Skip to main content
Glama
pipeworx-io

mcp-law-commission

by pipeworx-io

@pipeworx/law-commission

Consultation papers, reports, summaries and law-reform projects published by the Law Commission of England & Wales (lawcom.gov.uk) — the independent statutory body that reviews the law and recommends reform to Parliament.

Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.

Tools

  • search_law_commission_publications(query?, limit?) — search publication titles and body text; returns title, link, date and excerpt.

  • get_law_commission_publication(id?, link?) — fetch one publication's full text, the law-reform project it belongs to, and any attached PDF reports.

  • list_law_commission_projects(status?, limit?) — list law-reform workstreams, optionally filtered to current, completed, upcoming or other.

Related MCP server: lex-provenance-mcp

Auth

Keyless. No signup, no key.

Data sources

Welsh-language duplicates

Every publication and project the Commission issues in Welsh is a separate WordPress post — same report, same date, its own numeric id — carrying a language taxonomy term (Cymraeg, the only term the language taxonomy has; English posts carry no term at all, since English is the unmarked default). A plain title search for "leasehold" returns both "Commercial leasehold: overcoming barriers to transactions" (English) and "Lesddaliad masnachol: goresgyn rhwystrau rhag trafodion" (the same report, in Welsh) as two hits.

search_law_commission_publications and list_law_commission_projects both filter out any row carrying a language term before applying limit, so a caller gets one English row per report rather than two. The filter fetches limit * 3 rows upstream (capped at 100) to leave headroom for the ones it drops — in practice Welsh duplicates run well under half of any result set. The Welsh original is still directly reachable via get_law_commission_publication by id or link; the filter only applies to search/listing, and the returned language field on that tool tells you which you got (en / cy).

X-WP-Total from the upstream API counts both languages, so it is surfaced as total_matching_all_languages rather than total — using it as the count of English rows would overstate coverage by roughly the Welsh-duplicate share.

Caveats worth passing to a user

  • This is not case law or legislation. The Commission's own reports recommend reform; they are not binding law. legislation-uk covers legislation.gov.uk, uk-caselaw covers judgments — this pack is the third leg (Law Commission reports) named in Bruce's "Parliamentary materials, explanatory notes and Law Commission reports" ask (docs/uk-primary-law-scope.md).

  • Full report text is PDF, not HTML. The publication post body typically carries only a link to its project — no summary text and no excerpt field content — so search_law_commission_publications' excerpt is usually empty and get_law_commission_publication's text is one line. The actual report is the PDF in attachments. This pack does not extract PDF text.

  • Search is title/body text, not the PDFs. Given the above, that means search is effectively title-only for most publications; a phrase that only appears inside the attached PDF will not match.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "law-commission": {
      "url": "https://gateway.pipeworx.io/law-commission/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/law-commission/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1679+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/search_law_commission_publications \
  -H 'Content-Type: application/json' \
  -d '{"query":"leasehold","limit":5}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/search_law_commission_publications. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "law-commission": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-law-commission"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-law-commission

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Law Commission data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    A
    maintenance
    Enables searching and retrieval of UK legislation (Acts, Statutory Instruments) from legislation.gov.uk with persistent identifiers and verifiable citations.
    9
    42 PyPI
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    A read-only MCP connector for searching, fetching, and citing provenance-tracked legal corpora with verifiable content hashes.
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Single-endpoint MCP server federating nine open-access legal scholarship indexes, enabling federated search, multi-jurisdiction comparison, and full-text retrieval via tools like search_legal_scholarship and compare_jurisdictions.
    MIT