# FIDE Laws of Chess

> FIDE Laws of Chess (2023) as an executable model: arbiter cases, answers with rules and judgments

- name: io.arxo/fide-chess
- version: 0.1.1
- connection class: R0 (autonomous)
- trust: 95/100
- quality: 88/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.arxo%2Ffide-chess
- tools: https://api.protogrid.dev/v1/servers/io.arxo%2Ffide-chess/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "fide-chess": {
      "type": "http",
      "url": "https://mcp.arxo.io/mcp/fide-chess"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 98
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-96% +updated-6d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 88/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 3 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 16 of 16 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 7,881 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 5 of the 7 days needed

### dependencies: 100 (weight 15)

- pass `deps.known_vulns`: no known advisory in 3 resolved packages
- n/a `deps.mcp_sdk_version`: the official MCP SDK is not in the dependency graph
- pass `deps.resolvable`: @arxo/mcp-fide-chess@0.1.1 resolved: 3 packages

- tools: 16, about 7,881 tokens to load them all
- tool set hash: b0c871f9a2434c926d7b0c64df830a8a
- badge: [![protogrid quality](https://protogrid.dev/badge/io.arxo/fide-chess.svg)](https://protogrid.dev/servers/io.arxo/fide-chess)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Dependencies

- npm @arxo/mcp-fide-chess@0.1.1: resolved, 2 dependencies

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://mcp.arxo.io/mcp/fide-chess (streamable-http, auth none, reachable true, uptime30d 0.95652175)

## Packages

- npm @arxo/mcp-fide-chess@0.1.1

## Tools (16)

- `law_answer_capabilities`: 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.
- `law_ask`: Put a question to formalised law. When the answer is "not established" it carries whyNot — the engine's why_not report: 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; 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; kind='why_not' — the why_not report 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 for presentation. The server does not guess: where a norm is not formalised, the answer is "not established" or an error.
- `law_capture_answer`: 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.
- `law_case_ask`: The ask operation: run a registered case of a case package over its pinned dependencies and return the answer: by default a projection of the evaluation document without the proof graph, on responseMode full or proof: true the canonical 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.
- `law_explain`: 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.
- `law_inspect`: Evaluation inspector over a SAVED evaluation document: summary — the origin card, resultHash and snapshot verification, listings of results, positions and issues; slice — the closure of proof nodes for a query, rule, position or node with addresses, both sides of BOTH, defeats, values, names resolved against the snapshot; diff — what changed between two documents on the context, result and justification levels; locate — the declaration by StableId. Nothing is evaluated or recomputed: the source is evaluation from law_ask(proof=true) or an answerResource. Missing data is a limit state (limits), never a negation.
- `law_packages`: 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: 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, "constants" — the CONSTANTS (names of declarations). "task-guides" — TASK GUIDES: 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.
- `law_passport`: 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.
- `law_prepare_answer`: At the explicit request of the user, repeat between 1 and 12 earlier law_ask or law_process_run calls, 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.
- `law_publish_answer`: Publish a prepared document. Repeating it with the same preparationId idempotently returns the same URL and the same separate revocation secret.
- `law_query`: A deterministic LawQL query over the CLIR of a formalization: a question about the model of the act itself, not about a case. Relations (14): anchors, edges, fields, imports, interpretations, labels, links, literals, nodes, norms, positions, rules, variables, windows. Full field lists: `law query --schema`. Functions (9): anchor/1, labels/1..2, short/1, contains/2, overlaps/2, starts_with/2, ends_with/2, position/2, derivation/2. 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: anchors-of, imports-of, links-of, producers, readers, type-step (see `law query --list` for the set) (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.
- `law_revoke_answer`: 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.
- `law_rules`: 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).
- `law_screen`: Build a necessary condition — a superset — for the preliminary selection of rows from an external source. 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.
- `law_search`: 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, 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.
- `law_sources`: 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.