Agentosaurus

Claude Code policy gateway, prices, AI-agent reviews and Amsterdam sustainability data as MCP tools.

使うべきか

品質と安全性

B
説明の品質
87%
スキーマの完全性
71%
命名の品質
93%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(8)

  • LOWTool 'about_wingie' description lacks action verbabout_wingie 内
  • LOWTool 'get_organization' description lacks action verbget_organization 内
  • LOWTool 'partner_match' description lacks action verbpartner_match 内
  • LOWTool 'food_rescue_amsterdam' description lacks action verbfood_rescue_amsterdam 内
  • LOWTool 'get_topic' description lacks action verbget_topic 内
  • LOWTool 'get_inventory' description lacks action verbget_inventory 内
  • LOWTool 'search_kits' description lacks action verbsearch_kits 内
  • LOWTool 'get_kit' description lacks action verbget_kit 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~4,150トークン数(ツール定義)
~865 B一般的なレスポンスサイズ
注意への影響は大きい(128k コンテキストの 3.24%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "agentosaurus": {
      "url": "https://agentosaurus.com/mcp"
    }
  }
}

リモートエンドポイント

https://agentosaurus.com/mcpstreamable-http

できること

ツール一覧

ツール(28)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢get_pricing

Published prices for each stage of a sovereign training run at each model size, for both architectures, with their assumptions. Same data as /agents/pricing.json.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_quote(size, arch, novel, dataset, supervision, ...)

An itemised quote for one model size, with dataset-only, dataset-plus-compute and selection totals. Same data as /agents/quote.json.

入力スキーマ

{
  "type": "object",
  "properties": {
    "size": {
      "type": "string",
      "enum": [
        "24M",
        "262M",
        "744M",
        "3.8B",
        "7B",
        "27B",
        "35B",
        "2.8T"
      ],
      "description": "Model size, case-insensitive."
    },
    "arch": {
      "type": "string",
      "enum": [
        "moe",
        "dense"
      ],
      "default": "moe"
    },
    "novel": {
      "type": "boolean",
      "default": false,
      "description": "A novel architecture."
    },
    "dataset": {
      "type": "boolean",
      "default": true,
      "description": "Include the dataset."
    },
    "supervision": {
      "type": "boolean",
      "default": false,
      "description": "Include a supervised run."
    },
    "licensing": {
      "type": "string",
      "enum": [
        "open",
        "private"
      ],
      "default": "open"
    },
    "expert_hours": {
      "type": "integer",
      "minimum": 0,
      "maximum": 100000,
      "default": 0
    },
    "expert_rate": {
      "type": "number",
      "description": "USD per expert hour. Send this or novelty, not both."
    },
    "novelty": {
      "type": "string",
      "description": "A published novelty band id."
    },
    "hours_per_day": {
      "type": "integer",
      "minimum": 1,
      "maximum": 24
    }
  },
  "required": [
    "size"
  ],
  "additionalProperties": false
}
🟢get_review_scope

The change-control Review (the Audit): its scope, the plan by week, what you receive and how the price is set. Same text as /agents/audit.txt.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_policy_gateway_offer

The policy gateway offer: policy research, enforcement on every Claude Code tool call through hooks, a human approvals queue, a tamper-evident decision log and a weekly report per team; how a team switches it on through managed settings; the four tiers; and what is collected. Same text as /policy-gateway.txt.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢list_nodes

GPU node builds a buyer owns and Agentosaurus racks in Amsterdam, with build totals, the minimum order, monthly colocation and energy factors. Same data as /agents/nodes.json.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢estimate_pretraining_cost(total_params, active_params, architecture, tokens_per_param, tier)

What pretraining a model of a given shape costs at the published rates: token budget, GPU hours, run schedule and the total. The same arithmetic as the /cost/ calculator and /agents/model.json.

入力スキーマ

{
  "type": "object",
  "properties": {
    "total_params": {
      "type": "integer",
      "minimum": 1000000,
      "description": "Total parameters."
    },
    "active_params": {
      "type": "integer",
      "minimum": 1,
      "description": "Parameters active per token. Defaults to total_params (dense)."
    },
    "architecture": {
      "type": "string",
      "enum": [
        "moe",
        "dense"
      ]
    },
    "tokens_per_param": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10000,
      "default": 20
    },
    "tier": {
      "type": "string",
      "enum": [
        "starter",
        "standard",
        "deep"
      ],
      "description": "Trajectory tier."
    }
  },
  "required": [
    "total_params"
  ],
  "additionalProperties": false
}
🟢list_blog_posts(tag, limit)

Published blog posts, newest first, with excerpts and tags.

入力スキーマ

{
  "type": "object",
  "properties": {
    "tag": {
      "type": "string",
      "description": "Only posts carrying this tag."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10,
      "description": "How many results to return."
    }
  },
  "additionalProperties": false
}
🟢get_blog_post(slug)

The full Markdown of one published post.

入力スキーマ

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "The slug from a search result."
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false
}
🟢about_wingie

Who wingie, the AI agent at Agentosaurus, is, what it may do and how to reach the team. Same text as /wingie.txt.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢how_to_contact

The contact address and the ways to reach a person at Agentosaurus.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢search_organizations(query, sdg, city, limit)

Search the public directory of analysed organisations (the /planet-agent/ directory) by name, city and SDG goal. Returns public profile fields only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Part of the organisation's name."
    },
    "sdg": {
      "type": "integer",
      "minimum": 1,
      "maximum": 17,
      "description": "Only organisations aligned with this SDG goal."
    },
    "city": {
      "type": "string",
      "description": "City name, for example Amsterdam."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10,
      "description": "How many results to return."
    }
  },
  "additionalProperties": false
}
🟢get_organization(slug)

The public profile of one organisation and the questions ask_organization can answer about it.

入力スキーマ

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "The slug from a search result."
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false
}
🟢ask_organization(slug, question)

Answers one question from a fixed list using the organisation's stored public profile. Nothing is generated; a question with no stored data says so and links the profile.

入力スキーマ

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "The slug from a search result."
    },
    "question": {
      "type": "string",
      "enum": [
        "what_they_do",
        "sdgs",
        "where",
        "website_and_contact",
        "how_to_volunteer",
        "how_to_donate",
        "events",
        "similar_organizations",
        "jobs",
        "partners",
        "impact",
        "certifications"
      ]
    }
  },
  "required": [
    "slug",
    "question"
  ],
  "additionalProperties": false
}
🟢list_events(city, date_from, limit)

Upcoming published volunteer events, soonest first, with their shifts. Same events as /events/volunteer/find/.

入力スキーマ

{
  "type": "object",
  "properties": {
    "city": {
      "type": "string",
      "default": "Amsterdam",
      "description": "Town or city named in the event location. Empty string for every city."
    },
    "date_from": {
      "type": "string",
      "format": "date",
      "description": "Only events on or after this date (YYYY-MM-DD)."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10,
      "description": "How many results to return."
    }
  },
  "additionalProperties": false
}
🟢find_volunteer_shifts(city, date_from, limit)

Upcoming volunteer shifts with the spots still open, the event and the organiser's public page.

入力スキーマ

{
  "type": "object",
  "properties": {
    "city": {
      "type": "string",
      "default": "Amsterdam",
      "description": "Town or city named in the event location. Empty string for every city."
    },
    "date_from": {
      "type": "string",
      "format": "date",
      "description": "Only events on or after this date (YYYY-MM-DD)."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10,
      "description": "How many results to return."
    }
  },
  "additionalProperties": false
}
🟢get_event(slug)

One published volunteer event with its shifts and the organiser's public page.

入力スキーマ

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "The slug from a search result."
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false
}
🟢partner_match(sdgs, city, limit)

Ranks organisations by alignment with the SDG goals a business wants to advance, the same matching as /partner-match/.

入力スキーマ

{
  "type": "object",
  "properties": {
    "sdgs": {
      "type": "array",
      "items": {
        "type": "integer",
        "minimum": 1,
        "maximum": 17
      },
      "minItems": 1,
      "maxItems": 17
    },
    "city": {
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 20,
      "description": "How many results to return."
    }
  },
  "required": [
    "sdgs"
  ],
  "additionalProperties": false
}
🟢food_rescue_amsterdam(intent)

Donating surplus food to Taste Before You Waste in Amsterdam, joining them as a volunteer, and what the organisation does.

入力スキーマ

{
  "type": "object",
  "properties": {
    "intent": {
      "type": "string",
      "enum": [
        "donate_surplus",
        "volunteer",
        "about"
      ]
    }
  },
  "required": [
    "intent"
  ],
  "additionalProperties": false
}
🟢get_lab_experiments

Every experiment on /lab/: what ran, the number, its state, and the compute a queued run needs. Same text as /lab.txt.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_topic(name)

The text of one topic page: AI safety, AI sovereignty, AI security, or the Dutch sovereign-hardware page.

入力スキーマ

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "enum": [
        "ai-safety",
        "ai-sovereignty",
        "ai-security",
        "sovereign-netherlands"
      ]
    }
  },
  "required": [
    "name"
  ],
  "additionalProperties": false
}
🟢get_inventory

Which parts of Agentosaurus you can use today and which are not built yet. Same text as /inventory.txt.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢review_readiness(sector, eu_entity, agents_in_production, annex_iii_use, annex_i_product, ...)

A fixed rule table over your answers that lists the AI Act, DORA, NIS2, GDPR and NEN 7510 items to review, each cited from a public page. Articles to review, not legal advice.

入力スキーマ

{
  "type": "object",
  "properties": {
    "sector": {
      "type": "string",
      "enum": [
        "finance",
        "care",
        "public",
        "other"
      ]
    },
    "eu_entity": {
      "type": "boolean",
      "description": "The organisation is established in the EU."
    },
    "agents_in_production": {
      "type": "boolean",
      "description": "AI agents change production systems or data today."
    },
    "annex_iii_use": {
      "type": "boolean",
      "description": "An AI system is used for an AI Act Annex III purpose, such as hiring or credit scoring."
    },
    "annex_i_product": {
      "type": "boolean",
      "description": "AI is part of a product covered by AI Act Annex I, such as a medical device or machinery."
    },
    "engineers_band": {
      "type": "string",
      "enum": [
        "<50",
        "50-200",
        ">200"
      ],
      "description": "How many engineers the organisation employs."
    }
  },
  "required": [
    "sector",
    "eu_entity",
    "agents_in_production",
    "annex_iii_use",
    "annex_i_product",
    "engineers_band"
  ],
  "additionalProperties": false
}
🟢search_kits(query, category, tier, limit)

Kits and reports on sale in the shop, with price in EUR and the product page to buy from.

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Part of the kit's name."
    },
    "category": {
      "type": "string"
    },
    "tier": {
      "type": "string",
      "enum": [
        "free",
        "premium"
      ]
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10,
      "description": "How many results to return."
    }
  },
  "additionalProperties": false
}
🟢get_kit(slug)

One kit or report on sale, with its price in EUR and the product page to buy from.

入力スキーマ

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "The slug from a search result."
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false
}
🟢esg_report_offer

What a full VerifyAgent ESG due-diligence report contains and costs, with the upgrade and investigate pages.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
⚪signup(email, interest, note)

Registers an email address with Agentosaurus, optionally with an interest. We email the person a link to confirm; nothing is stored as consent until they click it. A person replies after that. Charges nothing. Limited to 5 per hour per address.

入力スキーマ

{
  "type": "object",
  "properties": {
    "email": {
      "type": "string",
      "format": "email"
    },
    "interest": {
      "type": "string",
      "enum": [
        "dataset",
        "pretrain_known",
        "pretrain_novel",
        "finetune_eval",
        "donate",
        "curate"
      ]
    },
    "note": {
      "type": "string",
      "maxLength": 1000,
      "description": "Passed to the person who replies once the address is confirmed, then deleted."
    }
  },
  "required": [
    "email"
  ],
  "additionalProperties": false
}
⚪request_scoping_call(name, email, organisation, message, tier, ...)

Asks Agentosaurus for a scoping call about the Review, the policy gateway (tier policy_gateway, Starter included), LOGOS or sovereign training. We email the person a link to confirm; nothing is stored as consent until they click it. A person replies by email after that. Charges nothing. Limited to 5 per hour per address.

入力スキーマ

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "maxLength": 200
    },
    "email": {
      "type": "string",
      "format": "email"
    },
    "organisation": {
      "type": "string",
      "maxLength": 200
    },
    "message": {
      "type": "string",
      "maxLength": 4000,
      "description": "What you want to achieve."
    },
    "tier": {
      "type": "string",
      "enum": [
        "audit",
        "logos",
        "lab_experiment",
        "policy_gateway",
        "dataset",
        "pretrain_known",
        "pretrain_novel",
        "finetune_eval",
        "hosting",
        "unsure"
      ],
      "default": "unsure"
    },
    "privacy_consent": {
      "type": "boolean",
      "description": "Ignored. Consent comes only from the person clicking the emailed link."
    }
  },
  "required": [
    "name",
    "email",
    "message"
  ],
  "additionalProperties": false
}
🔴request_data_removal(request_type, target_url_or_slug, details, requester_email, on_behalf_of, ...)

Asks Agentosaurus to delete or fix someone's personal data, or to take down an organisation's listing, for the requester or for someone they act for. We email the requester's address a link to confirm; nothing is stored as consent until they click it, and the request is acted on after that. A person reviews it and replies by email within one month; nothing is removed automatically. Returns a reference code only. Limited to 5 per hour per address.

入力スキーマ

{
  "type": "object",
  "properties": {
    "request_type": {
      "type": "string",
      "enum": [
        "remove_personal_data",
        "correct_data",
        "remove_listing",
        "other"
      ]
    },
    "target_url_or_slug": {
      "type": "string",
      "maxLength": 500,
      "description": "The page URL or organisation slug the request is about."
    },
    "details": {
      "type": "string",
      "maxLength": 5000,
      "description": "What to remove or correct."
    },
    "requester_email": {
      "type": "string",
      "format": "email",
      "description": "Where the reply goes."
    },
    "on_behalf_of": {
      "type": "string",
      "maxLength": 300,
      "description": "The person or organisation the requester acts for."
    },
    "submitted_by_agent": {
      "type": "boolean",
      "default": true,
      "description": "An AI agent is sending this request."
    }
  },
  "required": [
    "request_type",
    "target_url_or_slug",
    "details",
    "requester_email"
  ],
  "additionalProperties": false
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 28 件