USE THIS TOOL WHEN you have a judgment slug and need metadata (parties, judges, neutral citation, court, dates).
Call case_law_search FIRST to get the slug. AFTER calling, use
judgment_get_index to discover paragraphs, then judgment_get_paragraph to
read specific ones. Authoritative source for UK judgment metadata.
Parameters (1)
slugstringrequired
Judgment slug, e.g. 'uksc/2024/12' or 'ewca/civ/2023/450'
judgment_get_index
USE THIS TOOL WHEN you have a judgment slug and want the paragraph navigation index (eId + preview line for every paragraph).
Call case_law_search FIRST to get the slug. AFTER calling, pass an eId
from the returned list into judgment_get_paragraph to read that paragraph's
full text, or use case_law_grep_judgment for content search across all
paragraphs.
Parameters (1)
slugstringrequired
Judgment slug, e.g. 'uksc/2024/12'
judgment_get_paragraph
USE THIS TOOL WHEN you have a judgment slug + LegalDocML eId and want that paragraph's full text.
Call judgment_get_index FIRST to discover available eIds (or use
case_law_grep_judgment to locate paragraphs by content). Returns the
paragraph XML content (400–1,700 tokens typical).
Parameters (2)
eIdstringrequired
Paragraph eId from judgment_get_index, e.g. 'para_12'. Numeric strings like '12' are accepted and normalized to 'para_12'.
slugstringrequired
Judgment slug, e.g. 'uksc/2024/12'
case_law_search
USE THIS TOOL WHEN searching UK case law by party names, court, judge, date, or free-text query.
Returns paginated judgment summaries: neutral citation, court, dates, slug,
stable TNA URI. AFTER calling: pass slug into judgment_get_header /
judgment_get_index / judgment_get_paragraph (or the judgment:// resource
family) for content; pass the neutral citation into citations_resolve
to verify before constructing an OSCOLA citation; use
case_law_grep_judgment to find text within a single judgment. When a
party name returns several candidates, narrow with court + year filters
before grep-iterating across full judgments — targeted filtering beats
scanning every candidate.
Coverage: TNA Find Case Law indexes UK judgments from roughly the early
2000s onwards. For older authorities, search for a modern judgment that
quotes them and read that paragraph.
Authoritative source for UK case law. Web search returns out-of-date or
unstable URLs — do not supplement.
Earliest judgment date (YYYY-MM-DD). NOTE: the TNA atom.xml endpoint currently appears to ignore this filter — the same results come back regardless. Do not rely on it to narrow output; sort+slice client-side or refine `query` instead.
judgeany
Filter by judge surname. Case-insensitive substring match against the indexed form. Use the surname alone ('Reed', 'Sumption') or with the bare title ('Lord Reed'). Honorific suffixes silently zero the result set — do not append 'JSC', 'of Allermuir', 'KC' etc. Speculating a fuller form than what TNA indexed will return 0 hits with no error.
limitinteger
Maximum results to return (1–50). TNA returns up to 50 per request; this slices client-side. Default 10 for a tight shortlist. Set higher for breadth (e.g. 50 to scan the full result set).
pageinteger
Result page number (1-indexed)
partyany
Filter by party name
querystringrequired
Full-text search query, e.g. 'negligence duty of care'
to_dateany
Latest judgment date (YYYY-MM-DD). Same caveat as `from_date` — currently silently ignored by upstream. Filtering happens client-side at best.
case_law_grep_judgment
USE THIS TOOL WHEN you have a judgment slug and want to find paragraphs whose text matches a pattern.
Returns a list of `{eId, snippet, match}` hits — small per-paragraph
snippets centred on the match. AFTER calling, read full paragraphs via
judgment_get_paragraph(slug, eId) or the judgment://{slug}/para/{eId}
resource.
Use case: content search within one judgment (e.g. "negligence", "test
for foreseeability", "Donoghue"). For paragraph-number navigation by
eId, call judgment_get_index instead.
Pattern is regex; if it doesn't compile, falls back to literal substring
search.
Parameters (4)
case_insensitiveboolean
Default true. Set false for case-sensitive matching.
max_hitsinteger
Cap on number of hits returned.
patternstringrequired
Regex pattern (or plain substring) to search within paragraph text. If the pattern doesn't compile as regex, falls back to literal substring match.
slugstringrequired
TNA judgment slug, e.g. 'uksc/2024/12' or 'ewca/civ/2023/450'.
legislation_search
USE THIS TOOL WHEN searching UK Acts and Statutory Instruments by title, phrase, or full-text.
Returns ranked results: title, type, year, number, legislation.gov.uk URL,
and next_steps hints (toc URI, section template). AFTER calling, chain
to legislation_get_toc then legislation_get_section for structural drill-in.
Filter discipline: `type` and `year` are exact-match. Use only when you
already know the value. For currency-driven searches ("the recent
Renters' Rights Act"), query by phrase alone and read the year from the
results — guessing a year and filtering by it zeroes results when wrong.
For broader concept queries across content, set `fulltext=True`.
Authoritative source for UK primary and secondary legislation
(legislation.gov.uk).
Parameters (5)
fulltextboolean
Default false → searches Act/SI titles only (best for finding a named Act, e.g. 'Housing Act 1988' returns ukpga/1988/50 first). Set true to search the full text of every Act/SI for the query (returns SIs and regulations that cite the term — e.g. 'rental deposits' would return many implementing instruments).
limitinteger
Maximum results to return (1–50). Passed to the upstream results-count param.
querystringrequired
Search query, e.g. 'Housing Act 1988' or 'data protection personal data'
typeany
Filter by type: 'ukpga' (Acts), 'uksi' (SIs), 'asp' (Scottish Acts), 'nia' (NI Acts). Exact-match — omit if you don't already know whether you're looking for an Act vs an SI.
yearany
Filter by year of enactment (exact-match — a single integer, not a range). Omit unless you already know the Act's year. Speculating a year (e.g. 'this is recent so it must be 2026') and getting it wrong will zero out the result set. Better workflow: query without `year`, then read the year from the returned results.
legislation_get_section
USE THIS TOOL WHEN you have a known Act / SI and want the parsed text of a specific section, with extent and in-force metadata.
Returns full section text, territorial extent, in-force status, and
prospective flag. Content capped per max_chars (default 10,000,
~2,500 tokens) — raise for unusually long definition sections; check
content_truncated in the response.
ALWAYS check `extent` — a section may apply to England & Wales but not
Scotland or Northern Ireland. Reciting a section without checking
extent is a recurring legal-research error.
Alternative: call read_resource(uri="legislation://{type}/{year}/{number}/
section/{section}") for raw CLML XML; use this tool when you want the
parsed structured response instead.
Parameters (5)
max_charsinteger
Maximum characters of section content to return. Default 10,000 (~2,500 tokens) covers almost every section. Raise to 50,000+ only for unusually long Finance Act definition sections. Check content_truncated in the response to see if it was cut.
numberintegerrequired
Chapter or SI number
sectionstringrequired
Section number, e.g. '47' or '12A'. Use the numeric part only — not 'section-47'. Schedules are not currently supported.
typestringrequired
Legislation type code: 'ukpga' (Acts), 'uksi' (SIs), 'asp' (Scottish Acts), 'nia' (NI Acts). Use the value from legislation_search results.
yearintegerrequired
Year of enactment
legislation_get_toc
USE THIS TOOL WHEN you have a known Act / SI and want the structural table of contents (parts, chapters, sections, schedules).
Returns structural elements with XML id and title, e.g. 'section-47:
Definitions'. AFTER calling, pass the numeric section identifier (use
'47', NOT 'section-47') into legislation_get_section for full text.
Large statutes (Companies Act 2006 has many hundreds of items) are
paginated via offset/limit. Check has_more and total_items.
Alternative: call read_resource(uri="legislation://{type}/{year}/{number}/
toc") for the full TOC as a newline-separated `id: title` string (no
pagination). Use this tool when you need the structured response with
offset / limit / has_more for stepping through large statutes.
Parameters (5)
limitinteger
Maximum items to return in this call (default 200, max 1000). Raise only when you need a larger slice in one response. Check has_more and total_items to know if further pages exist.
numberintegerrequired
Chapter or SI number
offsetinteger
Number of items to skip from the flattened TOC. Use with limit to page through very large statutes like the Companies Act 2006 (1300+ items).
typestringrequired
Legislation type code: 'ukpga' (Acts), 'uksi' (SIs), 'asp' (Scottish Acts), 'nia' (NI Acts). Use the value from legislation_search results.
yearintegerrequired
Year of enactment
parliament_search_hansard
USE THIS TOOL WHEN searching Hansard by topic, bill title, or text phrase.
Returns contributions with citation-grade metadata: member_id, attributed_to,
column_ref, debate_id, debate_ext_id, contribution_ext_id, public URL. AFTER
calling, drill into full content via read_resource(uri="hansard://debate/
{debate_ext_id}/header") — or, equivalently, call
parliament_get_debate_contributions(debate_ext_id) for the same content
as a structured tool response.
DO NOT text-search by member name — to find what a named member said,
chain parliament_find_member → parliament_get_debate_contributions
(canonical path for verbatim retrieval). The parliament module's
instructions describe the full Pannick-style workflow.
Pagination: limit + offset honour the upstream paginated endpoint. For
breadth across a topic, see parliament_policy_position_summary.
Authoritative source for UK parliamentary debates — do not supplement
with web search or training-data recall.
Parameters (9)
contribution_typestring
Which Hansard section to paginate. 'Spoken' = chamber + Westminster Hall debates (the default; what a lawyer usually means). 'Written' = written answers and statements. 'Corrections' = published corrections to the record. The corpus envelope (total_debates, total_divisions, etc.) is independent of this and always populated.
from_dateany
Start date (YYYY-MM-DD)
housestring
Restrict to one House. Default 'both' returns Commons + Lords contributions.
limitinteger
Max contributions per call (1–100). Default 20. Paginate further with offset; total corpus size is in total_corpus on the response.
member_idany
Filter to contributions by a single member. Pass the integer Members API ID (resolve a name via parliament_find_member). The prior `member` field accepted a name string but Hansard's /search.json silently ignored it — the spec requires `memberId`.
offsetinteger
Skip this many contributions before the page. Default 0. Re-call with offset=offset+returned to paginate; has_more flags whether more remain.
querystringrequired
Phrase to find in Hansard contribution text bodies. Hansard searches the words members actually said in their speeches — NOT debate titles, topic metadata, or written headlines. Pass tokens that would appear in someone's speech: distinctive arguments ('disproportionate sanction'), statutory references ('section 21'), or specific phrases. Bill titles (e.g. 'Renters\'s Rights Bill') often DON'T match because members refer to 'the Bill' or 'this legislation' in their speeches. Tokenised matching: 'housing benefit fraud' will match contributions saying 'fraud in housing benefit claims'. For 'all contributions in a specific debate' regardless of words used, drill via top_debates[].debate_ext_id into parliament_get_debate_contributions.
text_modestring
'preview' returns the upstream ~250-char snippet (fast, low context cost). 'full' returns ContributionTextFull (still capped at 3000 chars). For full contribution text without the cap, read the resource hansard://debate/{debate_ext_id}/contribution/{contribution_ext_id}.
to_dateany
End date (YYYY-MM-DD)
parliament_policy_position_summary
USE THIS TOOL WHEN you want debate-level corpus signals on a topic — by_house, by_year, by_section breakdowns — without reading every contribution.
Aggregates Hansard debate-level signals on a topic. Pure counts — no LLM,
no editorial labels. Sweeps /search/Debates.json with pagination (up to
max_debates_scanned), then aggregates by_house, by_section, by_year,
by_month, and top_debates from debate metadata. Also captures the
corpus-wide envelope counts (total_contributions, total_written_statements,
total_divisions, etc.) from /search.json for cross-section scope.
AFTER calling, pick a debate from top_debates and pass its debate_ext_id
into parliament_get_debate_contributions to drill into who said what.
Note on member-level facets: Hansard's search API exposes debate
metadata, not per-contribution member identifiers, at the corpus
level. by_party and top_contributors are therefore omitted from this
deterministic summary. To see who spoke in a specific debate, read
hansard://debate/{debate_ext_id}/header for an ordered contribution
index, or call parliament_member_debates for one named member.
This is the authoritative source for UK Hansard corpus-level signals.
Parameters (5)
from_dateany
Start date (YYYY-MM-DD)
housestring
Restrict to one House. Default 'both'.
max_debates_scannedinteger
Hard cap on debates sampled from /search/Debates.json to compute facets. Default 200 issues ≤4 upstream calls (take=50 each). Raise to 2000 (≤40 calls) for an exhaustive sweep on a heavily-debated topic. Hansard rate limit: 1000 req/5min.
to_dateany
End date (YYYY-MM-DD)
topicstringrequired
Phrase to find in Hansard contribution text bodies for the facet aggregation. Same semantics as parliament_search_hansard.query: tokens that appear in members' actual speeches, not bill titles or topic metadata. The aggregator sweeps top_debates[] returned by /search/Debates.json — those debates are matched on the phrase appearing in titles or contribution text, so passing a Bill title (e.g. 'Renters\' Rights Bill') usually works for THIS tool even though it wouldn't for member-level text search, because debate-level matching uses metadata in addition to body text.
parliament_find_member
USE THIS TOOL WHEN you have a member's name and need their integer member_id.
Returns all members matching the name query, each with the integer `id`,
party, constituency, house, and current-sitting status. Disambiguates
common-name matches (e.g. "Lord Smith" returns multiple peers).
CALL THIS BEFORE any tool that filters by member_id — including
parliament_get_debate_contributions, parliament_member_debates, and
parliament_member_interests. Name → ID first; ID-based filtering second.
Skipping this step and text-searching by name returns unrelated results
(see parliament_search_hansard's anti-bypass note for the Pannick case).
Parameters (1)
namestringrequired
Name or partial name, e.g. 'Starmer', 'Baroness Hale'
parliament_member_debates
USE THIS TOOL WHEN you have a member_id and want contributions where THAT member used a specific topic phrase verbatim (text-body search).
CALL parliament_find_member(name) FIRST to obtain the integer member_id.
This is a name-based text-body search — it matches contributions whose
TEXT contains the topic phrase. A member who spoke in a debate but
didn't use your phrase verbatim is filtered out. For verbatim retrieval
of every contribution by a member in a known debate (regardless of
vocabulary), use parliament_get_debate_contributions(debate_ext_id,
member_id=...) instead.
Each contribution's text field is capped at 3000 characters.
Parameters (4)
limitinteger
Maximum contributions to return. Default 20.
member_idintegerrequired
Parliament Members API integer ID. Obtain from parliament_find_member.
offsetinteger
Number of contributions to skip before this page. Default 0. Re-call with offset=offset+returned while has_more is true.
topicany
Optional phrase to find in THIS member's contribution text bodies. Hansard searches the words the member actually said, NOT the topic or title of the debate. Pass tokens this member would have spoken — distinctive arguments ('disproportionate sanction'), statutory references ('section 21'), or motion numbers ('Motion C1') — not the bill's name (members rarely say e.g. 'Renters\' Rights Bill' verbatim in their speeches). If you want 'every contribution this member made in a specific debate' regardless of words used, find the debate_ext_id then use parliament_get_debate_contributions(debate_ext_id, member_id=...).
parliament_member_interests
USE THIS TOOL WHEN you have a member_id and need their registered financial interests (donations, directorships, land, gifts).
CALL parliament_find_member(name) FIRST to obtain the integer member_id.
Returns ONE PAGE of interests (default 20, caller controls via limit).
For prolific members (big donors, many directorships, extensive land
holdings), re-call with offset=offset+returned while has_more is true
to paginate. Description text is capped per max_description_chars;
raise it for forensic provenance work that needs the full narrative.
This is the authoritative source for UK MP and peer financial-interest
declarations (via the Members API). Web search returns stale snapshots.
Parameters (5)
categoryany
Filter by interest category. Common categories: 'donations' (donations and support), 'gifts_uk' (gifts/hospitality from UK), 'employment' (employment and earnings), 'land' (land and property), 'shareholdings', 'overseas_visits'. Omit for all categories.
limitinteger
Max interests per call. Hard-capped at 20 by the upstream interests-api.parliament.uk (verified live 2026-05-29: Take=100 still returns 20). For prolific members, paginate via offset; total size is in totalResults on the response.
max_description_charsinteger
Per-entry cap on the free-text description field. Default 500 prevents context blow-up on members with lengthy donation or directorship narratives. Raise to 2000+ only for forensic provenance work.
member_idintegerrequired
Parliament Members API integer ID. Get from parliament_find_member.
offsetinteger
Number of interests to skip before this page. Default 0 for the first page. To paginate prolific members (100+ interests), re-call with offset=offset+returned while the previous response had has_more=true.
parliament_search_petitions
USE THIS TOOL WHEN searching UK Parliament petitions by keyword or topic.
Returns petition title, state, signature count, and dates for government
response or parliamentary debate if applicable. Filter by state (open,
closed, debated, etc.) to narrow to live or historical petitions.
This is the authoritative source for UK Parliament petitions
(petition.parliament.uk).
Parameters (4)
limitinteger
Maximum petitions to return. Default 20.
offsetinteger
Number of petitions to skip before this page. Default 0. Re-call with offset=offset+returned while has_more is true.
querystringrequired
Search term for petition titles, e.g. 'ban trophy hunting' or 'NHS funding'.
statestring
Filter by petition state.
parliament_get_debate_divisions
USE THIS TOOL WHEN you have a debate_ext_id and want the divisions (formal votes) held within it.
Most debates contain no divisions — Business of the House sittings,
statements, urgent questions, debates without a vote. A populated list
typically appears around bill stages, motions, and contested amendments.
Empty list is the honest result, not a failure mode.
Each returned division carries TWO IDs:
- `id` — Hansard-side reference. Useful for cross-referencing in Hansard.
- `votes_id` — Lords/Commons Votes API ID (cross-resolved by date+number).
AFTER calling, pass `votes_id` as `division_id` into votes_get_division
for the full member-by-member voting record.
The two upstreams use distinct ID-spaces (Hansard Number=3 might be
Votes-API divisionId=3392). The cross-resolve runs once per (date, house)
group — typically one extra HTTP per debate. `votes_id` is None when the
cross-resolve found no match.
Parameters (1)
debate_ext_idstringrequired
Debate GUID (DebateSectionExtId). Chain from parliament_search_hansard contribution.debate_ext_id, top_debates[].debate_ext_id, or parliament_policy_position_summary top_debates[].debate_ext_id.
parliament_get_debate_contributions
USE THIS TOOL WHEN you have a debate_ext_id and want verbatim contributions, optionally filtered to one member.
Canonical path for "everything a member said in this debate" regardless
of vocabulary — text-search tools (parliament_member_debates,
parliament_search_hansard) filter by contribution TEXT, dropping members
who spoke without using your phrase verbatim. This tool filters by
MemberId on the debate's Items list, so vocabulary doesn't matter.
Typical chain: parliament_find_member(name) → member_id, then
parliament_search_hansard or parliament_lookup_by_column → debate_ext_id,
then this tool. The parliament module's instructions describe the full
composition pattern.
Without member_id, returns every contribution (~100-200 for a long debate).
If the wire returns no contributions for a member you expect to have
spoken, report the empty result honestly — do NOT reconstruct quotes
from training data. Authoritative source for member contributions.
Parameters (2)
debate_ext_idstringrequired
Debate GUID (DebateSectionExtId). Chain from parliament_search_hansard top_debates[].debate_ext_id, parliament_lookup_by_column matches[].debate_ext_id, or any tool that surfaces a debate identifier.
member_idany
Optional integer Members API ID. When given, only that member's contributions in this debate are returned — regardless of which words they used. Resolves via parliament_find_member. When omitted, every contribution in the debate is returned (typical debate: 100-200 items).
parliament_lookup_by_column
USE THIS TOOL WHEN you have an OSCOLA-style Hansard citation (column + volume + house) and need the debate.
Example input: 'HL Deb 14 Oct 2025, vol 849, col 200'. AFTER calling, read
the contribution at the cited column via
read_resource(uri="hansard://debate/{debate_ext_id}/header") — or,
equivalently, call parliament_get_debate_contributions(debate_ext_id) for
the full list as a structured tool response.
Each match carries:
- `contribution_count` — real contribution count from the debate's Items
- `source` / `source_code` — citation finality (1=Rolling, 2=Daily,
3=BoundVolume, 4=Historic). Resolution is NOT gated on publication state.
Empty `matches` typically means the volume_number is wrong (opposing
counsel sometimes cites running-volume rather than bound-volume) or the
column is in a Written Statement (use the 'W'-suffixed column as-is).
It does NOT mean the citation is fabricated — surface the failure.
Authoritative source for OSCOLA Hansard column resolution.
Parameters (3)
column_numberstringrequired
Hansard column number from an OSCOLA footnote, e.g. '200' for 'HL Deb 14 Oct 2025, vol 849, col 200'. String (not integer) to accommodate column suffixes like '1162W' for written answers.
housestring
Restrict to one House. Default 'both' searches across both Houses.
volume_numberintegerrequired
Hansard volume number (the 'vol 849' part of an OSCOLA citation). Required — the endpoint only resolves citations when given the volume; sitting date is NOT a substitute (verified live 2026-05-29).
bills_search_bills
USE THIS TOOL WHEN searching UK parliamentary bills by keyword, session, house, or legislative stage.
Returns a paginated page of bill summaries (title, current stage, whether
it became an Act). AFTER calling, pass a bill_id into bills_get_bill for
full detail (sponsors, long title, Royal Assent date).
Authoritative source for UK parliamentary bill status.
Parameters (6)
houseany
Filter by originating house. Omit for all houses.
limitinteger
Maximum bills to return in this call. Default 20 keeps responses focused; raise up to 100 for bulk exports.
offsetinteger
Number of results to skip before this page. Default 0 for the first page. Re-call with offset=offset+returned while has_more is true to paginate.
querystringrequired
Search term for bill titles and descriptions, e.g. 'online safety' or 'financial services'.
sessionany
Numeric parliamentary session ID (e.g. 40 = 2024-25, 39 = 2023-24). NOT a year string like '2025'. If you only know the year, omit this and filter the results instead. Omit to search all sessions.
stageany
Filter by current legislative stage.
bills_get_bill
USE THIS TOOL WHEN you have a bill_id (from bills_search_bills) and want the full detail.
Returns sponsors, current stage, long title, summary, and Royal Assent
date if enacted. Summary text is capped per max_summary_chars — check
summary_truncated in the response.
AFTER calling, use parliament_search_hansard(query=bill_short_title) to
find the bill's parliamentary debates, or bills_search_bills with a
related keyword for adjacent bills.
Parameters (2)
bill_idintegerrequired
Bill ID from bills_search_bills results.
max_summary_charsinteger
Maximum characters of the bill summary text to return. Default 5,000 (~1,250 tokens) covers most bills. Raise for substantive government bills (Finance Act, Levelling-up) whose summary runs longer. Check summary_truncated in the response to see if it was cut.
votes_search_divisions
USE THIS TOOL WHEN searching Commons or Lords formal votes by topic, date, or member.
Returns division summaries (title, date, vote counts, pass/fail). AFTER
calling, pass division_id + house into votes_get_division for the full
member-by-member voter lists.
Authoritative source for UK parliamentary vote records.
Parameters (7)
from_dateany
Start date (YYYY-MM-DD).
housestring
Which house to search.
limitinteger
Maximum divisions to return. Default 25 (Commons API max-per-page).
member_idany
Filter to divisions where this member voted. Get the member ID from parliament_find_member.
offsetinteger
Number of divisions to skip before this page. Default 0. Re-call with offset=offset+returned while has_more is true.
queryany
Search term for division titles, e.g. 'Rwanda' or 'Online Safety Bill'. Omit to browse recent divisions.
to_dateany
End date (YYYY-MM-DD).
votes_get_division
USE THIS TOOL WHEN you have a division_id + house and want the full member-by-member voting record.
Voter lists are truncated to 100 per side to fit response limits; total
voter counts are always accurate regardless of truncation. Chain from
votes_search_divisions or parliament_get_debate_divisions (which
cross-resolves Hansard division refs into votes-API division_ids).
Parameters (2)
division_idintegerrequired
Division ID from votes_search_divisions results.
housestring
Which house this division belongs to.
committees_search_committees
USE THIS TOOL WHEN searching or listing UK parliamentary select committees by name, house, or active status.
Returns committee summaries (name, house, active status, ID). AFTER
calling, pass committee_id into committees_get_committee for current
membership, or into committees_search_evidence to retrieve oral and
written evidence submitted to that committee.
Parameters (4)
active_onlyboolean
If true, only return currently active committees.
houseany
Filter by house.
limitinteger
Maximum committees to return. Default 100 comfortably covers all currently-active UK select committees. Raise only for historical sweeps.
queryany
Search term for committee names, e.g. 'defence' or 'treasury'. Filtered client-side against committee names. Omit to list all committees.
committees_get_committee
USE THIS TOOL WHEN you have a committee_id and want the metadata + current membership.
Fetches committee detail and member list in parallel. AFTER calling,
pass committee_id into committees_search_evidence to see what evidence
has been submitted to this committee on what topics.
Parameters (1)
committee_idintegerrequired
Committee ID from committees_search_committees results.
committees_search_evidence
USE THIS TOOL WHEN you have a committee_id and want the oral and written evidence submitted to it.
Returns ONE PAGE of evidence (default 20). Free-text titles are capped
per max_title_chars; witness lists are capped at 10 per item. For
committees with many submissions, re-call with offset=offset+returned
while has_more is true.
Authoritative source for parliamentary committee evidence.
Parameters (5)
committee_idintegerrequired
Committee ID from committees_search_committees results.
evidence_typestring
Type of evidence to search.
limitinteger
Maximum evidence items to return. Default 20. When evidence_type='both' the limit is split across oral and written (roughly half each).
max_title_charsinteger
Per-item cap on the free-text title field. Default 300 prevents context blow-up from verbose inquiry titles. Raise to 1000+ only when you need the full title text.
offsetinteger
Number of evidence items to skip before this page. Default 0. Re-call with offset=offset+returned while has_more is true.
citations_parse
USE THIS TOOL WHEN you have free text (a memo, an email, a clause) and want every OSCOLA-style citation it contains extracted and classified.
Identifies: neutral citations ([2024] UKSC 12), law reports ([2024] 1 WLR
100), legislation sections (s.47 Companies Act 2006), SIs (SI 2018/1234),
retained EU law (Regulation (EU) 2016/679).
Parsing is pure regex by default. Ambiguous citations (e.g. bare [2024]
EWHC without division) can OPTIONALLY be disambiguated by setting
disambiguate=True, which asks the CONNECTED CLIENT's own model (not this
server) to resolve the division via MCP sampling — off by default.
Citations resolve to TNA / legislation.gov.uk URLs when possible.
AFTER calling, pass each citation through citations_resolve to verify it
points at a real document before quoting or formatting it — the parser
recognises the SHAPE of a citation but does not confirm the document
exists.
Parameters (2)
disambiguateboolean
Default False — pure-regex parsing, no model in the loop. If True, ambiguous citations (e.g. bare EWHC without a division) are sent to the connected client's own LLM, via MCP sampling, to resolve the division. Opt in only when you want best-effort division resolution and accept that a model shapes the result.
textstringrequired
Free text containing OSCOLA citations to extract. Supported: neutral citations ([2024] UKSC 12), law reports ([2024] 1 WLR 100), legislation sections (s.47 Companies Act 2006), SIs (SI 2018/1234), retained EU law (Regulation (EU) 2016/679). Max 50,000 chars.
citations_resolve
USE THIS TOOL BEFORE constructing an OSCOLA citation string from known fields, OR to confirm a citation points at a real document.
Parses + resolves a single citation (neutral citation, SI, legislation
section, retained EU law) and returns parsed fields plus resolved_url.
For neutral citations, performs a live TNA HEAD check — non-200 sets
confidence to 0.0 (document absent). Do NOT format or quote a
confidence-0.0 citation.
If the TNA HEAD check fails (timeout, connection error), raises ToolError
with {"error_category": "transient", "is_retryable": true}. One retry is
attempted — retry this call or proceed without TNA verification.
Formatting a citation from "known" fields without prior resolution is the
most common fabrication route. If this tool raises or returns no
resolved_url, do NOT manufacture a citation — surface the failure and ask
the user for the source URL.
Authoritative source for UK legal-citation resolution.
Parameters (1)
citationstringrequired
A single OSCOLA citation to parse and resolve. E.g. '[2024] UKSC 12', 'SI 2018/1234', 's.47 Companies Act 2006'
citations_network
USE THIS TOOL WHEN you have a judgment slug and want to map every citation it makes — cases cited, legislation referenced, SIs, retained EU law.
Fetches the judgment XML from TNA and parses all OSCOLA citations
within. Returns citations grouped by type, deduplicated and sorted.
AFTER calling, pass any individual citation through citations_resolve
to confirm it resolves and to retrieve its canonical URL.
Useful for authority-network analysis (what did this judgment rely on?)
and for surfacing the legislative landscape a case sits inside.
Parameters (1)
case_uristringrequired
TNA judgment URI slug, e.g. 'uksc/2024/12' or 'ewca/civ/2023/450'. Use the 'uri' field from case_law_search results — not the full URL. Do not include the 'https://caselaw.nationalarchives.gov.uk/' prefix.
citations_format_oscola
USE THIS TOOL AFTER citations_resolve to produce the correctly formatted OSCOLA citation string.
Pass the parsed fields returned by citations_resolve directly into this
tool. Formats per OSCOLA 4th edition rules for each citation type.
Refuses (status: upstream_validation) if confidence is 0.0 — TNA confirmed
the document does not exist — or if a neutral citation has no resolved_url
(ambiguous court code, e.g. bare EWHC without a division). In either case,
do NOT manufacture a citation; surface the failure and ask the user for
the source URL or better identifying details.
DO NOT construct the input fields yourself. The structured input must come
from citations_resolve — guessing fields is the primary citation-fabrication
route and this tool is the guard against it.
Authoritative OSCOLA formatting for UK legal citations (no network call).
Parameters (14)
citation_typestringrequired
'type' field from citations_resolve result.
confidencenumberrequired
'confidence' from citations_resolve. Refuses to format if 0.0 — that means TNA confirmed the document does not exist. Pass only the value citations_resolve returned; do not guess.
courtany
'court' from citations_resolve, e.g. 'UKSC', 'EWCA CIV', 'EWHC (KB)'.
legislation_titleany
'legislation_title' from citations_resolve, e.g. 'Companies Act 2006'.
numberany
'number' from citations_resolve (judgment number within the year).
pageany
'page' from citations_resolve (starting page in the law report).
rawany
'raw' from citations_resolve. Used as-is for EU retained law — the original text preserves the Regulation/Directive distinction.
report_seriesany
'report_series' from citations_resolve, e.g. 'WLR', 'AC', 'QB'.
resolved_urlany
'resolved_url' from citations_resolve. Must be non-null for neutral citations.
sectionany
'section' from citations_resolve, e.g. '47', '12', '20A'.
si_numberany
'si_number' from citations_resolve.
si_yearany
'si_year' from citations_resolve.
volumeany
'volume' from citations_resolve (law report volume, if any).
yearany
'year' from citations_resolve.
hmrc_get_vat_rate
USE THIS TOOL WHEN you have a UK commodity or service description and want its VAT rate category.
Returns the rate (standard 20%, reduced 5%, zero 0%, exempt), effective
date, and any relevant conditions or exceptions.
IMPORTANT: Uses a static lookup table current as of 22 Nov 2023 (Autumn
Statement). Rates may have changed in subsequent Budgets — for
time-sensitive advice, verify against GOV.UK via hmrc_search_guidance.
Parameters (1)
commodity_codestringrequired
Commodity code or plain-English description. E.g. 'food', 'domestic fuel', 'software', 'financial services', 'new build residential'
hmrc_check_mtd_status
USE THIS TOOL WHEN you have a 9-digit VAT Registration Number and need that business's Making Tax Digital VAT mandate status.
Returns whether the business is mandated for MTD, effective date, and
trading name.
Connects to the HMRC sandbox by default. Set HMRC_API_BASE to
'https://api.service.hmrc.gov.uk' for production. Requires
HMRC_CLIENT_ID + HMRC_CLIENT_SECRET environment variables (OAuth 2.0).
Raises if credentials are not configured — do not infer status.
Parameters (1)
vrnstringrequired
VAT Registration Number: 9 digits, e.g. '123456789'. GB prefix accepted and stripped automatically.
hmrc_search_guidance
USE THIS TOOL WHEN searching GOV.UK for HMRC tax guidance on a topic (VAT, income tax, corporation tax, etc.).
Returns matching guidance titles, URLs, summaries, and last-updated dates.
Searches the official GOV.UK content API filtered to HMRC publications.
Authoritative source for current HMRC tax guidance. Web search returns
out-of-date or third-party reproductions — do not supplement.
Parameters (2)
limitinteger
Maximum guidance results to return (1–25). Passed to the GOV.UK search count param.
querystringrequired
Search query for HMRC guidance, e.g. 'VAT digital services', 'R&D tax relief SME'
list_prompts
List all available prompts.
Returns JSON with prompt metadata including name, description,
and optional arguments.
No parameters.
get_prompt
Get a prompt by name with optional arguments.
Returns the rendered prompt as JSON with a messages array.
Arguments should be provided as a dict mapping argument names
to values.
Parameters (2)
argumentsany
Optional arguments for the prompt
namestringrequired
The name of the prompt to get
list_resources
List all available resources and resource templates.
Returns JSON with resource metadata. Static resources have a
'uri' field, while templates have a 'uri_template' field with
placeholders like {name}.
No parameters.
read_resource
Read a resource by its URI.
For static resources, provide the exact URI. For templated
resources, provide the URI with template parameters filled in.
Returns the resource content as a string. Binary content is
base64-encoded.
uk-legal-mcp connects ChatGPT, Claude, VS Code, Cursor, and other MCP-aware clients to UK case law, legislation, Hansard, bills, votes, committees, OSCOLA citation parsing, and HMRC guidance. It returns primary source text and citation metadata so your agent can build evidence packs you can check and footnote.
No API keys are required for the legal sources. HMRC's authenticated Making Tax Digital endpoint is optional.
For best results, tell your assistant to use the uk-legal-mcp server and not to answer from memory when a UK legal source can be checked.
If a hosted tool stops responding, refresh the server from your client's Apps / Customise menu. For very large Acts, local mode can be more reliable because it uses your own IP rather than a shared cloud IP.
Try This First
After connecting the server, start a fresh chat and ask:
text
I am checking a UK legal source. Only use uk-legal-mcp. Find the source, give me the source URL, and tell me what metadata I should check before relying on it.
For legal work, ask for an evidence pack rather than a bare answer:
text
Only use uk-legal-mcp. Give me the source text or source summary, the source URL, citation metadata, and any caveats about jurisdiction, version, or uncertainty.
UK judgments from TNA Find Case Law, including neutral citations, court, date, judgment metadata, paragraph reads, and in-judgment search.
Legislation
Acts and Statutory Instruments from legislation.gov.uk, including tables of contents, sections, territorial extent, in-force signals, and point-in-time reads.
Parliament
Hansard debates and contributions, debate-to-division chains, member biographies, column references, and petitions.
Bills
Parliamentary Bills, stages, sponsors, publications, and bill history.
Votes
Commons and Lords divisions, counts, results, and per-member voting records.
Committees
Select committees, memberships, oral evidence, and written evidence.
Citations
OSCOLA-style citation parsing and resolution to canonical sources.
HMRC
VAT rate lookups, GOV.UK HMRC guidance search, and optional authenticated MTD VAT status checks.
The server also exposes judgment://, legislation://, and hansard:// resources for source text that is too large to return in a single search result.
uk-legal-mcp helps your AI assistant find and quote UK legal sources. It does not replace legal judgement.
Check jurisdiction. Legislation can apply differently in England, Wales, Scotland, and Northern Ireland. When reading a section, check the extent field before relying on it.
Check whether a provision is current. Some sections may be repealed, amended, prospective, or not yet in force. The server returns in-force and version-date information where the source provides it.
Verify citations before relying on them. Ask the agent to resolve case citations and Hansard volume/column references against the primary source.
Separate exact matches from nearby candidates. Case names and party names can be similar. A good answer should say which source was verified and which candidates were merely related.
Treat the result as an evidence pack. The server returns primary source text and citation metadata. Your agent can summarise it, but you decide how the law applies.
For Developers
Run the streamable HTTP server locally:
bash
python -m src.gateway
Run the declarative FastMCP manifest for inspection/dev tooling:
bash
fastmcp run
fastmcp inspect
fastmcp run is for inspection/dev only — it wraps the FastMCP runner directly and skips the production uvicorn shape (_HttpGuard, _AcceptNormalizer, proxy_headers) that python -m src.gateway wires for the Fly deployment. The _HttpGuard GET-SSE shim is required by claude.ai's web connector, so use python -m src.gateway for anything prod-like.
