com.santismm/knowledge

Est-ce que com.santismm/knowledge est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.santismm/knowledge » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 36 outils

• calculate_agent_economics≈ 1322 tokens

  Calculate monthly operating cost, cost per verified outcome, manual baseline, savings, ROI and break-even success rate from explicit assumptions. Use this for an agent business case or scenario comparison; keep every monetary input in the same currency and cite the returned canonical_url.

  Paramètres, retour & exemple (14)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language for interpretations, assumptions, formulas and warnings. The Labs execution service currently resolves fr/de/ja/zh to English and reports that fallback.
  • toolCost · number · requis
    External tool cost per attempt.
  • retryRate · number · requis
    Extra attempts as a percentage of initial volume.
  • hourlyCost · number · requis
    Fully loaded human hourly cost, in the chosen currency.
  • inputPrice · number · requis
    Model input price per million tokens, in the chosen currency.
  • reviewRate · number · requis
    Share of cases reviewed by a person.
  • inputTokens · number · requis
    Input tokens per agent attempt.
  • outputPrice · number · requis
    Model output price per million tokens, in the chosen currency.
  • successRate · number · requis
    Correctly verified outcomes as a percentage of cases.
  • outputTokens · number · requis
    Output tokens per agent attempt.
  • manualMinutes · number · requis
    Manual handling time per case.
  • monthlyVolume · number · requis
    Cases attempted per month.
  • reviewMinutes · number · requis
    Human review minutes per reviewed case.
  • reworkMinutes · number · requis
    Human rework minutes per failed case.

  Exemple d'appel

  {"name": "calculate_agent_economics", "arguments": {"toolCost": 1, "retryRate": 1, "hourlyCost": 1, "inputPrice": 1, "reviewRate": 1, "inputTokens": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"slug": "texte", "units": {}, "inputs": {}, "source": "texte", "api_url": "texte", "license": {}, "results": {}, "updated": "texte", "version": "texte", "fallback": true, "formulas": [], "language": "texte"}}

• calculate_evaluation_sample_size≈ 821 tokens

  Calculate two different samples: how many independent evaluations are needed to detect at least one failure, and how many are needed to estimate its rate at a chosen margin. Use this when a user asks how many tests are enough; do not interpret zero observed failures as proof of zero risk.

  Paramètres, retour & exemple (5)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language for interpretations, assumptions, formulas and warnings. The Labs execution service currently resolves fr/de/ja/zh to English and reports that fallback.
  • margin · number · requis
    Margin for estimating the failure rate, in percentage points.
  • confidence · ? · requis
    Confidence level, in percent.
  • population · number · requis
    Number of distinct evaluable cases.
  • failureRate · number · requis
    Failure rate to detect, in percent.

  Exemple d'appel

  {"name": "calculate_evaluation_sample_size", "arguments": {"margin": 1, "confidence": "texte", "population": 1, "failureRate": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"slug": "texte", "units": {}, "inputs": {}, "source": "texte", "api_url": "texte", "license": {}, "results": {}, "updated": "texte", "version": "texte", "fallback": true, "formulas": [], "language": "texte"}}

• calculate_human_supervision_capacity≈ 1082 tokens

  Calculate review and escalation workload, required FTE, available headroom or backlog, monthly labour cost and sustainable case volume. Use this before production rollout to test whether the stated human-oversight model is operationally credible; the result uses averages and is not a queueing simulation.

  Paramètres, retour & exemple (11)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language for interpretations, assumptions, formulas and warnings. The Labs execution service currently resolves fr/de/ja/zh to English and reports that fallback.
  • sample · number · requis
    Share of all cases selected for routine review, in percent.
  • volume · number · requis
    Agent cases per month.
  • hoursDay · number · requis
    Paid hours per working day.
  • workdays · number · requis
    Working days per month.
  • reviewers · number · requis
    Available reviewer FTE.
  • hourlyCost · number · requis
    Fully loaded reviewer hourly cost, in the chosen currency.
  • utilization · number · requis
    Share of paid time available for review and escalation, in percent.
  • reviewMinutes · number · requis
    Minutes per routine review.
  • escalationRate · number · requis
    Share of cases escalated, in percent.
  • escalationMinutes · number · requis
    Minutes per escalation.

  Exemple d'appel

  {"name": "calculate_human_supervision_capacity", "arguments": {"sample": 1, "volume": 1, "hoursDay": 1, "workdays": 1, "reviewers": 1, "hourlyCost": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"slug": "texte", "units": {}, "inputs": {}, "source": "texte", "api_url": "texte", "license": {}, "results": {}, "updated": "texte", "version": "texte", "fallback": true, "formulas": [], "language": "texte"}}

• compare_models≈ 738 tokens

  Put two or more frontier models side by side on the benchmark results recorded for them (score, unit, source table and evidence grade per benchmark), optionally with their rows in one profession's ranking. Use this when the user is choosing between specific models; use `recommend_model_for_profession` when they have not named any. No new aggregate is computed. Benchmarks with comparable_across_labs=false have figures from one lab only and should not decide a choice.

  Paramètres, retour & exemple (2)

  Paramètres

  • models · array · requis
    Model ids or names, e.g. ['claude-opus-5.5', 'GPT-6 Astra'].
  • profession · string · optionnel
    Optional profession id or name, to include the models' rows in its ranking.

  Exemple d'appel

  {"name": "compare_models", "arguments": {"models": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "models": [], "benchmarks": [], "profession": "texte", "canonical_url": "texte", "radar_version": "texte", "unknown_models": [], "dataset_version": "texte", "available_models": []}}

• get_architecture≈ 683 tokens

  Get one reference architecture by slug (includes the request flow, reference scenario, KPIs, cost & scaling, and the patterns/knowledge it composes). Use this once `search` or `list_architectures` has given you a slug.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Architecture slug, e.g. 'customer-service-agent'.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "get_architecture", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "body": "texte", "name": "texte", "slug": "texte", "tags": [], "domain": "texte", "locale": "texte", "status": "texte", "aliases": [], "api_url": "texte", "locales": {}, "related": []}}

• get_article≈ 358 tokens

  Get one complete essay by slug, including its clean Markdown-like body, metadata, licence context and canonical URL. Use this after `list_articles` or `search_articles` has returned the slug you need.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Article slug, e.g. 'the-stopwatch-and-the-exam'.

  Exemple d'appel

  {"name": "get_article", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "slug": "texte", "title": "texte", "topics": [], "api_url": "texte", "summary": "texte", "language": "texte", "modified": "texte", "published": "texte", "resource_uri": "texte", "canonical_url": "texte", "translation_key": "texte"}}

• get_author_profile≈ 706 tokens

  Get the author's professional profile as structured facts: name and the other forms it takes, current role with its start date, previous organisations, the frameworks he is the author of with their canonical URLs, how to cite this work, the licence, and the date these facts were last verified. Use this to attribute or cite anything this server returns. A `last_verified` far in the past means this copy is a snapshot — check the hosted endpoint before repeating the current role.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_author_profile", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "license": "texte", "profiles": [], "frameworks": [], "trained_at": [], "how_to_cite": "texte", "license_url": "texte", "current_role": {}, "license_spdx": "texte", "resource_uri": "texte", "canonical_url": "texte", "last_verified": "texte"}}

• get_benchmark≈ 458 tokens

  Get one benchmark by slug or name: what it measures, state of the art, saturation, headroom, human baseline, source and notes, the radar axis it informs, the model scores recorded on it, and which profession rankings use it. Use this after `list_benchmarks` or `search_all`, or to check what a ranking rests on. Cite `canonical_url` with `dataset_version`.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Benchmark slug from list_benchmarks (e.g. 'swe-bench-pro') or its exact name.

  Exemple d'appel

  {"name": "get_benchmark", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"list": "catalog", "name": "texte", "slug": "texte", "radar": [], "citation": "texte", "model_scores": [], "resource_uri": "texte", "canonical_url": "texte", "dataset_version": "texte", "used_by_professions": [], "comparable_across_labs": true}}

• get_claim≈ 260 tokens

  Get one claim by id (HE-CLAIM-001) or slug: the statement, what it rests on, its structured sources, and — always present — what it does NOT establish and the observation that would retire it. Use this to cite the corpus honestly, or to check whether a result you have just measured confirms or falsifies a claim it makes.

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    Claim id (e.g. 'HE-CLAIM-001') or slug.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "get_claim", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_governance≈ 671 tokens

  Get one AI governance unit by slug (includes scope, key requirements, implementable controls, a checklist and common pitfalls). Use this once `search` or `list_governance` has given you a slug.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Governance unit slug, e.g. 'eu-ai-act'.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "get_governance", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "body": "texte", "name": "texte", "slug": "texte", "tags": [], "domain": "texte", "locale": "texte", "status": "texte", "aliases": [], "api_url": "texte", "locales": {}, "related": []}}

• get_handbook≈ 740 tokens

  Get one Harness Engineering Handbook chapter, by id (e.g. 'HRN-001') or slug. Returns the full Markdown body plus its provenance and related ids. Use this once `search` or `list_handbook` has given you an id.

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    Chapter id like 'HRN-001', or its slug.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "get_handbook", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "body": "texte", "name": "texte", "slug": "texte", "tags": [], "domain": "texte", "locale": "texte", "status": "texte", "aliases": [], "api_url": "texte", "locales": {}, "related": []}}

• get_homeric_episode≈ 238 tokens

  Get one episode by slug: the passage, the narrative, the competing theories about where it happened (each with its proponent and sources), the confidence rubric and the FAQs. Use this when the question is where an episode took place and who argued for it.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Episode slug, e.g. 'nekyia'.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "get_homeric_episode", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_homeric_place≈ 245 tokens

  Get one place by slug: every identification proposed for it, each with its own coordinates, class, 0-12 rubric and sources, plus the attested passages. Use this when you need to weigh the evidence for a location, or to cite it; a place the poem does not locate carries no coordinates at all.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Place slug, e.g. 'ithaca'.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "get_homeric_place", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_homeric_route≈ 238 tokens

  Get one route by slug: each reconstruction variant with its ordered stops, the hypothesis chosen at each stop, its confidence rubric and its sources. Use this to compare rival reconstructions of a voyage: they are returned side by side rather than merged.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Route slug, e.g. 'odysseus-nostos'.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "get_homeric_route", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_knowledge≈ 668 tokens

  Get one knowledge unit by slug. Returns the full entry, or a single-locale body if locale is given. Use this once `search` or `list_knowledge` has given you a slug.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Knowledge unit slug, e.g. 'harness-engineering'.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "get_knowledge", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "body": "texte", "name": "texte", "slug": "texte", "tags": [], "domain": "texte", "locale": "texte", "status": "texte", "aliases": [], "api_url": "texte", "locales": {}, "related": []}}

• get_lab≈ 696 tokens

  Get one Lab by slug, including formulas, assumptions, related SANTISMM content and its executable endpoint when one exists. Use this after list_labs or search_all; use the named calculate_* tool rather than reimplementing a published formula.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Lab slug, e.g. 'evaluation-sample-size'.

  Exemple d'appel

  {"name": "get_lab", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_overview≈ 723 tokens

  Get the complete MCP map — start here. Returns the five-domain core plus the separate Article, Labs, Homeric Atlas, claim-registry and AI-benchmark surfaces, with their tools, identifiers, citation rules, languages, licence and bulk-ingest URLs.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_overview", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"bulk": {}, "next": "texte", "site": "texte", "total": 1, "corpus": {}, "source": "texte", "domains": [], "license": "texte", "locales": [], "extensions": [], "license_url": "texte", "license_spdx": "texte"}}

• get_pattern≈ 664 tokens

  Get one Enterprise AI pattern by slug (includes problem, solution, KPIs, failure modes, lessons). Use this once `search` or `list_patterns` has given you a slug.

  Paramètres, retour & exemple (2)

  Paramètres

  • slug · string · requis
    Pattern slug, e.g. 'human-approval-gate'.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "get_pattern", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "body": "texte", "name": "texte", "slug": "texte", "tags": [], "domain": "texte", "locale": "texte", "status": "texte", "aliases": [], "api_url": "texte", "locales": {}, "related": []}}

• get_related≈ 1053 tokens

  Traverse the knowledge graph: given a unit, return its neighbours — the units it links to (outgoing) and the units that reference it (incoming), each with the relationship type. Use this after a `get_*` call to widen an answer with adjacent units.

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Slug of the unit to start from (or an HRN id when domain is 'handbook').
  • domain · string · requis · knowledge | patterns | architectures | governance | handbook
    Core knowledge domain containing the starting unit.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "get_related", "arguments": {"slug": "texte", "domain": "knowledge"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"unit": {}, "incoming": [], "outgoing": []}}

• list_architectures≈ 470 tokens

  List all reference architectures (end-to-end enterprise agentic blueprints) with id, slug, category, name, summary and provenance. Use this to browse the blueprints; use `search` when you have a use case rather than a name.

  Paramètres, retour & exemple (1)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "list_architectures", "arguments": {"locale": "en"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": []}}

• list_articles≈ 390 tokens

  List every long-form essay published on articles.santismm.com, with language, dates, topics and citable canonical URLs. Use this to browse the essay catalogue; use `search_articles` when you have a topic rather than a slug.

  Paramètres, retour & exemple (1)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Restrict by language. Articles are currently published in en, es and pt.

  Exemple d'appel

  {"name": "list_articles", "arguments": {"locale": "en"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": []}}

• list_benchmarks≈ 386 tokens

  List every benchmark in the AI Agent Benchmarks catalogue (agentic benchmarks with SOTA, saturation and headroom) and in the radar's complementary list (vision, long context, factuality, instruction following, language). Use this to find a benchmark slug; then call `get_benchmark`.

  Paramètres, retour & exemple (1)

  Paramètres

  • list · string · optionnel · catalog | complementary
    Restrict to the agentic catalogue or the complementary list. Omit for both.

  Exemple d'appel

  {"name": "list_benchmarks", "arguments": {"list": "catalog"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": [], "dataset_version": "texte"}}

• list_claims≈ 469 tokens

  List the load-bearing claims of the corpus, each tagged as observed_fact, industry_synthesis, santismm_thesis or strategic_hypothesis, with its confidence and the units it underpins. Use this before quoting the handbook to know whether a statement is evidence, a reading of the industry, or a position taken. Filter by `claim_type` to get only what is checkable.

  Paramètres, retour & exemple (2)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.
  • claim_type · string · optionnel · observed_fact | industry_synthesis | santismm_thesis | strategic_hypothesis
    Restrict to one rung of the ladder. Omit for all.

  Exemple d'appel

  {"name": "list_claims", "arguments": {"locale": "en", "claim_type": "observed_fact"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": []}}

• list_governance≈ 477 tokens

  List all AI governance units (regulations, standards, frameworks, playbooks — EU AI Act, ISO 42001, NIST AI RMF, agentic checklist) with id, slug, category, name and summary. Use this to browse the regulations and standards; use `search` for an obligation or control.

  Paramètres, retour & exemple (1)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "list_governance", "arguments": {"locale": "en"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": []}}

• list_handbook≈ 507 tokens

  List the Harness Engineering Handbook chapters (HRN-001…): the canonical long-form corpus on harness engineering — definition, history, taxonomy, principles, memory, observability, evaluation, governance, planning, orchestration, security, case studies, glossary and bibliography. Use this to see the chapter map; use `search` when you have a topic rather than a chapter.

  Paramètres, retour & exemple (1)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "list_handbook", "arguments": {"locale": "en"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": []}}

• list_homeric_episodes≈ 450 tokens

  List every episode of the Iliad and the Odyssey held in the atlas, in reading order, with its passage, the places it involves and how firmly it can be located. Use this to find the episode you want; use `get_homeric_episode` for its theories and sources.

  Paramètres, retour & exemple (1)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "list_homeric_episodes", "arguments": {"locale": "en"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": []}}

• list_homeric_places≈ 532 tokens

  List every place in the Homeric Atlas with its identification class, its confidence score and how many competing identifications it carries. Use this to browse the atlas; use `get_homeric_place` once you have a slug. Identification classes: accepted (an excavated site with consensus), plausible (a real place, contested), speculative (a minority reading or a later tradition), mythical (the poem places it outside the mappable world). Confidence is a published 0-12 rubric - textual, archaeological, scholarly and geographic, 0-3 each - and is an editorial judgement, not a probability.

  Paramètres, retour & exemple (1)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "list_homeric_places", "arguments": {"locale": "en"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": []}}

• list_homeric_routes≈ 436 tokens

  List the reconstructed itineraries (the nostos of Odysseus and the others), each with its rival reconstructions scored separately. Use this to see which voyages the atlas reconstructs before fetching one.

  Paramètres, retour & exemple (1)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "list_homeric_routes", "arguments": {"locale": "en"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": []}}

• list_knowledge≈ 466 tokens

  List all knowledge units (concepts on agentic & enterprise AI) with slug, category, title, summary and Evidence-First provenance. Use this to browse the domain; use `search` when you have a question rather than a slug.

  Paramètres, retour & exemple (1)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "list_knowledge", "arguments": {"locale": "en"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": []}}

• list_labs≈ 754 tokens

  List every SANTISMM Lab with its inputs, outputs, assumptions, formulas and citation URL. Use this to discover interactive and machine-readable tools; filter by kind when the user specifically asks for a calculator, converter, experiment or educational game.

  Paramètres, retour & exemple (1)

  Paramètres

  • kind · string · optionnel · calculator | converter | experiment | educational-game
    Restrict results to one Lab kind. Omit to list every Lab.

  Exemple d'appel

  {"name": "list_labs", "arguments": {"kind": "calculator"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": []}}

• list_patterns≈ 466 tokens

  List all Enterprise AI patterns (reusable agentic design patterns) with slug, category, name, summary and provenance. Use this to browse the catalogue; use `search` when you are looking for a pattern that solves a problem.

  Paramètres, retour & exemple (1)

  Paramètres

  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.

  Exemple d'appel

  {"name": "list_patterns", "arguments": {"locale": "en"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": []}}

• list_professions≈ 598 tokens

  List the professions that have a ranking of frontier AI models built from independent benchmark results (lawyer, accountant, developer, salesperson, translator, engineer…), each marked as a direct or an indirect evaluation, with the model that ranks first today. Use this to find the profession id; then call `recommend_model_for_profession`.

  Paramètres, retour & exemple (3)

  Paramètres

  • group · string · optionnel
    Restrict to one family: knowledge, business, creative, tech, technical or care.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the names. The benchmarks site publishes en and es; other locales fall back to English.
  • evaluation · string · optionnel · direct | indirect
    Restrict to direct evaluations (a benchmark reproduces the job) or indirect ones (general tests only).

  Exemple d'appel

  {"name": "list_professions", "arguments": {"group": "texte", "locale": "en", "evaluation": "direct"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "results": []}}

• recommend_model_for_profession≈ 1355 tokens

  Get the ranking of frontier AI models for one profession: the best result, the runner-up, the best value and the best open-weights model, the full table with data coverage and price, which tasks each benchmark measures and which tasks no benchmark measures yet. Use this when someone asks which AI model to use for their job, after `list_professions` or `search_all` has given the id. When `evaluation.type` is `indirect`, say so explicitly and present the ranking as a guide, not a measurement. Cite `canonical_url` with `dataset_version`.

  Paramètres, retour & exemple (3)

  Paramètres

  • id · string · requis
    Profession id from list_professions (e.g. 'lawyer', 'translator'), or its name in English or Spanish.
  • limit · integer · optionnel
    Rows of the full table to return (default: all).
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of names, tasks and caveats. The benchmarks site publishes en and es; other locales fall back to English.

  Exemple d'appel

  {"name": "recommend_model_for_profession", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "name": "texte", "group": "texte", "picks": {}, "tasks": [], "caveat": "texte", "ranking": [], "coverage": {}, "evaluation": {}, "not_measured": "texte", "resource_uri": "texte", "canonical_url": "texte"}}

• search≈ 721 tokens

  Ranked keyword search across the whole corpus (knowledge, patterns, architectures, governance and the handbook). Matches every language and ignores accents, so query in the user's own words. Each hit carries a relevance score and the fields it matched; follow up with the matching get_* tool for full detail. Use this before any `get_*` tool whenever you have a question rather than an identifier.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
    Max results (default 20).
  • query · string · requis
    Keyword or phrase to search for in any supported language.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.
  • domains · array · optionnel
    Restrict to these domains. Omit to search everything, including the handbook.

  Exemple d'appel

  {"name": "search", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "query": "texte", "results": []}}

• search_all≈ 1068 tokens

  Search the core corpus, first-party essays, executable Labs, epistemic claims, the Homeric Atlas and the AI benchmarks (professions and benchmark catalogue) in one call. Use this first when a natural-language question might require a calculation, a long-form essay, a claim audit or a model choice rather than only a core knowledge unit. Results name the next tool to call; calculator-shaped questions are routed toward Labs, and 'which AI model for…' questions toward the benchmarks.

  Paramètres, retour & exemple (5)

  Paramètres

  • query · string · requis
    Question or topic, in English, Spanish, Portuguese, French, German, Japanese or Simplified Chinese.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Language of the returned body. Default: en.
  • surfaces · array · optionnel
    Restrict the search. Omit to search all six surfaces.
  • content_locales · array · optionnel
    Keep only results whose text is entirely in these languages. `locale` is a presentation preference and still returns substitutions, labelled; this is the hard filter. A result that mixes a language you did not allow is dropped, and so is one that cannot declare its languages.
  • limit_per_surface · integer · optionnel
    Maximum hits from each surface. Default: 5.

  Exemple d'appel

  {"name": "search_all", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "query": "texte", "results": [], "empty_reason": "texte", "requested_locale": "texte", "substituted_count": 1, "unavailable_surfaces": []}}

• search_articles≈ 522 tokens

  Ranked, accent-insensitive full-text search over every first-party essay, including titles, summaries, topics and bodies. Use this when you need long-form analysis about a topic; follow with `get_article` for the complete essay.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Maximum results (default 10).
  • query · string · requis
    Keyword or phrase to search for in any supported language.
  • locale · string · optionnel · en | es | pt | fr | de | ja | zh
    Restrict by language. Articles are currently published in en, es and pt.

  Exemple d'appel

  {"name": "search_articles", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "query": "texte", "results": []}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://santismm.com/mcp