This server provides read-only access to UK legislation, case law, and government documents from three official sources: legislation.gov.uk, The National Archives' Find Case Law service, and GOV.UK. No API key is required, and every response includes a source_url and human_readable_citation for verifiable citations.
Legislation (legislation.gov.uk)
gb_search — Full-text search across Acts of Parliament, Statutory Instruments, and devolved instruments, filterable by document type (e.g. ukpga, uksi) and year.
gb_get_act — Fetch detailed metadata for a specific act or instrument by reference (e.g. ukpga/2018/12), including title, dates, extent, and status.
gb_get_text — Retrieve the full text of legislation in formats such as XML, HTML, Akoma Ntoso (AKN), RDF, PDF, or CSV.
gb_recent_legislation — List legislation published since a given date, newest-first, optionally filtered by document type.
Case Law (caselaw.nationalarchives.gov.uk)
gb_search_case_law — Search UK judgments by text, court/tribunal code (e.g. uksc, ewca/civ), and date range.
gb_get_case — Retrieve a specific judgment by neutral citation, Find Case Law URI/path, or opaque ID; returns Akoma Ntoso XML or a PDF fallback link.
GOV.UK Documents (gov.uk)
gb_search_govuk — Search across tribunal decisions, HMRC internal manuals, CMA cases, and more, with filters for document type, organisation, and date range.
gb_get_govuk_content — Fetch a specific GOV.UK document by path; tribunal decisions return a PDF link, HMRC manual sections return full body text.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@gb-eli-mcp Show me the Data Protection Act 2018"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server for legislation.gov.uk, The National Archives' official portal for United Kingdom legislation. It searches and retrieves Acts of Parliament, UK Statutory Instruments, and the equivalent instruments of the Scottish Parliament, Senedd Cymru/Welsh Parliament and Northern Ireland Assembly, with persistent identifiers and verifiable citations.
Part of the MateMatic eu-legal-mcp production line: the UK counterpart of the Polish
sejm-eli-mcp and the German de-eli-mcp, built on the same architecture and citation
contract against the UK's own source.
No native ELI. legislation.gov.uk does not publish a native
/eli/namespace (confirmed live:GET /eli/ukpga/2018/12returns 404), even though its own persistent-identifier scheme predates and is closely related to ELI - the UK is widely credited with pioneering the URI-based legislation-identifier concept that ELI later formalised EU-wide.eli_uritherefore carries the UK's own stable id URI (https://www.legislation.gov.uk/id/{type}/{year}/{number}) instead of a fabricated ELI path - the same disclosure pattern used by this factory'snl-eli-mcpandse-eli-mcp. SeeCONSTITUTION.mdArt. 4.Licence. Content is published under the Open Government Licence v3.0 (confirmed live from the site's own
/helppage), which permits copying, publishing and adapting with attribution. This connector only relays that public content, with asource_urlon every response.
Tool | What it does |
| Search legislation by text, doc type and year ( |
| Fetch act/instrument metadata by reference (e.g. |
| Fetch the full text ( |
| Legislation published since a date, newest-first, optionally by doc type. |
| Search UK judgments via The National Archives' Find Case Law Atom feed, by text, court, and date range. |
| Fetch a judgment by neutral citation, Find Case Law URI/path, or opaque id - returns Akoma Ntoso XML, or a PDF link fallback. |
| Search GOV.UK documents via the keyless Search API - employment/tax/property tribunal decisions, HMRC internal manuals, CMA cases - with server-side date filters and real totals. |
| Fetch one GOV.UK document via the Content API - tribunal decisions return the judgment PDF link, HMRC manual sections return the full text. |
| Declare what this connector covers, when each family was captured, and - explicitly - what it does NOT cover. Every gap carries a fallback. |
One upstream, many institutions: gb_search_govuk filters by document_type.
Live-verified totals (2026-07-07, from the Search API's own total/facet fields -
probe: https://www.gov.uk/api/search.json?count=0&facet_content_store_document_type=1000):
| Documents |
| 132,162 |
| 85,315 |
| 17,088 |
| 2,571 |
| 2,565 |
| 2,031 |
| 1,414 |
| 101 |
See SOURCES.md for the full per-source ledger, including what was scouted and
deliberately rejected (ICO, FCA, IAC) and why.
Every response carries the contract: eli_uri
(e.g. https://www.legislation.gov.uk/id/ukpga/2018/12), human_readable_citation
(e.g. Data Protection Act 2018 c. 12), and source_url. Case-law responses carry the
same-spirit contract (human_readable_citation, source_url, dataset_note) - see
CONSTITUTION.md Art. 5.
Related MCP server: UK Case Law MCP Server
cd gb-eli-mcp
pip install -e .Copy .mcp.json.example and adjust if needed:
{
"mcpServers": {
"gb-eli-mcp": { "command": "gb-eli-mcp" }
}
}Smart App Control blocks unsigned executables, which covers uvx.exe, pip.exe
and the gb-eli-mcp.exe launcher that pip writes at install time. The python.exe and
py.exe from the python.org installer are signed by the Python Software
Foundation, so running the module through the interpreter works:
python -m pip install gb-eli-mcp
python -m gb_eli_mcppip.exe is blocked for the same reason, so install with python -m pip, not
pip install. If python is not on PATH, use the Windows launcher: py -3 -m gb_eli_mcp.
{ "mcpServers": { "gb-eli-mcp": { "command": "python", "args": ["-m", "gb_eli_mcp"] } } }Do not turn Smart App Control off to work around this - it cannot be re-enabled without reinstalling Windows.
Environment:
GB_ELI_BASE_URL - default https://www.legislation.gov.uk
GB_ELI_CASELAW_BASE_URL - default https://caselaw.nationalarchives.gov.uk
GB_ELI_GOVUK_BASE_URL - default https://www.gov.uk
GB_ELI_CACHE_DIR - default ~/.matematic/cache/gb-eli
GB_ELI_AUDIT_DIR - default ~/.matematic/audit
No API key. legislation.gov.uk is keyless.
Public data only - read-only against legislation.gov.uk; no client data leaves the machine beyond search parameters.
Audit log - every tool call appends one JSON line to
~/.matematic/audit/gb-eli-mcp.jsonl.
Vendor-neutral - the server talks only to legislation.gov.uk and the local filesystem; no LLM provider, no telemetry.
Verifiable citations - every response is independently checkable via source_url.
See CONSTITUTION.md (the binding rules) and DISCOVERY.md (the live API probe).
pip install -e ".[dev]"
pytest tests/test_instructions_drift.py -v # offline
pytest tests/test_citations_case_law.py -v # offline
pytest tests/test_citations_govuk.py -v # offline
pytest tests/test_smoke.py -v # hits live legislation.gov.uk
pytest tests/test_smoke_case_law.py -v # hits live caselaw.nationalarchives.gov.uk
pytest tests/test_smoke_govuk.py -v # hits live www.gov.ukApache-2.0. (c) Matematic Solutions / Wieslaw Mazur.
Note: the code in this repository is Apache-2.0. The legislation content fetched at runtime from legislation.gov.uk remains Crown copyright, published under the Open Government Licence v3.0 - not relicensed by this project.
Declare what this connector covers, how it is sourced, and what it does NOT cover.
Call this before telling a user that the law "does not contain" something, and whenever a search comes back empty: the absence may be a gap in this connector rather than in the law. Every gap carries a fallback saying where to look instead.
Returns:
Coverage with families, an as-of note, and a non-empty list of known gaps.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| status | No | |
| families | No | |
| as_of_note | Yes | States what the dates mean, and what they do not promise. |
| known_gaps | No | Never empty. An empty list would mean 'not checked', not 'no gaps'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds meaningful behavioral context beyond the annotations: it reveals that the connector may be incomplete ('the absence may be a gap in this connector rather than in the law') and promises a fallback location for each gap. It also discloses sourcing and non-coverage limits. The annotations already establish read-only and open-world behavior, and the description complements them with actionable caveats.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded: core action, call conditions, gap/fallback logic, and return summary. Every sentence carries distinct information and none is fluff. The 'does NOT cover' caveat is placed early where it matters most.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With zero parameters and an existing output schema, the description adequately covers what the tool does, how data is sourced, what limitations exist, and what to expect in the return (families, as-of note, known gaps). The fallback guidance completes the operational picture for an agent. Nothing essential is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so there are no argument semantics to miscommunicate. Schema description coverage is 100% trivially, and the description makes clear no input is required. A baseline of 4 applies for 0-param tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with 'Declare what this connector covers, how it is sourced, and what it does NOT cover' – a specific verb and resource that clearly distinguishes it from sibling tools like gb_search or gb_get_act. It also states the exact call contexts: before claiming a law lacks something or when a search returns empty. This is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states trigger conditions: 'Call this before telling a user that the law "does not contain" something, and whenever a search comes back empty.' This provides clear context for when to invoke it. It does not name explicit exclusions or alternatives, but the tool is a unique meta-tool among siblings, making that gap minor.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch UK legislation metadata from legislation.gov.uk by reference.
| Name | Required | Description | Default |
|---|---|---|---|
| reference | Yes | a reference like ``"ukpga/2018/12"`` (Data Protection Act 2018), ``"uksi/2019/419"``, ``"asp/2015/1"``, or a full legislation.gov.uk URL. An optional point-in-time date suffix (``/2026-06-19``) selects a specific revised version. |
| Name | Required | Description |
|---|---|---|
| isbn | No | |
| year | Yes | |
| title | No | |
| number | Yes | |
| eli_uri | Yes | |
| doc_type | Yes | |
| made_date | No | |
| publisher | No | |
| source_url | Yes | |
| description | No | |
| dataset_note | No | |
| date_modified | No | |
| enactment_date | No | |
| document_status | No | |
| restrict_extent | No | |
| document_category | No | |
| document_main_type | No | |
| restrict_start_date | No | |
| human_readable_citation | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering the safety profile. The description adds that it fetches metadata from legislation.gov.uk by reference, but offers no additional behavioral context such as rate limits or response format. This is a minimal but non-contradictory addition, deserving a middle score.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single 11-word sentence that starts with the verb 'Fetch' and wastes no words. It is appropriately sized for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter tool with a detailed schema and informative annotations plus an output schema, the description is sufficient to understand the tool's purpose and invocation. It does not explicitly discuss alternative tools or edge cases, but these are covered in other dimensions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema's reference parameter is thoroughly described with example formats and optional date suffix, achieving 100% schema description coverage. The tool description's mention of 'by reference' adds no new meaning beyond this. Thus the baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Fetch UK legislation metadata from legislation.gov.uk by reference' uses a specific verb and resource, clearly identifying the tool's function. It distinguishes from siblings like gb_search and gb_get_text by emphasizing 'metadata' and 'by reference', though it doesn't explicitly name alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as gb_search or gb_get_text. It neither mentions exclusions nor suggests related tools for different needs, leaving the agent to infer usage from the tool's name and schema.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch a UK judgment from The National Archives' Find Case Law service.
| Name | Required | Description | Default |
|---|---|---|---|
| reference | Yes | a neutral citation (e.g. ``"[2026] EWHC 1698 (Admin)"``), a Find Case Law URI/path (e.g. ``"ewhc/admin/2026/1698"`` or a full ``caselaw.nationalarchives.gov.uk`` URL), or an opaque ``"d-{uuid}"`` id. Neutral citations resolve directly to a URI only for pre-April-2025 documents (``/{court}/{year}/{number}``); for later documents (opaque id), use `gb_search_case_law` first to find the ``uri``. |
| Name | Required | Description |
|---|---|---|
| date | No | |
| court | No | |
| title | No | |
| format | No | |
| content | No | |
| pdf_url | No | |
| byte_size | No | |
| source_url | Yes | |
| dataset_note | No | |
| neutral_citation | No | |
| human_readable_citation | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering safety and idempotency. Description adds the specific data source but does not elaborate on error handling, availability, or other behavioral details beyond what annotations convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The main description is a single, concise sentence with no wasted words. The overall definition is well-structured with the necessary schema and annotations, making it easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has a simple interface (1 parameter, no nested objects), the description combined with the output schema and annotations covers the essential aspects. However, it could mention what happens if the judgment is not found or confirm the output format explicitly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'reference' has a detailed schema description (100% coverage) that explains multiple input formats and provides a usage hint about pre/post April 2025 documents. This adds significant meaning beyond the parameter name and type.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Fetch' and resource 'a UK judgment' from a specific source 'The National Archives' Find Case Law service'. It distinguishes from sibling tools like gb_get_act and gb_get_govuk_content by targeting case law specifically.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Main description does not explicitly state when to use this tool vs alternatives. However, the parameter description hints that for newer documents with opaque ids, gb_search_case_law should be used first, providing indirect guidance. Lacks explicit when-to-use or when-not-to-use context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch one GOV.UK document (tribunal decision, HMRC manual section, CMA case).
Maps to the GOV.UK Content API (www.gov.uk/api/content/{path} - confirmed live
2026-07-07). Tribunal decisions carry the judgment as a PDF in attachments with
only a short HTML body; HMRC manual sections carry the full text in body_html.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | the document's site path - take it from a ``gb_search_govuk`` result's ``link`` field, e.g. ``"/employment-tribunal-decisions/mr-b-king-v-thales-dis-uk-ltd-1403603-slash-2020"`` or ``"/hmrc-internal-manuals/vat-government-and-public-bodies/vatgpb9700"``. A full ``www.gov.uk`` URL is also accepted. |
| Name | Required | Description |
|---|---|---|
| title | No | |
| base_path | No | |
| body_html | No | |
| byte_size | No | |
| source_url | Yes | |
| attachments | No | |
| description | No | |
| dataset_note | No | |
| document_type | No | |
| public_updated_at | No | |
| first_published_at | No | |
| human_readable_citation | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable context beyond these by explaining the API mapping, the confirmed live status, and content-specific differences (PDF attachments vs. body_html). It does not cover error handling or rate limits, but the annotation coverage lowers the bar.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and purpose-first, using three sentences to convey the function, API endpoint, and important content-type caveats. Every clause adds information; there is no filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having only one parameter, the description covers the key behavioral nuances (attachments vs. body_html) and references the output schema implicitly by noting where content appears. With a detailed schema, output schema, and strong annotations, this is a complete and self-sufficient tool description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description provides 100% coverage for the single 'path' parameter, including its source, format, and examples. The tool description itself adds no further parameter semantics, so with high schema coverage the baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Fetch') with a clear resource ('one GOV.UK document') and enumerates the covered content types (tribunal decision, HMRC manual section, CMA case). This distinguishes it from sibling tools like gb_get_act or gb_get_case by scope and source.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides clear context on when to use the tool (fetching a single GOV.UK document) and gives direction on obtaining the path from gb_search_govuk results. However, it does not explicitly name alternative tools or state when not to use it, so it falls short of full exclusion guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch the full text of UK legislation.
Uses legislation.gov.uk's content-negotiation path suffix (/data.{format}) -
xml (the site's own legislation.xsd schema), html, akn (Akoma Ntoso),
rdf, pdf, or csv.
| Name | Required | Description | Default |
|---|---|---|---|
| format | No | one of ``"xml"``, ``"html"``, ``"akn"``, ``"rdf"``, ``"pdf"``, ``"csv"``. | html |
| reference | Yes | reference of the act/instrument (work or point-in-time expression). |
| Name | Required | Description |
|---|---|---|
| format | Yes | |
| content | No | |
| eli_uri | Yes | |
| byte_size | No | |
| source_url | Yes | |
| dataset_note | No | |
| human_readable_citation | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint) already indicate safety. The description adds valuable context about the source (legislation.gov.uk) and format options, enhancing transparency beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose, no wasted words. Each sentence earns its place, explaining purpose and technical details efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple tool (2 params, output schema present, annotations thorough), the description covers the source, format options, and reference requirement. It omits return-value details, but output schema likely covers that.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description provides context about the content-negotiation path but does not add new parameter meaning beyond the schema definitions for 'reference' and 'format'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Fetch the full text of UK legislation' with a specific verb and resource. It distinguishes itself from siblings like gb_get_act and gb_get_case by focusing on text retrieval in multiple formats.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the mechanism (content-negotiation) but does not explicitly state when to use this tool versus alternatives like gb_get_act or gb_search. No when-not or exclusion criteria are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
UK legislation published since since_iso (ISO 8601 date), newest-first.
Maps to the Atom search feed sorted/filtered by publication year, optionally scoped
to one doc_type. legislation.gov.uk's public search feed does not support a
generic dateFrom filter across all types, so this tool filters the requested
year's feed by the published date client-side.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | max items to return (1..100). | |
| doc_type | No | restrict to one UK document-type code (e.g. ``"ukpga"``, ``"uksi"``). | |
| since_iso | Yes | a date in ISO 8601 (e.g. ``"2026-01-01"``). Only the year is used to select the feed to scan; items are then filtered to on/after this date. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and destructiveHint=false, but the description adds a valuable behavioral trait: it explains that the public feed does not support a generic dateFrom filter, so the tool fetches the yearly feed and filters client-side. This discloses a limitation and implementation nuance that an agent should know, going beyond the structured hints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, front-loaded with the main verb and resource. It includes necessary implementation details without fluff. Every sentence adds value: purpose, mapping to feed, and filtering rationale.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present and robust annotations, the description completes the picture by explaining the feed source, the client-side filtering rationale, and the optional scoping. This is adequate for an agent to select and invoke the tool correctly, including understanding the year-based limitation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the description adds meaningful semantics beyond the schema. It clarifies that 'since_iso' uses only the year to choose the feed and then filters to on/after the date, and that doc_type scopes the feed. This extra context helps the agent understand parameter behavior beyond the raw schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific action and resource: 'UK legislation published since since_iso (ISO 8601 date), newest-first.' This clearly identifies the tool as a date-filtered list of legislation, distinguishing it from siblings like gb_search which searches generally. The optional doc_type scoping further refines the purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context: this is for retrieving legislation by publication date, optionally restricted to a document type. It explains the underlying feed mechanism and client-side filtering, but it does not explicitly name alternatives or state when not to use it. This is strong context without explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search UK legislation on legislation.gov.uk.
Maps to the official Atom search feed (/all/data.feed or /{doc_type}/data.feed,
optionally with ?text=...&year=...&page=...). Each item gets eli_uri,
human_readable_citation, source_url (per Art. 4 CONSTITUTION).
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ``SearchQuery`` - text, doc_type (e.g. 'ukpga', 'uksi', 'asp'), year, page. |
| Name | Required | Description |
|---|---|---|
| items | No | |
| query_echo | No | |
| dataset_note | No | |
| total_estimate | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly, idempotent, openWorld, and non-destructive hints. The description adds useful behavioral context: it maps to the Atom feed endpoint, lists how query parameters are used, and specifies that each item includes eli_uri, human_readable_citation, and source_url. This goes beyond the annotations, though the 'per Art. 4 CONSTITUTION' is cryptic but not misleading.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences and front-loaded with the core purpose. The second sentence packs technical detail about mapping and return fields. However, 'per Art. 4 CONSTITUTION' is obscure and might distract, slightly reducing clarity. Overall, it is fairly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity, existing annotations, and presence of an output schema, the description provides adequate context. It fully explains the tool's scope and the source mapping. It does not elaborate on pagination or error behavior, but these are not critical given the annotations and output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with the query object already documented. The description mentions the Atom feed query parameters (?text=...&year=...&page=...), but this largely mirrors the schema. It adds minimal meaning beyond what the schema provides, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search UK legislation on legislation.gov.uk' — a specific verb, resource, and platform. It distinguishes from sibling search tools like gb_search_case_law and gb_search_govuk by explicitly focusing on legislation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The context of use is clear (searching UK legislation), but there are no explicit exclusions or alternative recommendations. The description doesn't mention when to use this tool instead of sibling search tools, so usage guidance is implied rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search UK case law on The National Archives' Find Case Law service.
Maps to the public Atom feed at caselaw.nationalarchives.gov.uk/atom.xml
(confirmed live 2026-07-06 - keyless, Open Justice Licence). A separate service from
legislation.gov.uk: different host, different Atom dialect (tna: namespace).
| Name | Required | Description | Default |
|---|---|---|---|
| court | No | court/tribunal code, e.g. ``"ewhc/admin"``, ``"ewca/civ"``, ``"uksc"``. Passed through to Find Case Law's own ``court`` query param. | |
| limit | No | max items to return (1..100). | |
| query | No | full-text search (matches judgment text in order, per upstream docs). | |
| to_date | No | ISO 8601 date (YYYY-MM-DD), inclusive. Same client-side caveat. | |
| from_date | No | ISO 8601 date (YYYY-MM-DD), inclusive. Find Case Law's public API has no documented server-side date-range filter, so this is applied client-side against each result's ``date`` field after fetching. |
| Name | Required | Description |
|---|---|---|
| items | No | |
| query_echo | No | |
| dataset_note | No | |
| total_estimate | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as true/false. The description adds value by confirming the service is live, keyless, and uses Open Justice Licence, and notes the Atom dialect ('tna:' namespace). No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (two sentences plus a mapping note), front-loaded with the main purpose, and contains no redundant information. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the number of parameters (all optional) and the presence of an output schema, the description provides sufficient context about the service and its caveats (client-side date filtering). It is mostly complete, though it does not explain default behavior when no filters are applied.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%. The description does not add new meaning beyond the schema; it only mentions the Atom feed mapping. Baseline 3 is appropriate since the schema already documents the parameters adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search UK case law' with a specific verb and resource. It distinguishes from siblings by noting it targets The National Archives' Find Case Law service and is separate from legislation.gov.uk.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides context about the service (keyless, Open Justice Licence) and how it differs from legislation.gov.uk, but does not explicitly specify when to use this tool versus alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search GOV.UK documents - tribunal decisions, HMRC manuals, CMA cases and more.
Maps to the GOV.UK Search API (www.gov.uk/api/search.json - confirmed live
2026-07-07: keyless, Open Government Licence v3.0). One upstream aggregating many
institutions; filter with document_type. Legally weighty types with live-verified
totals (2026-07-07): employment_tribunal_decision (132,162),
hmrc_manual_section (85,315), residential_property_tribunal_decision
(17,088), employment_appeal_tribunal_decision (2,571), cma_case (2,565),
utaac_decision (2,031), tax_tribunal_decision (1,414),
asylum_support_decision (101).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | max items to return (1..100). | |
| query | No | full-text search terms. | |
| start | No | result offset for pagination (0-based). | |
| to_date | No | ISO 8601 date (YYYY-MM-DD), inclusive. Same server-side filter. | |
| from_date | No | ISO 8601 date (YYYY-MM-DD), inclusive - passed server-side via ``filter_public_timestamp`` (unlike Find Case Law, GOV.UK supports this). | |
| organisation | No | GOV.UK organisation slug, e.g. ``"competition-and-markets-authority"``. | |
| document_type | No | GOV.UK ``content_store_document_type`` slug (see above). |
| Name | Required | Description |
|---|---|---|
| items | No | |
| total | Yes | |
| query_echo | No | |
| dataset_note | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly and idempotent annotations, the description discloses that the API is keyless, under the Open Government Licence v3.0, and confirmed live as of 2026-07-07. It also provides live-verified totals for legally weighty document types, adding concrete behavioral context about the upstream data source and filtering behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose, then adds useful API mapping and document type details. The long list of type counts is valuable but somewhat verbose, so it earns a strong score rather than a perfect one.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Annotations cover safety and idempotency, the schema covers all parameters, and an output schema exists, so the description only needs to add real-world context. It provides the exact endpoint, license, live verification date, and document type options, making it complete for agent selection and invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already documents all 7 parameters with descriptions (100% coverage). The main description adds a curated list of valid document_type slugs with raw counts, directly enriching the document_type parameter beyond the schema's "see above" note. Other parameters are not further elaborated, so it stays slightly above baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with "Search GOV.UK documents - tribunal decisions, HMRC manuals, CMA cases and more," specifying the verb and resource clearly. It distinguishes itself from siblings like gb_search_case_law by naming the GOV.UK API and listing concrete document types, making the tool's purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly implies when to use this tool by listing supported content types and noting it maps to the GOV.UK Search API. However, it does not explicitly state when not to use it or mention alternative tools like gb_search_case_law, so it provides context but no exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.5.3gb_coveragev0.4.3gb_get_actgb_get_govuk_contentgb_recent_legislationgb_searchgb_search_govukv0.4.2gb_get_actgb_get_govuk_contentgb_recent_legislationgb_searchgb_search_govukv0.3.0gb_get_actgb_get_casegb_get_govuk_contentgb_get_textgb_recent_legislationgb_searchgb_search_case_lawgb_search_govukTools are mostly separated by source and action: legislation search/retrieval vs case law search/retrieval vs GOV.UK content search/retrieval. Minor ambiguity exists between gb_search and the domain-qualified search tools, and between gb_get_act vs gb_get_text for obtaining full legislation text.
Names use lowercase snake_case with an gb_ prefix and mostly follow get_/object or search_domain. Deviations are minor: gb_search lacks a resource qualifier, and gb_recent_legislation/gb_coverage are noun-only rather than verb-first.
Nine tools is well-scoped for a read-only legal research connector spanning legislation, case law, GOV.UK documents, and coverage. Each tool has a clear role and none feel redundant.
Core workflows are covered: search and retrieve for each major source, plus recent legislation and a coverage mechanism. Minor gaps exist, such as no direct PDF attachment extraction for some GOV.UK tribunal decisions, but gb_coverage explicitly notes known gaps and fallbacks.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search UK Acts, Statutory Instruments, and legislation with full text retrieval
Resolve, search and verify legal citations against the official sources, with provenance.
UK legal research — case law, legislation, Hansard, bills, votes, committees, HMRC, citations
Official EUR-Lex, UK, US, and gazette search, metadata fetch, and change-only watches.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/matematicsolutions/gb-eli-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
