Server definition

Hash: sha256:e29b3f8f6374765f5d472feacf3994f7e47e1b2fc5ed3abf7f6b0195e78cf407
What it is: What a remote MCP server returned when asked what it offers: 19 tools

The blob, as servednamed by its sha256

{
  "instructions": "Rekvira gives compliance officers and counsel the official text of EU regulations\nwith pinpoints — article, paragraph, recital, annex — and `data_as_of` on every answer.\nEnglish-first; every tool takes a `regulation` id from the registry (eu-ai-act, dora, …).\n\nSEARCH IN ENGLISH. The EUR-Lex corpus is English consolidated text. Use the words a\ncompliance officer would type: high-risk AI system, GPAI, conformity assessment, ICT risk.\n\nTALK IN THE USER'S LANGUAGE. Explain, ask and write the work product in the language the\nuser writes in. Quote the official text in English exactly as the tools return it, and put\nany translation beside it marked as your own, unofficial rendering. Every EU act is\npublished in all official EU languages: when the user needs a quote they can cite in their\nown language, give the pinpoint and point them to that language version on EUR-Lex rather\nthan presenting your translation as the law.\n\n\nTOOLS (no account and no key needed to look things up)\n\n* `list_regulations` — which regulations are in the registry and which have corpus loaded\n* `search_regulation` — full-text search over one regulation; returns pinpoints, not summaries\n* `search_regulations` — same search across every loaded module when the question spans acts\n  (e.g. DORA and the AI Act). Hits are ranked by relevance across all modules;\n  `per_regulation_min` guarantees each act a share. Each hit names its regulation id for `read_unit`\n* Every search/list tool takes `limit`, `detail` (compact excerpt | full text) and `max_chars`;\n  a response cut to fit carries `truncated` with how to get the rest\n* `lookup_obligations` — articles whose EUR-Lex title names a role (and optional system\n  class). Heading index, not a complete duty list — then `read_unit` the article\n* `read_unit` — one unit by kind + number/label; articles return full text; paragraphs need\n  article=. number/label/article accept JSON numbers (6) or strings (\"6\") — agents often emit\n  numbers. It also takes a result row's pinpoint verbatim: pinpoint='Article 6(1)'\n* `verify_citation` — check a pinpoint someone else produced (model, memo, vendor doc):\n  does it exist in held text, and optionally does a quote match? Then `read_unit` for full text\n* `whoami` — tier, whether this call is signed in, and the trial handle\n* Jobs — `start_here` and `list_workflows` list them first: a job chains playbooks into one\n  work product (classification memo, DORA contract review, questionnaire answers, NIS2\n  scoping memo). Start one with `get_workflow(workflow_id='job-<id>')` or the prompt job-<id>\n* `list_workflows` / `get_workflow` — shipped playbooks; pass the `trial_id` from `connect`\n  to also list or read this client's own private drafts\n* `save_workflow` / `publish_workflow` / `delete_workflow` — write, mark ready, or remove a\n  private trial playbook. Publishing never shares it outside that trial\n\nACCOUNT (optional — the free account keeps assessments and private playbooks across chats)\n\n* Speak to the user in THEIR language at every step; the tools return machine states to explain.\n* Offer an account only when the user wants to keep something; never to look something up.\n* `connect(email, language)` sends ONE email in that language with a Confirm link and a six-digit\n  code. Tell the user to click Confirm, then IMMEDIATELY call `connect_verify(request_id)` with no\n  code: it waits for the click, so the user never has to come back and say they clicked. Pass the\n  `trial_id` they already have to `connect_verify` and their keyless work moves into the account.\n* The result carries `session`: pass session=<that value> on every later call in the conversation\n  that keeps things (assessments, playbooks, `rekvira_account`). Clients with \"Sign in\" (OAuth) or\n  a key need no session value.\n* `rekvira_account` — the account (everything is free during the beta: no paid plan, nothing\n  charged), usage, keys (list, revoke), export and deletion.\n\n\nTWO RULES THAT ARE NOT OPTIONAL\n\n1. REPEAT THE PINPOINT. Every result names an article, paragraph, recital or annex. Pass it\n   on. A compliance officer cannot use a proposition they cannot verify against the official\n   text.\n\n2. SAY THE DATE. Every response carries `data_as_of` — when the EUR-Lex source was fetched.\n   If it is not recent for the user's question, say so before the answer.\n\nWHAT THIS SERVICE WILL NOT DO\n\nRekvira is not a lawyer and does not give legal advice. It retrieves official sources and\npinpoints; interpreting what they mean for a specific deployment, predicting enforcement\noutcomes, or saying what to do next is the professional's job.\n\nWhen a user asks whether they are compliant, what the law means for their facts, or what\nthey should do, do not answer as though you know. Call the tools, repeat the pinpoints,\nand say plainly that you are not giving legal advice. A list of governing provisions is not\na compliance conclusion.\n\nDo not state a conclusion the sources do not say on their own. Summarise what each\nprovision says, with a pinpoint on every proposition, and let the professional conclude.\n\n\nCorpus loaded:\n  • eu-ai-act (32024R1689): 1148 units, fetched 2026-09-24T19:05:04+00:00\n  • dora (32022R2554): 572 units, fetched 2026-09-24T19:05:04+00:00\n  • gdpr (32016R0679): 769 units, fetched 2026-09-24T19:05:05+00:00\n  • nis2 (32022L2555): 489 units, fetched 2026-09-24T19:05:05+00:00\n  • cra (32024R2847): 689 units, fetched 2026-09-24T19:05:05+00:00",
  "tools": [
    {
      "description": "Connect. With no arguments: the keyless trial — 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) — it waits for the click. Nothing is charged and no card is needed.",
      "inputSchema": {
        "properties": {
          "email": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Only to sign in: the user's email. Omit for the keyless trial",
            "title": "Email"
          },
          "language": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "The language you speak with the user (en, de, lt, fr, es, pl); the email uses it",
            "title": "Language"
          }
        },
        "title": "connectArguments",
        "type": "object"
      },
      "name": "connect",
      "outputSchema": null
    },
    {
      "description": "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 — 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.",
      "inputSchema": {
        "properties": {
          "code": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Only if the user reads you the six-digit code from the email",
            "title": "Code"
          },
          "request_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "request_id returned by connect(email)",
            "title": "Request Id"
          },
          "trial_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Optional trial_id from the keyless connect(): its work moves into the account",
            "title": "Trial Id"
          }
        },
        "title": "connect_verifyArguments",
        "type": "object"
      },
      "name": "connect_verify",
      "outputSchema": null
    },
    {
      "description": "Delete one private workflow for this trial_id. It cannot delete a shipped playbook or a draft owned by another trial.",
      "inputSchema": {
        "properties": {
          "session": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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.",
            "title": "Session"
          },
          "trial_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "trial_id returned by connect()",
            "title": "Trial Id"
          },
          "workflow_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Id of your private workflow to delete",
            "title": "Workflow Id"
          }
        },
        "title": "delete_workflowArguments",
        "type": "object"
      },
      "name": "delete_workflow",
      "outputSchema": null
    },
    {
      "description": "Full step-by-step playbook for one workflow id from list_workflows. Follow the named tools (search_regulation, read_unit, verify_citation, …) rather than summarising the playbook.",
      "inputSchema": {
        "properties": {
          "id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Alias for workflow_id",
            "title": "Id"
          },
          "name": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Alias for workflow_id",
            "title": "Name"
          },
          "session": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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.",
            "title": "Session"
          },
          "trial_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Optional trial_id from connect to read your private draft",
            "title": "Trial Id"
          },
          "workflow_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Id from list_workflows, e.g. high-risk-triage",
            "title": "Workflow Id"
          }
        },
        "title": "get_workflowArguments",
        "type": "object"
      },
      "name": "get_workflow",
      "outputSchema": null
    },
    {
      "description": "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.",
      "inputSchema": {
        "properties": {
          "limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "default": 50,
            "description": "Max rows (1–100, default 50)",
            "title": "Limit"
          },
          "max_chars": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Cap on the response size in characters (default 8000)",
            "title": "Max Chars"
          },
          "session": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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.",
            "title": "Session"
          },
          "trial_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "trial_id returned by connect()",
            "title": "Trial Id"
          }
        },
        "title": "list_assessmentsArguments",
        "type": "object"
      },
      "name": "list_assessments",
      "outputSchema": null
    },
    {
      "description": "List regulations in the registry and whether corpus JSON is loaded. Then search_regulation, search_regulations, or list_workflows for a named process.",
      "inputSchema": {
        "properties": {
          "limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Most rows to return (default 10 on searches, max 50)",
            "title": "Limit"
          },
          "max_chars": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Cap on the response size in characters (default 8000)",
            "title": "Max Chars"
          }
        },
        "title": "list_regulationsArguments",
        "type": "object"
      },
      "name": "list_regulations",
      "outputSchema": null
    },
    {
      "description": "Playbook library for compliance-officer workflows — 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.",
      "inputSchema": {
        "properties": {
          "limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Most rows to return (default 10 on searches, max 50)",
            "title": "Limit"
          },
          "max_chars": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Cap on the response size in characters (default 8000)",
            "title": "Max Chars"
          },
          "session": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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.",
            "title": "Session"
          },
          "trial_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Optional trial_id from connect for this client private drafts",
            "title": "Trial Id"
          }
        },
        "title": "list_workflowsArguments",
        "type": "object"
      },
      "name": "list_workflows",
      "outputSchema": null
    },
    {
      "description": "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 — 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 — 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 — the index is not a complete duty set.",
      "inputSchema": {
        "properties": {
          "limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Most rows to return (default 10 on searches, max 50)",
            "title": "Limit"
          },
          "max_chars": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Cap on the response size in characters (default 8000)",
            "title": "Max Chars"
          },
          "query": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Alias for role when agents pass search-style query= instead of role=",
            "title": "Query"
          },
          "regulation": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Regulation id from list_regulations (required)",
            "title": "Regulation"
          },
          "role": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Addressee in the article title, e.g. deployer",
            "title": "Role"
          },
          "system_class": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Optional class in the same title, e.g. high-risk",
            "title": "System Class"
          }
        },
        "title": "lookup_obligationsArguments",
        "type": "object"
      },
      "name": "lookup_obligations",
      "outputSchema": null
    },
    {
      "description": "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.",
      "inputSchema": {
        "properties": {
          "published": {
            "default": true,
            "description": "true marks it ready in this trial; false returns it to draft",
            "title": "Published",
            "type": "boolean"
          },
          "session": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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.",
            "title": "Session"
          },
          "trial_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "trial_id returned by connect()",
            "title": "Trial Id"
          },
          "workflow_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Id of your private workflow",
            "title": "Workflow Id"
          }
        },
        "title": "publish_workflowArguments",
        "type": "object"
      },
      "name": "publish_workflow",
      "outputSchema": null
    },
    {
      "description": "Read one citable unit by kind and number or label. Articles return aggregated paragraph text. Paragraphs repeat across articles — 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.",
      "inputSchema": {
        "properties": {
          "article": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "integer"
              },
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Required for paragraphs: parent article number (e.g. 6 or '6')",
            "title": "Article"
          },
          "as_of": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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",
            "title": "As Of"
          },
          "citation": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Alias for pinpoint",
            "title": "Citation"
          },
          "cite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Alias for pinpoint",
            "title": "Cite"
          },
          "kind": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "recital | article | paragraph | annex | section",
            "title": "Kind"
          },
          "label": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "integer"
              },
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Exact label e.g. (47) or 1. (string or JSON number)",
            "title": "Label"
          },
          "number": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "integer"
              },
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Unit number within kind (string or JSON number)",
            "title": "Number"
          },
          "pinpoint": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "integer"
              },
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "A pinpoint string from a result row, e.g. 'Article 6(1)' — read instead of kind/number",
            "title": "Pinpoint"
          },
          "regulation": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Regulation id (required)",
            "title": "Regulation"
          }
        },
        "title": "read_unitArguments",
        "type": "object"
      },
      "name": "read_unit",
      "outputSchema": null
    },
    {
      "description": "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 — 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.",
      "inputSchema": {
        "properties": {
          "pinpoint": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Pinpoint string, e.g. Article 6(1)",
            "title": "Pinpoint"
          },
          "reason": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Optional structured reason: wrong_entity_type | below_threshold | already_covered_elsewhere | awaiting_vendor_answer | confirmed_obligation | revisit_after_guidance",
            "title": "Reason"
          },
          "regulation": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Regulation id, e.g. eu-ai-act",
            "title": "Regulation"
          },
          "session": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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.",
            "title": "Session"
          },
          "trial_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "trial_id returned by connect()",
            "title": "Trial Id"
          },
          "verdict": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "applicable | not_applicable | needs_review | deferred",
            "title": "Verdict"
          }
        },
        "title": "record_assessmentArguments",
        "type": "object"
      },
      "name": "record_assessment",
      "outputSchema": null
    },
    {
      "description": "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.",
      "inputSchema": {
        "properties": {
          "action": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "status | plan | usage | keys | revoke_key | export | delete",
            "title": "Action"
          },
          "confirm_email": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "With action='delete': the account's email, typed back by the user",
            "title": "Confirm Email"
          },
          "key_prefix": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "With action='revoke_key': the key's prefix as action='keys' lists it (rek_xxxxxx)",
            "title": "Key Prefix"
          },
          "session": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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.",
            "title": "Session"
          },
          "tier": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "With action='plan': not needed during the beta — everything is free and there is no paid plan to choose",
            "title": "Tier"
          }
        },
        "title": "rekvira_accountArguments",
        "type": "object"
      },
      "name": "rekvira_account",
      "outputSchema": null
    },
    {
      "description": "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.",
      "inputSchema": {
        "properties": {
          "body": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "The steps and tool calls for this private playbook",
            "title": "Body"
          },
          "session": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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.",
            "title": "Session"
          },
          "summary": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "One sentence saying when this private playbook is useful",
            "title": "Summary"
          },
          "title": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Plain title for this private playbook",
            "title": "Title"
          },
          "trial_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "trial_id returned by connect()",
            "title": "Trial Id"
          },
          "workflow_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Lowercase id for this private workflow, e.g. vendor-ai-review",
            "title": "Workflow Id"
          }
        },
        "title": "save_workflowArguments",
        "type": "object"
      },
      "name": "save_workflow",
      "outputSchema": null
    },
    {
      "description": "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.",
      "inputSchema": {
        "properties": {
          "as_of": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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",
            "title": "As Of"
          },
          "detail": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "compact (default: ~400-char excerpt around the match) | full (whole unit text)",
            "title": "Detail"
          },
          "kinds": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Optional filter: recital, article, paragraph, annex, section",
            "title": "Kinds"
          },
          "limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Most rows to return (default 10 on searches, max 50)",
            "title": "Limit"
          },
          "max_chars": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Cap on the response size in characters (default 8000)",
            "title": "Max Chars"
          },
          "query": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Search terms in English (required)",
            "title": "Query"
          },
          "regulation": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Regulation id from list_regulations (required)",
            "title": "Regulation"
          }
        },
        "title": "search_regulationArguments",
        "type": "object"
      },
      "name": "search_regulation",
      "outputSchema": null
    },
    {
      "description": "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 — then read_unit per regulation.",
      "inputSchema": {
        "properties": {
          "as_of": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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",
            "title": "As Of"
          },
          "detail": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "compact (default: ~400-char excerpt around the match) | full (whole unit text)",
            "title": "Detail"
          },
          "kinds": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Optional filter: recital, article, paragraph, annex, section",
            "title": "Kinds"
          },
          "limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Most rows to return (default 10 on searches, max 50)",
            "title": "Limit"
          },
          "max_chars": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Cap on the response size in characters (default 8000)",
            "title": "Max Chars"
          },
          "per_regulation_min": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Optional: at least this many rows from each act with matches",
            "title": "Per Regulation Min"
          },
          "query": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Search terms in English (required)",
            "title": "Query"
          },
          "regulations": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Optional subset of regulation ids; default = all loaded corpus",
            "title": "Regulations"
          }
        },
        "title": "search_regulationsArguments",
        "type": "object"
      },
      "name": "search_regulations",
      "outputSchema": null
    },
    {
      "description": "Orientation for this corpus right now — 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.",
      "inputSchema": {
        "properties": {},
        "title": "start_hereArguments",
        "type": "object"
      },
      "name": "start_here",
      "outputSchema": null
    },
    {
      "description": "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.\nWhen 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.\nAsk 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.\nFill 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.\nThe reply carries a reference id. Tell the user it reached the team; do not promise a reply or a date.",
      "inputSchema": {
        "properties": {
          "authored_by": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "user (their words) | agent_drafted (you wrote it, they approved) | agent (your own observation)",
            "enum": [
              "user",
              "agent_drafted",
              "agent"
            ],
            "title": "Authored By"
          },
          "confirmed": {
            "default": false,
            "description": "true once the user approved sending this; required for authored_by user or agent_drafted",
            "title": "Confirmed",
            "type": "boolean"
          },
          "contact_email": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Only if the user wants a reply: the address to reply to",
            "title": "Contact Email"
          },
          "expected": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "For a wrong answer: what the right answer or result would have been",
            "title": "Expected"
          },
          "got": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "For a wrong answer: what came back instead",
            "title": "Got"
          },
          "kind": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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)",
            "enum": [
              "bug",
              "wrong_answer",
              "missing_data",
              "missing_feature",
              "workflow_idea",
              "praise",
              "other"
            ],
            "title": "Kind"
          },
          "message": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Older name for `what`, kept so earlier callers still work; prefer `what`",
            "title": "Message"
          },
          "query": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "The query or arguments that produced it; only with the user's OK",
            "title": "Query"
          },
          "severity": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "low | normal | high | blocking (blocking: the user cannot do their work)",
            "enum": [
              "low",
              "normal",
              "high",
              "blocking"
            ],
            "title": "Severity"
          },
          "tool": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "The tool the feedback is about, if one (e.g. the tool that answered wrongly); several: comma-separated",
            "title": "Tool"
          },
          "what": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "The task and what went wrong or what is needed (3-2000 characters)",
            "title": "What"
          }
        },
        "title": "submit_feedbackArguments",
        "type": "object"
      },
      "name": "submit_feedback",
      "outputSchema": null
    },
    {
      "description": "Verify a citation someone else produced — 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.",
      "inputSchema": {
        "properties": {
          "as_of": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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",
            "title": "As Of"
          },
          "citation": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Citation as written, e.g. Article 6(1) EU AI Act",
            "title": "Citation"
          },
          "cite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Alias for citation when agents pass cite= instead of citation=",
            "title": "Cite"
          },
          "quote": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Optional sentence to check against held text",
            "title": "Quote"
          },
          "regulation": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Regulation id when the cite string alone is ambiguous",
            "title": "Regulation"
          }
        },
        "title": "verify_citationArguments",
        "type": "object"
      },
      "name": "verify_citation",
      "outputSchema": null
    },
    {
      "description": "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.",
      "inputSchema": {
        "properties": {
          "session": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "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.",
            "title": "Session"
          },
          "trial_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Optional trial_id from connect() — echoed when present",
            "title": "Trial Id"
          }
        },
        "title": "whoamiArguments",
        "type": "object"
      },
      "name": "whoami",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:e29b3f8f6374765f5d472feacf3994f7e47e1b2fc5ed3abf7f6b0195e78cf407 | sha256sum