD_<ID>-Override the spawn command for a source, e.g. PRAWO_PL_MCP_CMD_SAOS="node C:/dev/mcp-saos/dist/index.js" for a local checkout. <ID> = source id, uppercase, -_.PRAWO_PL_MCP_INIT_TIMEOUT180Seconds allowed for a connector's first start (includes package download).PRAWO_PL_MCP_TIMEOUT90Seconds per tool call after startup.PRAWO_PL_MCP_AUDIT_DIR~/.matematic/auditWhere the JSONL audit log goes.PRAWO_PL_MCP_API_KEY-ASGI mode only: require this API key (dual-channel).

Architecture

The aggregator is a thin proxy (ADR 0001). Connectors are not imported, vendored or forked; the aggregator speaks MCP to them over stdio the same way any client would. The whole layer is a source registry (one dataclass entry per connector), a lazy subprocess pool, a parameter translator and a paginator. Adding a source means adding a registry entry.

LLM client ──MCP──▶ prawo-pl-mcp ──MCP/stdio──▶ npx @matematicsolutions/mcp-saos
                        │         ──MCP/stdio──▶ uvx kio-orzeczenia-mcp
                        │         ──MCP/stdio──▶ ... (spawned on first use)
                        └─ registry + param mapping + 5000-char pagination

Every call lands in a JSONL audit log (timestamp, tool, source, parameter hash, latency - never document content).

Development

git clone https://github.com/matematicsolutions/prawo-pl-mcp && cd prawo-pl-mcp
uv sync --extra dev
uv run pytest          # offline tests: registry, dispatch mapping, pagination, drift
uv run prawo-pl-mcp    # stdio server

License

Apache-2.0. Individual connectors carry their own licenses (MIT or Apache-2.0), their own rate limits and their own terms toward upstream databases - the aggregator adds no caching and no transformation beyond pagination, so each connector's constraints apply unchanged.

README curated by the maintainer · Jul 31, 2026 · original on GitHub →