MCP security checks — WARDEN and HISTOR

Scan MCP tool definitions for poisoning, look up server history, count tool-list tokens. Free.

使うべきか

品質と安全性

A
説明の品質
95%
スキーマの完全性
93%
命名の品質
80%
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%

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

~740トークン数(ツール定義)
~939 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 0.58%)

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": {
    "mcp-security": {
      "url": "https://modelmarket.dev/tools/mcp/security"
    }
  }
}

リモートエンドポイント

https://modelmarket.dev/tools/mcp/securitystreamable-http

できること

ツール一覧

ツール(4)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢warden_scan(tools, server)

Scan an MCP server's tools/list with WARDEN, the open-source MCP firewall: static rules and a threat list over every name, description, schema and annotation. Returns allow or block and each finding with its rule and severity. Quoted fragments of the scanned text are left out of the answer.

入力スキーマ

{
  "type": "object",
  "properties": {
    "tools": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "The server's tools/list result: [{name, description, inputSchema, ...}]"
    },
    "server": {
      "type": "object",
      "description": "Optional {name, url} to label the verdict"
    }
  },
  "required": [
    "tools"
  ]
}
🟢histor_check(endpoint, name)

Look up an MCP server in HISTOR, a public append-only log of MCP tool sets: when its tool set was first pinned, how often it changed, and what the pattern scan found. HISTOR answers from its own observations and never contacts the server.

入力スキーマ

{
  "type": "object",
  "properties": {
    "endpoint": {
      "type": "string",
      "description": "https URL of the MCP server"
    },
    "name": {
      "type": "string",
      "description": "Or its registry name, e.g. io.github.owner/server"
    }
  }
}
🟢tool_list_cost(tools, server)

How many tokens an MCP server's tool list adds to every model request, what that costs per 1,000 requests, the heaviest tools, and where it sits among 18,204 packages and 16,170 remote servers. Send a tools/list or name a server HISTOR observes.

入力スキーマ

{
  "type": "object",
  "properties": {
    "tools": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "A tools/list result"
    },
    "server": {
      "type": "string",
      "description": "Or a server HISTOR observes: https endpoint, npm:<package>, pypi:<package> or registry name"
    }
  }
}
🟢x402_check(x_payment, requirements, authorization, signature, network)

Check a signed x402 USDC payment before submitting it: recovers the EIP-712 signer, runs USDC's own checks and the seller's terms, and when the signature fails names the domain it was really made for (e.g. Base Sepolia's 'USDC' used on Base, where USDC is 'USD Coin').

入力スキーマ

{
  "type": "object",
  "properties": {
    "x_payment": {
      "type": "string",
      "description": "The X-PAYMENT header (base64)"
    },
    "requirements": {
      "type": "object",
      "description": "The 402's accepts entry: payTo, amount, asset, network"
    },
    "authorization": {
      "type": "object",
      "description": "Instead of x_payment: from, to, value, validAfter, validBefore, nonce"
    },
    "signature": {
      "type": "string",
      "description": "With authorization: the 65-byte hex signature"
    },
    "network": {
      "type": "string",
      "description": "With authorization: base, base-sepolia, … or eip155:<id>"
    }
  }
}

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 4 件