此 MCP 可以做什么
Provides searchable official EU regulation text with article and recital pinpoints, citation verification, obligation lookups, and private compliance workflows.
功能
工具
19
工具
connect
Connect, or sign in (step 1 of 2)
Connect. With no arguments: the keyless trial â no email, no key; returns trial_id for record_assessment / list_assessments and the private playbook tools. Call start_here next. With the user's email and the language you speak with them (e.g. 'en', 'de', 'lt'): sign in to a free account that keeps their assessments and playbooks across chats. Rekvira sends ONE email in that language with a Confirm link and a six-digit code, valid 15 minutes, and returns request_id. Tell the user to click Confirm; then IMMEDIATELY call connect_verify(request_id) â it waits for the click. Nothing is charged and no card is needed.
可访问外部资源
输入模式
{'type': 'object', 'title': 'connectArguments', 'properties': {'email': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Email', 'default': None, 'description': "Only to sign in: the user's email. Omit for the keyless trial"}, 'language': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Language', 'default': None, 'description': 'The language you speak with the user (en, de, lt, fr, es, pl); the email uses it'}}}
connect_verify
Sign in (step 2 of 2)
Finish signing in. Call it RIGHT AFTER connect(email) with the request_id and no code: it waits up to 45 s for the user to click Confirm in the email and returns as soon as they do (if it returns waiting, call it again â do not ask the user to report the click). If the user reads you the six-digit code, pass it as code. Pass the trial_id you already have and the keyless work moves into the account. Returns a rek_ key (shown once) and a `session` value to pass on later calls.
输入模式
{'type': 'object', 'title': 'connect_verifyArguments', 'properties': {'code': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Code', 'default': None, 'description': 'Only if the user reads you the six-digit code from the email'}, 'trial_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Trial Id', 'default': None, 'description': 'Optional trial_id from the keyless connect(): its work moves into the account'}, 'request_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Request Id', 'default': None, 'description': 'request_id returned by connect(email)'}}}
delete_workflow
Delete a private playbook
Delete one private workflow for this trial_id. It cannot delete a shipped playbook or a draft owned by another trial.
可能执行破坏性操作
幂等
输入模式
{'type': 'object', 'title': 'delete_workflowArguments', 'properties': {'session': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Session', 'default': None, 'description': 'The `session` value the sign-in returned. Pass it on every call in this conversation, so the sign-in survives however this client handles connections; omit it when the user connected with Sign in (OAuth) or a key.'}, 'trial_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Trial Id', 'default': None, 'description': 'trial_id returned by connect()'}, 'workflow_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Workflow Id', 'default': None, 'description': 'Id of your private workflow to delete'}}}
get_workflow
Open a playbook or job
Full step-by-step playbook for one workflow id from list_workflows. Follow the named tools (search_regulation, read_unit, verify_citation, â¦) rather than summarising the playbook.
只读
幂等
输入模式
{'type': 'object', 'title': 'get_workflowArguments', 'properties': {'id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Id', 'default': None, 'description': 'Alias for workflow_id'}, 'name': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Name', 'default': None, 'description': 'Alias for workflow_id'}, 'session': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Session', 'default': None, 'description': 'The `session` value the sign-in returned. Pass it on every call in this conversation, so the sign-in survives however this client handles connections; omit it when the user connected with Sign in (OAuth) or a key.'}, 'trial_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Trial Id', 'default': None, 'description': 'Optional trial_id from connect to read your private draft'}, 'workflow_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Workflow Id', 'default': None, 'description': 'Id from list_workflows, e.g. high-risk-triage'}}}
list_assessments
List my assessments
List this trial_id's recorded assessments, newest first. Pass the trial_id from connect(). Use when resuming a multi-week DPIA or applicability review. Never invent rows for another trial.
只读
幂等
输入模式
{'type': 'object', 'title': 'list_assessmentsArguments', 'properties': {'limit': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Limit', 'default': 50, 'description': 'Max rows (1â\x80\x93100, default 50)'}, 'session': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Session', 'default': None, 'description': 'The `session` value the sign-in returned. Pass it on every call in this conversation, so the sign-in survives however this client handles connections; omit it when the user connected with Sign in (OAuth) or a key.'}, 'trial_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Trial Id', 'default': None, 'description': 'trial_id returned by connect()'}, 'max_chars': {'anyOf': [{'type': 'integer'}, {'type': 'string'}, {'type': 'null'}], 'title': 'Max Chars', 'default': None, 'description': 'Cap on the response size in characters (default 8000)'}}}
list_regulations
List regulations
List regulations in the registry and whether corpus JSON is loaded. Then search_regulation, search_regulations, or list_workflows for a named process.
只读
幂等
输入模式
{'type': 'object', 'title': 'list_regulationsArguments', 'properties': {'limit': {'anyOf': [{'type': 'integer'}, {'type': 'string'}, {'type': 'null'}], 'title': 'Limit', 'default': None, 'description': 'Most rows to return (default 10 on searches, max 50)'}, 'max_chars': {'anyOf': [{'type': 'integer'}, {'type': 'string'}, {'type': 'null'}], 'title': 'Max Chars', 'default': None, 'description': 'Cap on the response size in characters (default 8000)'}}}
list_workflows
List playbooks and jobs
Playbook library for compliance-officer workflows â high-risk triage, DORA ICT review, cross-reg scans, vendor questionnaires. Read a playbook before improvising a process. Pass trial_id from connect to list your own private drafts beside the shipped library. Then call get_workflow with workflow_id from this list.
只读
幂等
输入模式
{'type': 'object', 'title': 'list_workflowsArguments', 'properties': {'limit': {'anyOf': [{'type': 'integer'}, {'type': 'string'}, {'type': 'null'}], 'title': 'Limit', 'default': None, 'description': 'Most rows to return (default 10 on searches, max 50)'}, 'session': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Session', 'default': None, 'description': 'The `session` value the sign-in returned. Pass it on every call in this conversation, so the sign-in survives however this client handles connections; omit it when the user connected with Sign in (OAuth) or a key.'}, 'trial_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Trial Id', 'default': None, 'description': 'Optional trial_id from connect for this client private drafts'}, 'max_chars': {'anyOf': [{'type': 'integer'}, {'type': 'string'}, {'type': 'null'}], 'title': 'Max Chars', 'default': None, 'description': 'Cap on the response size in characters (default 8000)'}}}
lookup_obligations
Look up obligations by role
Articles whose official title names a role as an obligation addressee (e.g. role='deployer', optional system_class='high-risk'). Heading index, not annotated metadata â then read_unit the article. role accepts the word a title uses (deployer, provider, importer, operator, authorised representative, controller, processor, joint controller, data subject, or supervisory authority on gdpr). notified body on eu-ai-act returns Arts 34/45. Read also_named (Arts 31 through 38) for related titles without 'obligation'. When result_count is 0, read also_named before concluding none match (e.g. Arts 22/54 on eu-ai-act authorised representative; Arts 63/94 on eu-ai-act operator; Arts 29/39 on eu-ai-act conformity assessment body; Arts 76/77/85 on eu-ai-act market surveillance authority; Art 100 on eu-ai-act union institution; Arts 53/55/88 on eu-ai-act GPAI provider / general-purpose AI provider / provider of general-purpose AI models; Arts 13/14/21/22 on cra manufacturer / manufacturer of products with digital elements; when also_named is empty read heading_note and use search_regulation; Arts 24/26/27/29/79 on gdpr controller; Arts 27/28/29/79 on gdpr processor; Art 26 on gdpr joint controller; Arts 12/13/14/15/34/80 on gdpr data subject; Arts 31/33/51/53/54/56/60/62/77/78 on gdpr supervisory authority; Art 32 on nis2 essential entity; Arts 3/33/34 on nis2 important entity; Arts 23/31 on dora provider; Art 31 on dora ict third-party service provider; on dora financial entity or operator also_named is empty â read heading_note and use search_regulation for body mentions (Arts 28/30 for ICT third-party context); Art 18 on cra authorised representative). Then read_unit each article â the index is not a complete duty set.
只读
幂等
输入模式
{'type': 'object', 'title': 'lookup_obligationsArguments', 'properties': {'role': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Role', 'default': None, 'description': 'Addressee in the article title, e.g. deployer'}, 'limit': {'anyOf': [{'type': 'integer'}, {'type': 'string'}, {'type': 'null'}], 'title': 'Limit', 'default': None, 'description': 'Most rows to return (default 10 on searches, max 50)'}, 'query': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Query', 'default': None, 'description': 'Alias for role when agents pass search-style query= instead of role='}, 'max_chars': {'anyOf': [{'type': 'integer'}, {'type': 'string'}, {'type': 'null'}], 'title': 'Max Chars', 'default': None, 'description': 'Cap on the response size in characters (default 8000)'}, 'regulation': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Regulation', 'default': None, 'description': 'Regulation id from list_regulations (required)'}, 'system_class': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'System Class', 'default': None, 'description': 'Optional class in the same title, e.g. high-risk'}}}
publish_workflow
Publish a private playbook
Mark one of this trial_id private playbooks ready or draft. Publishing is private state only; it never adds content to the shipped library or another trial.
输入模式
{'type': 'object', 'title': 'publish_workflowArguments', 'properties': {'session': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Session', 'default': None, 'description': 'The `session` value the sign-in returned. Pass it on every call in this conversation, so the sign-in survives however this client handles connections; omit it when the user connected with Sign in (OAuth) or a key.'}, 'trial_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Trial Id', 'default': None, 'description': 'trial_id returned by connect()'}, 'published': {'type': 'boolean', 'title': 'Published', 'default': True, 'description': 'true marks it ready in this trial; false returns it to draft'}, 'workflow_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Workflow Id', 'default': None, 'description': 'Id of your private workflow'}}}
read_unit
Read a provision
Read one citable unit by kind and number or label. Articles return aggregated paragraph text. Paragraphs repeat across articles â pass article= (e.g. 6 or '6') to disambiguate. number, label and article accept JSON numbers or strings. read_unit also takes a result row's pinpoint verbatim: pinpoint='Article 6(1)' resolves kind and number for you. Then verify_citation if checking someone else's pinpoint.
只读
幂等
输入模式
{'type': 'object', 'title': 'read_unitArguments', 'properties': {'cite': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Cite', 'default': None, 'description': 'Alias for pinpoint'}, 'kind': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Kind', 'default': None, 'description': 'recital | article | paragraph | annex | section'}, 'as_of': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'As Of', 'default': None, 'description': 'Optional date YYYY-MM-DD: answer with the wording in force on that date (default today). Amended provisions say which act gave them their wording'}, 'label': {'anyOf': [{'type': 'string'}, {'type': 'integer'}, {'type': 'number'}, {'type': 'null'}], 'title': 'Label', 'default': None, 'description': 'Exact label e.g. (47) or 1. (string or JSON number)'}, 'number': {'anyOf': [{'type': 'string'}, {'type': 'integer'}, {'type': 'number'}, {'type': 'null'}], 'title': 'Number', 'default': None, 'description': 'Unit number within kind (string or JSON number)'}, 'article': {'anyOf': [{'type': 'string'}, {'type': 'integer'}, {'type': 'number'}, {'type': 'null'}], 'title': 'Article', 'default': None, 'description': "Required for paragraphs: parent article number (e.g. 6 or '6')"}, 'citation': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Citation', 'default': None, 'description': 'Alias for pinpoint'}, 'pinpoint': {'anyOf': [{'type': 'string'}, {'type': 'integer'}, {'type': 'number'}, {'type': 'null'}], 'title': 'Pinpoint', 'default': None, 'description': "A pinpoint string from a result row, e.g. 'Article 6(1)' â\x80\x94 read instead of kind/number"}, 'regulation': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Regulation', 'default': None, 'description': 'Regulation id (required)'}}}
record_assessment
Record an assessment
Record one structured applicability verdict on a regulation pinpoint for this keyless trial_id (from connect). Verdicts: applicable | not_applicable | needs_review | deferred. Optional reason codes only â never free-text notes. Re-recording the same regulation+pinpoint overwrites. Assessments annotate; they never hide search or read results. Call after the officer states applicability.
输入模式
{'type': 'object', 'title': 'record_assessmentArguments', 'properties': {'reason': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Reason', 'default': None, 'description': 'Optional structured reason: wrong_entity_type | below_threshold | already_covered_elsewhere | awaiting_vendor_answer | confirmed_obligation | revisit_after_guidance'}, 'session': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Session', 'default': None, 'description': 'The `session` value the sign-in returned. Pass it on every call in this conversation, so the sign-in survives however this client handles connections; omit it when the user connected with Sign in (OAuth) or a key.'}, 'verdict': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Verdict', 'default': None, 'description': 'applicable | not_applicable | needs_review | deferred'}, 'pinpoint': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Pinpoint', 'default': None, 'description': 'Pinpoint string, e.g. Article 6(1)'}, 'trial_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Trial Id', 'default': None, 'description': 'trial_id returned by connect()'}, 'regulation': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Regulation', 'default': None, 'description': 'Regulation id, e.g. eu-ai-act'}}}
rekvira_account
Your account and plan
The signed-in account: action='status' (default: email, what is kept, keys), 'plan' (what the free beta includes: the keyless trial and the free account; nothing is charged), 'usage', 'keys' (list; never the key itself), 'revoke_key' with key_prefix, 'export' (everything held), 'delete' with confirm_email=<the account email> (mails a confirmation link; deletion happens on the click). Not signed in: says how to sign in, and 'plan' still shows what the free beta includes.
可能执行破坏性操作
输入模式
{'type': 'object', 'title': 'rekvira_accountArguments', 'properties': {'tier': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Tier', 'default': None, 'description': "With action='plan': not needed during the beta â\x80\x94 everything is free and there is no paid plan to choose"}, 'action': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Action', 'default': None, 'description': 'status | plan | usage | keys | revoke_key | export | delete'}, 'session': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Session', 'default': None, 'description': 'The `session` value the sign-in returned. Pass it on every call in this conversation, so the sign-in survives however this client handles connections; omit it when the user connected with Sign in (OAuth) or a key.'}, 'key_prefix': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Key Prefix', 'default': None, 'description': "With action='revoke_key': the key's prefix as action='keys' lists it (rek_xxxxxx)"}, 'confirm_email': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Confirm Email', 'default': None, 'description': "With action='delete': the account's email, typed back by the user"}}}
save_workflow
Save a private playbook
Save or update one private compliance playbook for this keyless trial. It stays inside this trial_id; call publish_workflow only to mark it ready here, never to share it with another user.
输入模式
{'type': 'object', 'title': 'save_workflowArguments', 'properties': {'body': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Body', 'default': None, 'description': 'The steps and tool calls for this private playbook'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Title', 'default': None, 'description': 'Plain title for this private playbook'}, 'session': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Session', 'default': None, 'description': 'The `session` value the sign-in returned. Pass it on every call in this conversation, so the sign-in survives however this client handles connections; omit it when the user connected with Sign in (OAuth) or a key.'}, 'summary': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Summary', 'default': None, 'description': 'One sentence saying when this private playbook is useful'}, 'trial_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Trial Id', 'default': None, 'description': 'trial_id returned by connect()'}, 'workflow_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Workflow Id', 'default': None, 'description': 'Lowercase id for this private workflow, e.g. vendor-ai-review'}}}
search_regulation
Search one regulation
Search held regulation text. Returns pinpoints and excerpts, not summaries. Requires regulation id (e.g. eu-ai-act) and query string. limit, detail (compact|full) and max_chars bound the response. Then read_unit on the best pinpoints; verify_citation if checking someone else's cite.
只读
幂等
输入模式
{'type': 'object', 'title': 'search_regulationArguments', 'properties': {'as_of': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'As Of', 'default': None, 'description': 'Optional date YYYY-MM-DD: answer with the wording in force on that date (default today). Amended provisions say which act gave them their wording'}, 'kinds': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Kinds', 'default': None, 'description': 'Optional filter: recital, article, paragraph, annex, section'}, 'limit': {'anyOf': [{'type': 'integer'}, {'type': 'string'}, {'type': 'null'}], 'title': 'Limit', 'default': None, 'description': 'Most rows to return (default 10 on searches, max 50)'}, 'query': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Query', 'default': None, 'description': 'Search terms in English (required)'}, 'detail': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Detail', 'default': None, 'description': 'compact (default: ~400-char excerpt around the match) | full (whole unit text)'}, 'max_chars': {'anyOf': [{'type': 'integer'}, {'type': 'string'}, {'type': 'null'}], 'title': 'Max Chars', 'default': None, 'description': 'Cap on the response size in characters (default 8000)'}, 'regulation': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Regulation', 'default': None, 'description': 'Regulation id from list_regulations (required)'}}}
search_regulations
Search all regulations
Search all loaded regulation modules in one call, ranked by relevance across them. Use when the question names more than one act or you do not know which act holds the answer. limit, detail (compact|full) and max_chars bound the response; per_regulation_min gives each act a share of the page. Each hit carries its regulation id â then read_unit per regulation.
只读
幂等
输入模式
{'type': 'object', 'title': 'search_regulationsArguments', 'properties': {'as_of': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'As Of', 'default': None, 'description': 'Optional date YYYY-MM-DD: answer with the wording in force on that date (default today). Amended provisions say which act gave them their wording'}, 'kinds': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Kinds', 'default': None, 'description': 'Optional filter: recital, article, paragraph, annex, section'}, 'limit': {'anyOf': [{'type': 'integer'}, {'type': 'string'}, {'type': 'null'}], 'title': 'Limit', 'default': None, 'description': 'Most rows to return (default 10 on searches, max 50)'}, 'query': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Query', 'default': None, 'description': 'Search terms in English (required)'}, 'detail': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Detail', 'default': None, 'description': 'compact (default: ~400-char excerpt around the match) | full (whole unit text)'}, 'max_chars': {'anyOf': [{'type': 'integer'}, {'type': 'string'}, {'type': 'null'}], 'title': 'Max Chars', 'default': None, 'description': 'Cap on the response size in characters (default 8000)'}, 'regulations': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Regulations', 'default': None, 'description': 'Optional subset of regulation ids; default = all loaded corpus'}, 'per_regulation_min': {'anyOf': [{'type': 'integer'}, {'type': 'string'}, {'type': 'null'}], 'title': 'Per Regulation Min', 'default': None, 'description': 'Optional: at least this many rows from each act with matches'}}}
start_here
Start here
Orientation for this corpus right now â which regulations are loaded, unit counts, data_as_of, what is not held, and first-call hints per module. Built from the loaded corpus at call time. Cheap: one call, no quota. Then list_regulations, search_regulation, or list_workflows.
只读
幂等
输入模式
{'type': 'object', 'title': 'start_hereArguments', 'properties': {}}
submit_feedback
Send feedback to the team
Send feedback about Rekvira to the team that builds it: a bug, a wrong answer, missing data, a missing feature, a workflow idea, or praise. Every item is read by a person.
When to offer it: an answer came back empty or wrong; the user corrected you or the result; a workflow was missing a step the user needed; the user repeats a manual step the service could do for them; the user says they need something the service does not do. Offer once, in one sentence; the user's task comes first.
Ask first. Show the user what you will send and send it only after they agree. Their own words, and any client, case, company or personal detail, go only with their explicit OK; then set confirmed=true. With authored_by='agent' you may report your own observation of the service (the tool, what you expected, what came back) without asking, as long as it holds none of the user's words or confidential content.
Fill kind and what (the task, and what went wrong or what is needed). For a wrong answer add expected and got. Add tool and query for context (the query only with the user's OK), severity, and contact_email only when the user wants a reply.
The reply carries a reference id. Tell the user it reached the team; do not promise a reply or a date.
可访问外部资源
输入模式
{'type': 'object', 'title': 'submit_feedbackArguments', 'properties': {'got': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Got', 'default': None, 'description': 'For a wrong answer: what came back instead'}, 'kind': {'enum': ['bug', 'wrong_answer', 'missing_data', 'missing_feature', 'workflow_idea', 'praise', 'other'], 'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Kind', 'default': None, 'description': 'One of: bug (something failed or errored), wrong_answer (an answer was returned but it was wrong or misleading), missing_data (a document, record or source the user expected is not covered), missing_feature (something the user needs that the service does not do), workflow_idea (a step, sequence or repeated manual task the service could handle), praise (something that worked well and should be kept), other (anything else)'}, 'tool': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Tool', 'default': None, 'description': 'The tool the feedback is about, if one (e.g. the tool that answered wrongly); several: comma-separated'}, 'what': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'What', 'default': None, 'description': 'The task and what went wrong or what is needed (3-2000 characters)'}, 'query': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Query', 'default': None, 'description': "The query or arguments that produced it; only with the user's OK"}, 'message': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Message', 'default': None, 'description': 'Older name for `what`, kept so earlier callers still work; prefer `what`'}, 'expected': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Expected', 'default': None, 'description': 'For a wrong answer: what the right answer or result would have been'}, 'severity': {'enum': ['low', 'normal', 'high', 'blocking'], 'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Severity', 'default': None, 'description': 'low | normal | high | blocking (blocking: the user cannot do their work)'}, 'confirmed': {'type': 'boolean', 'title': 'Confirmed', 'default': False, 'description': 'true once the user approved sending this; required for authored_by user or agent_drafted'}, 'authored_by': {'enum': ['user', 'agent_drafted', 'agent'], 'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Authored By', 'default': None, 'description': 'user (their words) | agent_drafted (you wrote it, they approved) | agent (your own observation)'}, 'contact_email': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Contact Email', 'default': None, 'description': 'Only if the user wants a reply: the address to reply to'}}}
verify_citation
Verify a citation
Verify a citation someone else produced â does the pinpoint exist in held text, and optionally does the quote appear. Pass the cite as written (e.g. 'Article 6(1) EU AI Act') plus optional quote=. Then read_unit for full text. regulation= disambiguates when the cite omits the act name; returns regulation_mismatch when the cite embeds YYYY/NNNN for a different act.
只读
幂等
输入模式
{'type': 'object', 'title': 'verify_citationArguments', 'properties': {'cite': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Cite', 'default': None, 'description': 'Alias for citation when agents pass cite= instead of citation='}, 'as_of': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'As Of', 'default': None, 'description': 'Optional date YYYY-MM-DD: answer with the wording in force on that date (default today). Amended provisions say which act gave them their wording'}, 'quote': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Quote', 'default': None, 'description': 'Optional sentence to check against held text'}, 'citation': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Citation', 'default': None, 'description': 'Citation as written, e.g. Article 6(1) EU AI Act'}, 'regulation': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Regulation', 'default': None, 'description': 'Regulation id when the cite string alone is ambiguous'}}}
whoami
Who am I
Who is calling: tier, trial state, corpus load count. Pass trial_id from connect() to confirm the handle used for assessments and private workflows. After connect, call start_here or list_regulations.
只读
幂等
输入模式
{'type': 'object', 'title': 'whoamiArguments', 'properties': {'session': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Session', 'default': None, 'description': 'The `session` value the sign-in returned. Pass it on every call in this conversation, so the sign-in survives however this client handles connections; omit it when the user connected with Sign in (OAuth) or a key.'}, 'trial_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Trial Id', 'default': None, 'description': 'Optional trial_id from connect() â\x80\x94 echoed when present'}}}
历史
近期工具变更
已更改
submit_feedback
2026年9月30日 02:41
已更改
rekvira_account
2026年9月28日 02:41
已更改
delete_workflow
2026年9月26日 02:40
已更改
publish_workflow
2026年9月26日 02:40
已更改
save_workflow
2026年9月26日 02:40
已更改
get_workflow
2026年9月26日 02:40
已更改
list_workflows
2026年9月26日 02:40
已更改
read_unit
2026年9月26日 02:40
已更改
verify_citation
2026年9月26日 02:40
已更改
lookup_obligations
2026年9月26日 02:40
已更改
search_regulations
2026年9月26日 02:40
已更改
search_regulation
2026年9月26日 02:40
已更改
list_regulations
2026年9月26日 02:40
已更改
submit_feedback
2026年9月26日 02:40
已更改
list_assessments
2026年9月26日 02:40
已更改
record_assessment
2026年9月26日 02:40
已更改
whoami
2026年9月26日 02:40
已更改
start_here
2026年9月26日 02:40
已添加
rekvira_account
2026年9月26日 02:40
已添加
connect_verify
2026年9月26日 02:40
已更改
connect
2026年9月26日 02:40
已添加
delete_workflow
2026年9月24日 02:40
已添加
publish_workflow
2026年9月24日 02:40
已添加
save_workflow
2026年9月24日 02:40
已添加
get_workflow
2026年9月24日 02:40
已添加
list_workflows
2026年9月24日 02:40
已添加
read_unit
2026年9月24日 02:40
已添加
verify_citation
2026年9月24日 02:40
已添加
lookup_obligations
2026年9月24日 02:40
已添加
search_regulations
2026年9月24日 02:40
发现
类似的 MCP 服务器
BNM Data Shop
io.github.bnmbnmai/bnm-data-shop
Sells access to cached official reports, enforcement orders, regulatory documents, inspection records, and other public-source te…
OpenHelvetia Gateway
swiss.openhelvetia/gateway
Provides sourced access to Swiss federal legislation and political data, including law metadata, versions, amendments, citations,…
Court Listener
io.github.pipeworx-io/court-listener
Searches and retrieves US court opinions, case citations, federal docket filings, and related legal documents.
Gov Uk Content
io.github.pipeworx-io/gov-uk-content
Searches and retrieves GOV.UK content, government organisations, and HMRC manuals, sections, and revision histories.
Eur Lex
io.github.pipeworx-io/eur-lex
Searches and retrieves EU legislation and CJEU judgments with article-level text, metadata, CELEX identifiers, and citations.
Openparliament Ca
io.github.pipeworx-io/openparliament-ca
Provides searchable Canadian Parliament data on bills, politicians, committees, meetings, and recorded votes.
Govinfo
io.github.pipeworx-io/govinfo
Searches and retrieves metadata and document content from US government publications, including bills, regulations, court materia…
Dailymed
io.github.pipeworx-io/dailymed
Retrieves FDA DailyMed structured drug labels, label histories and diffs, drug classes, recent updates, and label references by d…