Prawo Pl MCP server

prawo-pl-mcp

<!-- mcp-name: io.github.matematicsolutions/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:

pl_call - fewer tool schemas means less context spent before the LLM starts working.

• Four tools instead of 42. pllistsources, plsearch, plget_document,

there, pages counted from 0 or from 1 depending on the repo. Here page is always 1-based and dates are always datefrom/dateto (YYYY-MM-DD); the translation happens inside. One name per concept applies to the aggregator's own tools too: page is the page parameter of both plsearch and plgetdocument (pagenumber still works as a deprecated alias), and pl_call takes arguments or its alias args.

• One convention. The connectors grew organically: dateFrom here, date_from

native parameter name each unified one maps to for that source, so articlenumber (eu-compliance) is visible without spawning the connector or reading an upstream error. plcall checks the names it was given against the connector's own schema and says which one it meant.

• Native names on the table. Every catalog entry carries native_params - the

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.

• Nothing preinstalled. Connectors run as subprocesses via npx -y / uvx,

characters per page (yargi-mcp's pattern), so a 200-page ruling does not flood the context window. Sources that paginate server-side (isap) get the page forwarded natively and are reported as pagination: "native" - the aggregator does not re-cut an already-cut page and does not invent a total_pages it cannot know.

• Paginated documents. Full judgment and act texts are chunked at ~5000

Coverage

Shortened. The full README is on GitHub.