UNIDROIT Principles 2016

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

UNIDROIT Principles 2016 as executable rules: closed questions answered with grounds and source text

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "UNIDROIT Principles 2016": {
      "url": "https://mcp.arxo.io/mcp/picc",
      "transport": "streamable-http"
    }
  }
}

Measured tools (20)

• law_search read-only

  A semantic SEARCH over formalised law: a question or a notion in your own words → candidates with addresses — predicates with signatures, rules, article fragments. This is the layer of DISCOVERY, not of the answer: the result says WHAT to ask next (law_ask by signature, law_rules, law_sources) and establishes neither a fact nor a norm. The ranking is a deterministic lexical embedder (DECISION-0040), and similarity of text is not applicability of a norm. If you know the exact name, go straight to law_packages/law_ask; an empty result does NOT mean the norm does not exist.

  Parameters:

  • query (required) — string — a question or a notion in your own words
  • kinds — array — narrow the kinds of candidate
  • limit — integer — how many candidates (8, at most 25)
  • package — string — search inside this instrument only

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_passport read-only

  Passport of an exact release: purpose, interface, boundaries, checks and performance. The reports section holds the history of measurements, failures included. Entries are paged by JSON Pointer; next continues the answer.

  Parameters:

  • name (required) — string
  • version (required) — string
  • contentHash (required) — string
  • limit — integer
  • offset — integer
  • sections — array

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_answer_capabilities read-only

  A machine-readable matrix of the Lens producers that are actually installed, of replay/projection checks, profiles, limits and the contract tests that confirm them. declared_only means a schema with no executable witness.

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_capture_answer read-only

  Run a registered producer and obtain producerControl/0.2 for a later verifiable preparation of a Lens. The producer is chosen only from the shipped registry.

  Parameters:

  • producer (required) — string
  • request (required) — object

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_prepare_answer

  At the explicit request of the user, repeat between 1 and 12 earlier law_ask or law_process_run calls (the course of a case, DECISION-0160), compare their replayControl strictly, and prepare a non-public frozen document for 24 hours. The client never supplies the machine answer: the server obtains it only by executing afresh. A divergence in any input, in the law, in a resource, in the server code, in the engine library or in the result rejects the document as a whole.

  Parameters:

  • question (required) — string
  • language
  • assistant — object
  • calculations — array
  • producerRuns — array — Runs of registered producers with control/0.2; mutually exclusive with calculations.
  • documentVersion — Version of the immutable document; 0.1 is kept for transitional compatibility, 0.2 includes all native results and the common reader.

  Hints: read-only no · destructive no · idempotent no · open-world no

• law_publish_answer

  Publish a prepared document. Repeating it with the same preparationId idempotently returns the same URL and the same separate revocation secret.

  Parameters:

  • preparationId (required) — string

  Hints: read-only no · destructive no · idempotent yes · open-world yes

• law_revoke_answer destructive

  Revoke a published document using its separate secret. The public id alone grants no control; revocation closes the HTML page, the API and the download.

  Parameters:

  • publicId (required) — string
  • revokeSecret (required) — string

  Hints: read-only no · destructive yes · idempotent yes · open-world yes

• law_packages read-only

  The catalogue of formalised law: instruments, predicates with signatures, the boundaries of coverage. This is where the NAMES of predicates come from — they must never be guessed. But do NOT start from the catalogue when looking for the right instrument: the overview is large, and the title of an instrument rarely matches the words of a question ("Newton's laws of motion" contains no word "physics"). A question in your own words goes to law_search first, which returns addresses; the catalogue is for the exact signature of what you found. With no arguments — the overview: one line per instrument (key, title, legal order, counters of rules, facts, signatures, norms, constants); a whole instrument — package="kz-gpk"; a search over the signatures, labels and constants of every instrument — query="substring". All three modes are PAGED: limit and offset, with the remainder named in the text (`showing a–b of N; k more`) and in structuredContent (total, truncated, next — a ready-made continuation call). The unit of a page is named by pageUnit: the overview and query page over INSTRUMENTS (20 and 20 by default), package=… pages over the SIGNATURES of one instrument (20 by default, 300 at most) — large codes carry thousands. package=… together with catalog=… pages a separate list of the instrument: "questions" — the CATALOGUE OF QUESTIONS (DECISION-0190): which enquiries are provided for (a question in words, a form, a predicate or norms) and what the instrument does NOT answer, with the type of reason; a card is a template of an enquiry, not an answer, and not every instrument has one; "norms" — the NORMS of the instrument (modality §107 and label), "constants" — the CONSTANTS (names of declarations). "task-guides" — TASK GUIDES (DECISION-0414): the order of applying a canon to a document — what to gather, which cards to ask and how to read the answers; a guide answers nothing. catalog="task-guides" is allowed without package too — every guide of the profile; guide=… — the detail of one guide; the walkthrough — MCP Prompts under the same name. The detail of an instrument prints a preview of these lists and names the count and the ready-made call for the mode.

  Parameters:

  • guide — string — together with catalog="task-guides": the detail of one guide — a name <package>/<id> (as in prompts/list) or an id together with package
  • limit — integer — how many per page: instruments (overview 20, query 20), signatures of an instrument (20, at most 300) or elements of a catalog list (questions 20, norms 20, constants 100, task guides 20)
  • query — string — a substring filter over signatures, labels and constants (case-insensitive)
  • offset — integer — from which element of the page (0); the unit is the pageUnit of the answer
  • catalog — string — together with package: page the catalogue of questions, the norms, the constants or the task guides of the instrument instead of its signatures; "task-guides" also without package: every task guide of the profile
  • package — string — the full signatures of this instrument

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_ask read-only

  Put a question to formalised law. When the answer is "not established" it carries whyNot — the engine's why_not report §185: the candidate rules and the state of every conjunct (satisfied / not satisfied / undetermined); the missing facts are visible there and need not be guessed. BEFORE THE FIRST call obtain the predicate names through law_search (a question in your own words → addresses) or law_packages (the signatures of a known instrument) — an invented name will be rejected. If the tool returned an error or "not established", THAT IS THE ANSWER: pass it to the user and do not substitute general knowledge about the law of some other country. But "I found no suitable instrument" is NOT an answer until law_search has been asked: silence of the catalogue is a property of searching by title, not a conclusion about the corpus. kind='truth' — whether a fact is established (the answer follows §62: established / refuted / contradiction / not established); kind='collect' — enumerate the records; kind='deadline' — compute a time limit on the official calendar; kind='positions' — which DUTIES arose from the facts and what their statuses are (active / fulfilled / violated, §134–§138); kind='why_not' — the why_not report §185 on the same goal, whatever the status of the answer. The answer carries the rules applied, the warnings and the provenance with hashes; truth/collect also carry a signature block (parameter types, the closure of types, constants; DECISION-0139) for presentation. The server does not guess: where a norm is not formalised, the answer is "not established" or an error.

  Parameters:

  • args — array — the arguments of the predicate in the order of its signature; with kind='collect' exactly one of them is the selection variable ?name (for example ['urn:x:water', 'urn:x:mix', '?value']), the rest are values. Values follow the parameter type: an entity — 'urn:…' or a short name; Date — 'YYYY-MM-DD'; Money — '<number> <currency>' ('43250 KZT'); Quantity — '<number> <unit>' with the unit exactly as the package spells it ('25 calendar_year', '30 meter'; law_packages shows the units of the constants, units are never converted — §49); a constant of the package — its name
  • calc — kind='calc': a tree {op,left,right}, op ∈ add|sub|mul|div|le|lt|ge|gt|eq|ne (the synonyms divide/multiply/plus/minus and the signs are accepted); the leaves are 5 | '3932 KZT' | '2 mrp' | {lookup: 'mrp', args: [2026]} — a statutory value from the corpus; aggregates §59 are {aggregate: 'sum', element: '?v', over: [{predicate, args with '?variables'}]} over the facts given in facts
  • days — integer — deadline: the length of the period
  • kind — the kind of question (truth by default)
  • unit
  • after — string — deadline: the date of the event
  • facts — array — facts of the case: [{predicate, args, negated?, package?, provenance?, judgment?}]. package resolves an ambiguous short name. provenance is {origin?, evidence?: StableId, span?: {page?, quote?, offset?}, extractor?: {name, version?, confidence?}, observedAt?, recordedAt?}. origin defaults to case_input (section 73; extraction adds no origin value): the extractor is lowered to a was_generated_by edge, the document to was_derived_from. confidence is a decimal string; the threshold is read by the package EvidencePolicy (field confidence), not by the engine. A fact with an extractor and no evidence is accepted as case_input and yields the warning FACT_WITHOUT_EVIDENCE. A call without provenance is unchanged. args use the same notation as the args of the question
  • proof — boolean — return the evaluation field with the proof graph in the answer — a ready-made input for law_explain (kind truth|collect; by default a summary without the graph)
  • cutoff — string — deadline: the hour operations close
  • focused — boolean — kind='truth': ask as focused_truth (§181.3) — the same answer as the full truth, but the proof and the warnings cover only the cone of the question; the answer carries evaluationKind and the slice hashes (focus); the cone in focus is reduced to coneHash and the predicate count, the full cone manifest comes in evaluation.focusManifest with proof=true. A slice is not an audit document: law_prepare_answer does not accept it for publication
  • package — string — narrow the question to one package of law
  • version — string — the exact package version pinned by the client (open('name@version')); if it differs from the profile composition the host refuses instead of answering with another version
  • evidence — array — case documents, section 74, evidence_item nodes. One document is referenced from provenance.evidence of many facts. payload.confidence is data for the EvidencePolicy; the engine does not evaluate the number
  • afterTime — string — deadline: the time of filing
  • legalTime — string — the date of the law (YYYY-MM-DD)
  • predicate — string — what is being asked, e.g. 'duty_amount'
  • responseMode — full (default) — the complete answer. compact is accepted for compatibility: this server builds no short reply and returns the same complete answer in both modes; there is no fullAnswer reference and no stored snapshot of the answer.
  • supportEdges — array — support edges, section 75, support_edge nodes: from is the document id, to is the fact literal, relation is supports or refutes. Admission is decided by the package EvidencePolicy, not by the host
  • deadlinePolicy — object — the §86 policy for counting time limits expressed in days: {start_count: 'same_day'|'next_day', include_end: true|false, roll: 'no_roll'|'next_working_day'|'previous_working_day'[, month_end: 'last_day_of_month' — for months and years only]}. Without it a norm carrying a time limit answers with a DEADLINE_POLICY_* warning — the policy is set by the law of procedure and the server never assumes one. The snapshot of the official calendar §85 for working days is supplied by the server itself whenever an instrument counts them.
  • evidencePolicy — string — StableId of an evidence_policy node, section 78.2. Without it, previous calls keep their behaviour. The confidence threshold is a rule of that policy, not an argument of the call
  • selectedInterpretations — array — named readings §152; for an exactly_one group choose exactly one StableId out of law_packages/law_rules

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_screen read-only

  Build a necessary condition — a superset — for the preliminary selection of rows from an external source (DECISION-0120). This is NOT a legal answer and NOT SQL: the result is a typed tree and a manifest of the extensions up to TRUE. Every row that passes must then be computed in full by the engine, with a proof graph, on the same snapshot of the data. The binding is passed as a pinnable object; sourceSchemaContentHash is the actual hash of the source schema and is compared loudly with the pin. Case facts that carry provenance (origin, document, quote, extractor) are supplied to law_ask, not here. The confidence figure is read by the package EvidencePolicy, not by this tool and not by the engine.

  Parameters:

  • package (required) — string — the package key from law_packages
  • goal (required) — string — a StableId or a unique short name of the goal
  • binding (required) — object — a law.screen.binding/0.1 artefact
  • sourceSchemaContentHash (required) — string — the actual sha256 of the source schema
  • legalTime — string — the date of the law YYYY-MM-DD; without it every window of every rule is taken into account

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_rules read-only

  The rules of formalised law put into words: exactly how a predicate is derived (premises, source articles). Call this BEFORE supplying facts to law_ask — the rules say which facts are needed instead of leaving them to be guessed. For large instruments package=… returns a table of contents; the full text comes from predicate=…. The listing by package is paged: limit (20 by default, 500 at most) and offset; the remainder is named in the text (`showing a–b of N; k more`) and in structuredContent (total, truncated, next — a ready-made continuation call).

  Parameters:

  • lang — the language the rules are put into (DECISION-0032; the language of the profile by default; the rest are draft packs, with §218 label overlays)
  • limit — integer — package: how many rules per page (20; the budget may lower it)
  • offset — integer — package: from which rule (0)
  • package — string — every rule of the instrument
  • predicate — string — the rules that derive this predicate

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_explain read-only

  Unfold the proof of a law_ask answer into a chain "rule ← premises → conclusion". The compact input: question (the original law_ask arguments, truth/collect), resultHash and codeHash from the provenance of the answer. The server repeats the computation and compares the hashes; if anything changed it refuses explicitly. Alternatively pass the evaluation from law_ask(proof=true). answerResource=fullAnswer.uri explains a stored compact snapshot without recomputing and without the client loading pages; by default only the proofRef chain. nodeId selects one node and all of its premises (up to 24 KB, otherwise an explicit refusal). proofHash refers to the whole graph; scope marks the part selected.

  Parameters:

  • nodeId — string
  • codeHash — string
  • question — object — the original law_ask arguments
  • evaluation — object — the evaluation document from law_ask
  • resultHash — string
  • answerResource — string — the fullAnswer.uri of a stored answer taken with proof=true

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_case_ask read-only

  The ask operation §168.4 (DECISION-0165, DECISION-0399): run a registered case of a case package over its pinned dependencies and return the canonical evaluation document with a proof and a manifest. The question is JSON per query.schema.json (query), an evaluate string (evaluate + queryId), a saved queryId without query, or card + args. A refusal to prepare is an error with an LDC-* code, never an empty answer.

  Parameters:

  • package (required) — string — the path to the case package (the directory holding law.toml) from the root of the repository
  • args — object — the card parameters: name → string expression of the language
  • card — string — the id of a card of an installed catalog DECISION-0190
  • case — string — the name of the case declaration from [[cases]]; optional when there is only one case
  • query — object — the question as JSON per query.schema.json; queryId is a URN in the namespace of the package, or a short name given in queryId
  • queryId — string — without query/evaluate — the choice of a saved queries/*.json by short name or full URN; with evaluate — the id of the question being run
  • evaluate — string — the string `evaluate <expression>;` §267.2; requires queryId

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_sources read-only

  Sources: by default short excerpts (view=summary), 5 texts per page, with the address of the full text in fragments[].full. Either package or fragment is required (a StableId from law_search/law_rules). view=full returns exact parts of the text: textRange sets a range of Unicode characters, fragments[].next is the continuation with a contentHash. The hash refers to the WHOLE source, not to the excerpt or the part. textOffset/textLimit require fragment; a continuation requires contentHash. Lists are paged with offset/limit; the answer budget may shrink a page.

  Parameters:

  • view
  • limit — integer — how many texts: summary 5, full 1 (the budget may lower it)
  • offset — integer — from which fragment (0)
  • status — string — the status of the variant, as given on the source card
  • package — string — the package key — every fragment of that instrument
  • fragment — string — the StableId of a fragment
  • language — string — the language of the variant, as given on the source card
  • textLimit — integer — the maximum number of Unicode characters in a part of the text (also ≤8000 bytes of UTF-8)
  • textOffset — integer
  • contentHash — string — the hash of the full text taken from the previous part

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_argue read-only

  How robust a conclusion is: the map of the dispute under the argumentation profile §274 (DECISION-0039). The answer falls into four classes: SKEPTICALLY_ACCEPTED — the conclusion is invulnerable (it survives in the grounded extension); CREDULOUSLY_ACCEPTED — merely defensible (there is a position for it and a position against); REJECTED — it survives nowhere; NO_ARGUMENT — there are no arguments at all. It builds ALL arguments out of the facts and the rules of the instrument (chains that did not fire in ordinary inference included), the rebut/undermine/undercut attacks and the defeats by priority. Predicate names come from law_packages. On large instruments a refusal by cap is possible — narrow facts or raise limits.maxArguments.

  Parameters:

  • predicate (required) — string — the conclusion whose robustness is being measured
  • args — array — the arguments of the predicate
  • facts — array — facts of the case: [{predicate, args, negated?, provenance?}]. provenance is the same object as on law_ask: origin, document, quote, extractor. confidence is read by the package EvidencePolicy, not by the engine
  • limits — object — the caps of the §274 profile: maxArguments (64), maxExtensions (8), maxUndecided (16)
  • package — string — narrow the question to one package of law
  • legalTime — string — the date of the law (YYYY-MM-DD)

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_process read-only

  Which stages the procedure established by an instrument consists of, and whether it carries a structural defect (O-5, DECISION-0052). The stages, the transitions and the condition of every transition are reconstructed from the formalisation rather than retold: what leads from where to where, and under what condition. The check of the graph: unreachable stages, dead transitions, a transition that enters no stage at all. Without package — the list of instruments whose procedure is formalised. A stage with no exit is named but is NOT counted as a defect: whether it is terminal by design cannot be seen from the formalisation.

  Parameters:

  • package — string — the instrument; without it — the list of instruments that carry procedures

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_process_run read-only

  How a particular case will run, step by step (O-5, DECISION-0052): a log of {date, attempt?, facts?} is executed frame by frame, and the law of each frame is the law of ITS date. The answer says: which stages have been entered; which attempted transition produced NO legal effect (§164 — "the act was performed but did not take place"); which duties are violated and which time limits are running; what is available next and WHAT EXACTLY is missing for the rest. The names of transitions come from law_process. Stages entered means "was it ever entered", not "where it is now": the core 0.1 does not compute points of the current state.

  Parameters:

  • package (required) — string — the instrument
  • instance (required) — string — what is going through the procedure: the number of the lot, of the application, of the case
  • steps (required) — array — the log of the case: [{date, attempt?, time?, decisionTime?, knowledgeTime?, facts: [{predicate, args}]}]; on an attempted transition `time` is the instant of the event (ISO 8601 with an offset), and by it the bearer takes its place in the history §161.1 (DECISION-0156); the decision and knowledge axes of a frame come from the entry, else from the case, else from midnight UTC of the date; every frame names the axes it used and where they came from
  • legalTime — string — the base date (YYYY-MM-DD); the date of a frame is set by the step itself
  • probeTime — string — the instant of a hypothetical attempt, used to work out the steps available on the last frame; without it the available steps are not computed — the tool does not invent time
  • procedure — string — the procedure, where there is more than one

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_editions read-only

  The axis of editions (O-2): what changed in an instrument between two dates of the law — the state of the editions, the dating of the norms and the semantic diff §215 between the D1 projections. The verdict NOT_DATED means "there was nothing to date it by", not "nothing changed". The outcome of a particular question on a date comes from law_ask with legalTime.

  Parameters:

  • package (required) — string — the instrument of the corpus
  • dateA (required) — string — the date of the law "before" (YYYY-MM-DD)
  • dateB (required) — string — the date of the law "after" (YYYY-MM-DD)

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_query read-only

  A deterministic LawQL query over the CLIR of a formalization: a question about the model of the act itself, not about a case. Relations: nodes(id,kind,package,package_name,path), edges(from,to,role), anchors(node,anchor,act,locator,path), labels(node,lang,text,status), fields(node,field,value,value_kind), rules(id,strength,head_predicate,head_polarity,head_variables,body_variables,body_predicates), norms(id,modality,goal_kind,condition_predicates), positions(norm,kind,bearer_type), windows(norm,kind,deadline), imports(package,imported,semantic_hash), links(from,to,kind: imports|alias|subtype|produces|reads|anchored), literals(node,context,predicate,polarity), variables(node,context,name,type), interpretations(id,predicate,role). Functions: anchor, labels, short, contains, overlaps, starts_with, ends_with, position, derivation; exists/not exists over a bound variable; equality and membership only, no arithmetic and no ordering comparisons. Scope: corpus by package.name (for example kz.corpus.labour_code, not a file name) or a glob; without corpus, the whole profile slice; a scope outside the profile is empty (CORPUS_EMPTY). Examples: `from r in rules where r.head_predicate == "urn:…#eligible" select r.id as producer, r.strength as strength, anchor(r.id) as anchors` — who produces; `from l in literals where l.predicate == "urn:…#eligible" select l.node as reader, l.context as context` — who reads; `query eligible over "pkg" { for x: Person; where applicant(x); select eligible(x); }` — inference by the core. This is orchestration over the CLIR and the core; no new legal semantics is implemented here. Instead of text, a question from the catalog with arguments: producers, readers, anchors-of, imports-of, links-of, type-step (predicate/node/type parameters are URNs, pkg is a package.name or a glob). A structural answer is a queryPage: resultHash of the full queryResult, snapshot (hash of the scope package list), rowCount, rows by rowLimit (20, at most 5000) and rowOffset, next with the snapshot for continuation; full: true returns the full queryResult when the scope is one package. Every row carries provenance (CLIR nodes); an empty answer carries the explain funnel (emptyAt names the clause); errors carry LDC-Qxxxx codes with hints; a source product too wide is refused before execution (QUERY_TOO_BROAD), a continuation on another snapshot as SNAPSHOT_CHANGED.

  Parameters:

  • case — object — the case for query-over; it replaces the case clause
  • full — boolean — return the full queryResult instead of a page; only when the scope is one package
  • limit — integer — an explicit cap on eval() materialisations (it does NOT bound the rows — see rowLimit)
  • query — string — inline LawQL
  • corpus — string — the snapshot scope: a package.name (for example kz.corpus.labour_code) or a glob over package.name; without corpus, the whole profile slice
  • engine — there is one engine — the core; the reference implementation is called by its own command
  • question — string — the name of a question from the corpus/ql/questions catalog (producers, readers, anchors-of, imports-of, links-of, type-step) or of a lint; instead of query
  • rowLimit — integer — how many rows in structuredContent (20; the budget may lower it)
  • snapshot — string — the snapshot hash from next.snapshot of the previous page: a continuation on another snapshot is refused (SNAPSHOT_CHANGED)
  • arguments — object — the question parameters: an object of name → string (predicate, node, type — URNs; pkg — a package.name or a glob)
  • rowOffset — integer — from which row (0); continuation comes from next together with snapshot; structural queries only

  Hints: read-only yes · destructive no · idempotent no · open-world no

• law_report read-only

  A REPORT of a divergence between the formalisation and the source: the answer contradicts the pinned text, a norm of the source is not expressed by a rule, a §218 label diverges from the text, an address cannot be found. A report is a hypothesis for triage by a formaliser: it does NOT change the law, it never reaches the answers of the other tools, and "not derived" does not become "derived" because of it. An address is required and is checked against the catalogue: package, fragment (a StableId from law_sources) and/or predicate; callId is the X-Law-Call-Id of the answer you disagree with. The entry goes into the server log.

  Parameters:

  • package (required) — string — the instrument of the corpus
  • category (required) — the kind of divergence: norm not expressed / outcome against the text / label against the text / address not found / text against the official one / other
  • expected (required) — string — what the source says (with the article)
  • observed (required) — string — what the system answered
  • callId — string — the X-Law-Call-Id of the answer you disagree with
  • fragment — string — the StableId of the source fragment
  • predicate — string — the predicate the report is about

  Hints: read-only yes · destructive no · idempotent no · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.