Servers Playground How we check Add a server Log in

Santismm Knowledge — Harness Engineering, Agentic AI & Governance

Paid per call

com.santismm/knowledgev0.4.1 Domain verified

Query core AI knowledge, essays, executable Labs, Homeric data and epistemic claims.

Research & Knowledge AI & Agents

Source Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://santismm.com/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

calculate_agent_economics Read-only

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.

toolCostnumber, required

External tool cost per attempt.

retryRatenumber, required

Extra attempts as a percentage of initial volume.

hourlyCostnumber, required

Fully loaded human hourly cost, in the chosen currency.

inputPricenumber, required

Model input price per million tokens, in the chosen currency.

reviewRatenumber, required

Share of cases reviewed by a person.

inputTokensnumber, required

Input tokens per agent attempt.

outputPricenumber, required

Model output price per million tokens, in the chosen currency.

successRatenumber, required

Correctly verified outcomes as a percentage of cases.

outputTokensnumber, required

Output tokens per agent attempt.

manualMinutesnumber, required

Manual handling time per case.

monthlyVolumenumber, required

Cases attempted per month.

reviewMinutesnumber, required

Human review minutes per reviewed case.

reworkMinutesnumber, required

Human rework minutes per failed case.

localestring

Language for interpretations, assumptions, formulas and warnings. The Labs execution service currently resolves fr/de/ja/zh to English and reports that fallback.

Santismm Knowledge — Harness Engineering, Agentic AI & Governance MCP server | mcptry

Santismm Knowledge — Harness Engineering, Agentic AI & Governance

Paid per call

com.santismm/knowledgev0.4.1 Domain verified

Query core AI knowledge, essays, executable Labs, Homeric data and epistemic claims.

Research & Knowledge AI & Agents

Source Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://santismm.com/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

calculate_agent_economics Read-only

toolCostnumber, required

External tool cost per attempt.

retryRatenumber, required

Extra attempts as a percentage of initial volume.

hourlyCostnumber, required

Fully loaded human hourly cost, in the chosen currency.

inputPricenumber, required

Model input price per million tokens, in the chosen currency.

reviewRatenumber, required

Share of cases reviewed by a person.

inputTokensnumber, required

Input tokens per agent attempt.

outputPricenumber, required

Model output price per million tokens, in the chosen currency.

successRatenumber, required

Correctly verified outcomes as a percentage of cases.

outputTokensnumber, required

Output tokens per agent attempt.

manualMinutesnumber, required

Manual handling time per case.

monthlyVolumenumber, required

Cases attempted per month.

reviewMinutesnumber, required

Human review minutes per reviewed case.

reworkMinutesnumber, required

Human rework minutes per failed case.

localestring

Language for interpretations, assumptions, formulas and warnings. The Labs execution service currently resolves fr/de/ja/zh to English and reports that fallback.

Tools (36)

calculate_agent_economics

read-only

Argument	Type	Description
locale	string	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	External tool cost per attempt.
retryRate*	number	Extra attempts as a percentage of initial volume.
hourlyCost*	number	Fully loaded human hourly cost, in the chosen currency.
inputPrice*	number	Model input price per million tokens, in the chosen currency.
reviewRate*	number	Share of cases reviewed by a person.
inputTokens*	number	Input tokens per agent attempt.
outputPrice*	number	Model output price per million tokens, in the chosen currency.
successRate*	number	Correctly verified outcomes as a percentage of cases.
outputTokens*	number	Output tokens per agent attempt.
manualMinutes*	number	Manual handling time per case.
monthlyVolume*	number	Cases attempted per month.
reviewMinutes*	number	Human review minutes per reviewed case.
reworkMinutes*	number	Human rework minutes per failed case.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "monthlyVolume",
    "manualMinutes",
    "hourlyCost",
    "inputTokens",
    "outputTokens",
    "inputPrice",
    "outputPrice",
    "toolCost",
    "retryRate",
    "successRate",
    "reviewRate",
    "reviewMinutes",
    "reworkMinutes"
  ],
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language for interpretations, assumptions, formulas and warnings. The Labs execution service currently resolves fr/de/ja/zh to English and reports that fallback."
    },
    "toolCost": {
      "type": "number",
      "maximum": 1000000,
      "minimum": 0,
      "description": "External tool cost per attempt."
    },
    "retryRate": {
      "type": "number",
      "maximum": 500,
      "minimum": 0,
      "description": "Extra attempts as a percentage of initial volume."
    },
    "hourlyCost": {
      "type": "number",
      "maximum": 1000000,
      "minimum": 0,
      "description": "Fully loaded human hourly cost, in the chosen currency."
    },
    "inputPrice": {
      "type": "number",
      "maximum": 1000000,
      "minimum": 0,
      "description": "Model input price per million tokens, in the chosen currency."
    },
    "reviewRate": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "Share of cases reviewed by a person."
    },
    "inputTokens": {
      "type": "number",
      "maximum": 100000000,
      "minimum": 0,
      "description": "Input tokens per agent attempt."
    },
    "outputPrice": {
      "type": "number",
      "maximum": 1000000,
      "minimum": 0,
      "description": "Model output price per million tokens, in the chosen currency."
    },
    "successRate": {
      "type": "number",
      "maximum": 100,
      "minimum": 1,
      "description": "Correctly verified outcomes as a percentage of cases."
    },
    "outputTokens": {
      "type": "number",
      "maximum": 100000000,
      "minimum": 0,
      "description": "Output tokens per agent attempt."
    },
    "manualMinutes": {
      "type": "number",
      "maximum": 10080,
      "minimum": 0,
      "description": "Manual handling time per case."
    },
    "monthlyVolume": {
      "type": "number",
      "maximum": 1000000000,
      "minimum": 0,
      "description": "Cases attempted per month."
    },
    "reviewMinutes": {
      "type": "number",
      "maximum": 10080,
      "minimum": 0,
      "description": "Human review minutes per reviewed case."
    },
    "reworkMinutes": {
      "type": "number",
      "maximum": 10080,
      "minimum": 0,
      "description": "Human rework minutes per failed case."
    }
  }
}

calculate_evaluation_sample_size

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.

read-only

Argument	Type	Description
locale	string	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	Margin for estimating the failure rate, in percentage points.
confidence*	any	Confidence level, in percent.
population*	number	Number of distinct evaluable cases.
failureRate*	number	Failure rate to detect, in percent.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "failureRate",
    "confidence",
    "margin",
    "population"
  ],
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language for interpretations, assumptions, formulas and warnings. The Labs execution service currently resolves fr/de/ja/zh to English and reports that fallback."
    },
    "margin": {
      "type": "number",
      "maximum": 50,
      "minimum": 0.1,
      "description": "Margin for estimating the failure rate, in percentage points."
    },
    "confidence": {
      "anyOf": [
        {
          "type": "number",
          "const": 90
        },
        {
          "type": "number",
          "const": 95
        },
        {
          "type": "number",
          "const": 99
        }
      ],
      "description": "Confidence level, in percent."
    },
    "population": {
      "type": "number",
      "maximum": 1000000000,
      "minimum": 1,
      "description": "Number of distinct evaluable cases."
    },
    "failureRate": {
      "type": "number",
      "maximum": 99.9999,
      "minimum": 0.0001,
      "description": "Failure rate to detect, in percent."
    }
  }
}

calculate_human_supervision_capacity

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.

read-only

Argument	Type	Description
locale	string	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	Share of all cases selected for routine review, in percent.
volume*	number	Agent cases per month.
hoursDay*	number	Paid hours per working day.
workdays*	number	Working days per month.
reviewers*	number	Available reviewer FTE.
hourlyCost*	number	Fully loaded reviewer hourly cost, in the chosen currency.

compare_models

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.

read-only

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

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "models"
  ],
  "properties": {
    "models": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 128,
        "minLength": 1
      },
      "maxItems": 8,
      "minItems": 2,
      "description": "Model ids or names, e.g. ['claude-opus-5.5', 'GPT-6 Astra']."
    },
    "profession": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1,
      "description": "Optional profession id or name, to include the models' rows in its ranking."
    }
  }
}

get_architecture

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.

read-only

Argument	Type	Description
slug*	string	Architecture slug, e.g. 'customer-service-agent'.
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1,
      "description": "Architecture slug, e.g. 'customer-service-agent'."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

get_article

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.

read-only

Argument	Type	Description
slug*	string	Article slug, e.g. 'the-stopwatch-and-the-exam'.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1,
      "description": "Article slug, e.g. 'the-stopwatch-and-the-exam'."
    }
  }
}

get_author_profile

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.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}

get_benchmark

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`.

read-only

Argument	Type	Description
slug*	string	Benchmark slug from list_benchmarks (e.g. 'swe-bench-pro') or its exact name.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1,
      "description": "Benchmark slug from list_benchmarks (e.g. 'swe-bench-pro') or its exact name."
    }
  }
}

get_claim

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.

read-only

Argument	Type	Description
id*	string	Claim id (e.g. 'HE-CLAIM-001') or slug.
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Claim id (e.g. 'HE-CLAIM-001') or slug."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

get_governance

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.

read-only

Argument	Type	Description
slug*	string	Governance unit slug, e.g. 'eu-ai-act'.
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1,
      "description": "Governance unit slug, e.g. 'eu-ai-act'."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

get_handbook

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.

read-only

Argument	Type	Description
id*	string	Chapter id like 'HRN-001', or its slug.
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1,
      "description": "Chapter id like 'HRN-001', or its slug."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

get_homeric_episode

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.

read-only

Argument	Type	Description
slug*	string	Episode slug, e.g. 'nekyia'.
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Episode slug, e.g. 'nekyia'."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

get_homeric_place

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.

read-only

Argument	Type	Description
slug*	string	Place slug, e.g. 'ithaca'.
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Place slug, e.g. 'ithaca'."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

get_homeric_route

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.

read-only

Argument	Type	Description
slug*	string	Route slug, e.g. 'odysseus-nostos'.
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Route slug, e.g. 'odysseus-nostos'."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

get_knowledge

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.

read-only

Argument	Type	Description
slug*	string	Knowledge unit slug, e.g. 'harness-engineering'.
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1,
      "description": "Knowledge unit slug, e.g. 'harness-engineering'."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

get_lab

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.

read-only

Argument	Type	Description
slug*	string	Lab slug, e.g. 'evaluation-sample-size'.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1,
      "description": "Lab slug, e.g. 'evaluation-sample-size'."
    }
  }
}

get_overview

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.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}

get_pattern

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.

read-only

Argument	Type	Description
slug*	string	Pattern slug, e.g. 'human-approval-gate'.
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1,
      "description": "Pattern slug, e.g. 'human-approval-gate'."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

get_related

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.

read-only

Argument	Type	Description
slug*	string	Slug of the unit to start from (or an HRN id when domain is 'handbook').
domain*	string	Core knowledge domain containing the starting unit.
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "domain",
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Slug of the unit to start from (or an HRN id when domain is 'handbook')."
    },
    "domain": {
      "enum": [
        "knowledge",
        "patterns",
        "architectures",
        "governance",
        "handbook"
      ],
      "type": "string",
      "description": "Core knowledge domain containing the starting unit."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

list_architectures

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.

read-only

Argument	Type	Description
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

list_articles

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.

read-only

Argument	Type	Description
locale	string	Restrict by language. Articles are currently published in en, es and pt.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Restrict by language. Articles are currently published in en, es and pt."
    }
  }
}

list_benchmarks

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`.

read-only

Argument	Type	Description
list	string	Restrict to the agentic catalogue or the complementary list. Omit for both.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "list": {
      "enum": [
        "catalog",
        "complementary"
      ],
      "type": "string",
      "description": "Restrict to the agentic catalogue or the complementary list. Omit for both."
    }
  }
}

list_claims

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.

read-only

Argument	Type	Description
locale	string	Language of the returned body. Default: en.
claim_type	string	Restrict to one rung of the ladder. Omit for all.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    },
    "claim_type": {
      "enum": [
        "observed_fact",
        "industry_synthesis",
        "santismm_thesis",
        "strategic_hypothesis"
      ],
      "type": "string",
      "description": "Restrict to one rung of the ladder. Omit for all."
    }
  }
}

list_governance

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.

read-only

Argument	Type	Description
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

list_handbook

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.

read-only

Argument	Type	Description
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

list_homeric_episodes

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.

read-only

Argument	Type	Description
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

list_homeric_places

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.

read-only

Argument	Type	Description
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

list_homeric_routes

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.

read-only

Argument	Type	Description
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

list_knowledge

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.

read-only

Argument	Type	Description
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

list_labs

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.

read-only

Argument	Type	Description
kind	string	Restrict results to one Lab kind. Omit to list every Lab.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "kind": {
      "enum": [
        "calculator",
        "converter",
        "experiment",
        "educational-game"
      ],
      "type": "string",
      "description": "Restrict results to one Lab kind. Omit to list every Lab."
    }
  }
}

list_patterns

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.

read-only

Argument	Type	Description
locale	string	Language of the returned body. Default: en.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    }
  }
}

list_professions

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`.

read-only

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

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "group": {
      "type": "string",
      "maxLength": 64,
      "description": "Restrict to one family: knowledge, business, creative, tech, technical or care."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the names. The benchmarks site publishes en and es; other locales fall back to English."
    },
    "evaluation": {
      "enum": [
        "direct",
        "indirect"
      ],
      "type": "string",
      "description": "Restrict to direct evaluations (a benchmark reproduces the job) or indirect ones (general tests only)."
    }
  }
}

recommend_model_for_profession

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`.

read-only

Argument	Type	Description
id*	string	Profession id from list_professions (e.g. 'lawyer', 'translator'), or its name in English or Spanish.
limit	integer	Rows of the full table to return (default: all).
locale	string	Language of names, tasks and caveats. The benchmarks site publishes en and es; other locales fall back to English.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1,
      "description": "Profession id from list_professions (e.g. 'lawyer', 'translator'), or its name in English or Spanish."
    },
    "limit": {
      "type": "integer",
      "maximum": 50,
      "description": "Rows of the full table to return (default: all).",
      "exclusiveMinimum": 0
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of names, tasks and caveats. The benchmarks site publishes en and es; other locales fall back to English."
    }
  }
}

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.

read-only

Argument	Type	Description
limit	integer	Max results (default 20).
query*	string	Keyword or phrase to search for in any supported language.
locale	string	Language of the returned body. Default: en.
domains	array	Restrict to these domains. Omit to search everything, including the handbook.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 100,
      "description": "Max results (default 20).",
      "exclusiveMinimum": 0
    },
    "query": {
      "type": "string",
      "maxLength": 512,
      "minLength": 1,
      "description": "Keyword or phrase to search for in any supported language."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    },
    "domains": {
      "type": "array",
      "items": {
        "enum": [
          "knowledge",
          "patterns",
          "architectures",
          "governance",
          "handbook"
        ],
        "type": "string"
      },
      "description": "Restrict to these domains. Omit to search everything, including the handbook."
    }
  }
}

search_all

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.

read-only

Argument	Type	Description
query*	string	Question or topic, in English, Spanish, Portuguese, French, German, Japanese or Simplified Chinese.
locale	string	Language of the returned body. Default: en.
surfaces	array	Restrict the search. Omit to search all six surfaces.
content_locales	array	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	Maximum hits from each surface. Default: 5.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 512,
      "minLength": 1,
      "description": "Question or topic, in English, Spanish, Portuguese, French, German, Japanese or Simplified Chinese."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language of the returned body. Default: en."
    },
    "surfaces": {
      "type": "array",
      "items": {
        "enum": [
          "core",
          "articles",
          "labs",
          "claims",
          "homeric_atlas",
          "benchmarks"
        ],
        "type": "string"
      },
      "minItems": 1,
      "description": "Restrict the search. Omit to search all six surfaces."
    },
    "content_locales": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "description": "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": {
      "type": "integer",
      "maximum": 10,
      "description": "Maximum hits from each surface. Default: 5.",
      "exclusiveMinimum": 0
    }
  }
}

search_articles

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.

read-only

Argument	Type	Description
limit	integer	Maximum results (default 10).
query*	string	Keyword or phrase to search for in any supported language.
locale	string	Restrict by language. Articles are currently published in en, es and pt.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 20,
      "description": "Maximum results (default 10).",
      "exclusiveMinimum": 0
    },
    "query": {
      "type": "string",
      "maxLength": 512,
      "minLength": 1,
      "description": "Keyword or phrase to search for in any supported language."
    },
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Restrict by language. Articles are currently published in en, es and pt."
    }
  }
}

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "volume",
    "sample",
    "reviewMinutes",
    "escalationRate",
    "escalationMinutes",
    "workdays",
    "hoursDay",
    "utilization",
    "reviewers",
    "hourlyCost"
  ],
  "properties": {
    "locale": {
      "enum": [
        "en",
        "es",
        "pt",
        "fr",
        "de",
        "ja",
        "zh"
      ],
      "type": "string",
      "description": "Language for interpretations, assumptions, formulas and warnings. The Labs execution service currently resolves fr/de/ja/zh to English and reports that fallback."
    },
    "sample": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "Share of all cases selected for routine review, in percent."
    },
    "volume": {
      "type": "number",
      "maximum": 1000000000,
      "minimum": 0,
      "description": "Agent cases per month."
    },
    "hoursDay": {
      "type": "number",
      "maximum": 24,
      "minimum": 0.1,
      "description": "Paid hours per working day."
    },
    "workdays": {
      "type": "number",
      "maximum": 31,
      "minimum": 1,
      "description": "Working days per month."
    },
    "reviewers": {
      "type": "number",
      "maximum": 1000000,
      "minimum": 0.1,
      "description": "Available reviewer FTE."
    },
    "hourlyCost": {
      "type": "number",
      "maximum": 1000000,
      "minimum": 0,
      "description": "Fully loaded reviewer hourly cost, in the chosen currency."
    },
    "utilization": {
      "type": "number",
      "maximum": 100,
      "minimum": 1,
      "description": "Share of paid time available for review and escalation, in percent."
    },
    "reviewMinutes": {
      "type": "number",
      "maximum": 10080,
      "minimum": 0,
      "description": "Minutes per routine review."
    },
    "escalationRate": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "Share of cases escalated, in percent."
    },
    "escalationMinutes": {
      "type": "number",
      "maximum": 10080,
      "minimum": 0,
      "description": "Minutes per escalation."
    }
  }
}