ThirdMade Shelf

26 pay-per-call tools for agents: scrape, verify, guards, crypto. x402 USDC on Base.

使うべきか

品質と安全性

A
説明の品質
92%
スキーマの完全性
99%
命名の品質
82%
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(2)

  • LOWTool 'gas_now' description lacks action verbgas_now 内
  • LOWTool 'image_status' description lacks action verbimage_status 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

~2,066トークン数(ツール定義)
~362 B一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 1.61%)

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": {
    "shelf": {
      "url": "https://shelf.thirdmade.net/mcp"
    }
  }
}

リモートエンドポイント

https://shelf.thirdmade.net/mcpstreamable-http

できること

ツール一覧

ツール(26)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢robots(url)

Parses robots.txt for any domain — shows crawl rules, disallowed paths, sitemaps. Agents use this to check if they're allowed to scrape a site before doing it. [free]

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target webpage URL"
    }
  },
  "required": [
    "url"
  ]
}
⚪llms_txt(url)

Fetches and normalizes llms.txt / llms-full.txt from any site — the emerging standard for making websites readable to AI agents. [free]

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target webpage URL"
    }
  },
  "required": [
    "url"
  ]
}
⚪page_meta(url)

Extracts OG tags, canonical URL, title, and meta description from any web page. Useful for link previews, SEO audits, and content enrichment. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target webpage URL"
    }
  },
  "required": [
    "url"
  ]
}
🟢domain_facts(domain)

Live-checks a domain: is it up, does it have TLS, what's the title? Quick domain health check for agents evaluating links. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Domain name"
    }
  },
  "required": [
    "domain"
  ]
}
⚪link_graph(url)

Extracts all outbound links from a page, classified by domain. Shows where a page links to and which domains dominate. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target webpage URL"
    }
  },
  "required": [
    "url"
  ]
}
⚪scrape(url)

Scrapes any public web page and returns clean structured JSON (title, text, length). The workhorse — agents use this for real data extraction. [price: $0.01/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Target webpage URL"
    }
  },
  "required": [
    "url"
  ]
}
⚪captcha_eval(type)

Classifies captcha type (reCAPTCHA, hCaptcha, Turnstile) and difficulty. Eval only — we do NOT solve captchas. [price: $0.01/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string",
      "description": "Captcha type: recaptcha, hcaptcha, turnstile, image, slider, puzzle"
    }
  }
}
⚪geo_time(q)

Geocode + timezone + currency context for any location string. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Location string"
    }
  },
  "required": [
    "q"
  ]
}
🟢entity_find(text)

Extracts named entities (people, companies, places) from text. Wikidata resolution next iteration. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "Input text"
    }
  },
  "required": [
    "text"
  ]
}
🟢search_verify(url, claim)

Checks if a URL supports a claim. Returns confidence score. Research agents use this to verify sources. [price: $0.01/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Source URL"
    },
    "claim": {
      "type": "string",
      "description": "Claim to verify"
    }
  },
  "required": [
    "url",
    "claim"
  ]
}
⚪similar_domains(domain)

Finds similar/competitor domains by name-similarity. Lead-gen agents use this for prospecting. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Domain name"
    }
  },
  "required": [
    "domain"
  ]
}
⚪gas_now(chain)

Current gas prices in Gwei for Base, Ethereum, or Arbitrum via public RPC. [free]

入力スキーマ

{
  "type": "object",
  "properties": {
    "chain": {
      "type": "string",
      "description": "base (default), ethereum, or arbitrum"
    }
  }
}
⚪chain_stats(chain)

Block height + chain stats for Base or Ethereum. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "chain": {
      "type": "string",
      "description": "base (default), ethereum, or arbitrum"
    }
  }
}
⚪nonce(address, chain)

Current transaction nonce for any address on Base or Ethereum. Agent tx bots need this before sending transactions. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "address": {
      "type": "string",
      "description": "EVM address"
    },
    "chain": {
      "type": "string",
      "description": "base (default) or ethereum"
    }
  },
  "required": [
    "address"
  ]
}
⚪token_security(address, chain)

Token security heuristics: honeypot signals, proxy detection, LP data. Trading agents use this to avoid rugs. [price: $0.01/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "address": {
      "type": "string",
      "description": "Token contract address"
    },
    "chain": {
      "type": "string",
      "description": "base (default)"
    }
  },
  "required": [
    "address"
  ]
}
⚪ens_lookup(name)

ENS name resolution + reverse lookup via public Ethereum RPC. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "ENS name or address"
    }
  },
  "required": [
    "name"
  ]
}
⚪summarize(text)

Extractive summary (3 sentences) + top-5 keywords from any text. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "Input text"
    }
  },
  "required": [
    "text"
  ]
}
⚪jsonify(text)

Coerces messy text (key=value lines, CSV-ish, sentences) into clean JSON. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "Input text"
    }
  },
  "required": [
    "text"
  ]
}
⚪sentiment(text)

Sentiment classification (positive/negative/neutral) + emotion keyword hits. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "Input text"
    }
  },
  "required": [
    "text"
  ]
}
⚪image_gen(prompt)

Generates 1 PNG from a text prompt (FLUX.1-dev, 512px). Async: returns job ID + poll URL. GPU-backed via RunPod ComfyUI, scale-to-zero. [price: $0.02/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Image prompt"
    }
  },
  "required": [
    "prompt"
  ]
}
⚪image_status(job)

Poll image-gen job status by job ID. Returns image base64 PNG when COMPLETED. [free]

入力スキーマ

{
  "type": "object",
  "properties": {
    "job": {
      "type": "string",
      "description": "Job ID from image_gen"
    }
  },
  "required": [
    "job"
  ]
}
⚪pii_guard(text)

Detects PII (emails, phones, SSNs, credit cards) in any text with character spans. Compliance agents use this before processing user data. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "Input text"
    }
  },
  "required": [
    "text"
  ]
}
⚪prompt_guard(text)

Scores prompt-injection / jailbreak risk for LLM inputs. Agent builders use this to sanitize user inputs before hitting their LLM. [price: $0.01/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "Input text"
    }
  },
  "required": [
    "text"
  ]
}
🟢hallucination_check(context, claim)

Entailment scoring: does the provided context support this claim? Research agents use this to self-check outputs. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "Evidence/context text"
    },
    "claim": {
      "type": "string",
      "description": "Claim to check"
    }
  },
  "required": [
    "context",
    "claim"
  ]
}
⚪json_guard(json)

Validates JSON, detects PII inside values, reports schema stats. Pipeline agents use this as a data-quality gate. [price: $0.001/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "json": {
      "type": "string",
      "description": "JSON text to validate"
    }
  },
  "required": [
    "json"
  ]
}
⚪sweep(topic)

One verify-loop lane: confidence-labeled findings on any topic. The flagship teaser — full sweeps at $0.50-5 ship when this crosses BUILD. [price: $0.05/call USDC via x402]

入力スキーマ

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "Research topic"
    }
  },
  "required": [
    "topic"
  ]
}

推奨プロンプト

search_research
Search for information about [topic] using ThirdMade Shelf
想定されるツール: entity_find
find_specific
Find [specific item] using ThirdMade Shelf
想定されるツール: entity_find

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 26 件
検証済みバージョンは記録されていませんツール 26 件
検証済みバージョンは記録されていませんツール 26 件
検証済みバージョンは記録されていませんツール 26 件
検証済みバージョンは記録されていませんツール 26 件
検証済みバージョンは記録されていませんツール 26 件
検証済みバージョンは記録されていませんツール 26 件