agent-toolbox

13 free utility tools for AI agents: web text, markdown, hashing, IDs, dates, units, JSON.

我该使用它吗

质量与安全性

A
描述质量
92%
模式完整度
80%
命名质量
85%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现(1)

  • LOWTool 'encode_text' description lacks action verb在 encode_text 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~1,000token 数(工具定义)
~483 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.78%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "agent-toolbox": {
      "url": "https://agent-toolbox-mcp.nclexdrill.workers.dev/mcp"
    }
  }
}

远程端点

https://agent-toolbox-mcp.nclexdrill.workers.dev/mcpstreamable-http

它能做什么

工具清单

工具(13)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢fetch_page_text(url, max_chars)

Fetch a web page (http/https) and return its cleaned readable text, truncated to max_chars.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Full http(s) URL to fetch"
    },
    "max_chars": {
      "type": "integer",
      "description": "Max characters to return (default 12000, max 50000)",
      "default": 12000
    }
  },
  "required": [
    "url"
  ]
}
⚪summarize_text(text, sentences)

Extractive summary: returns the N most representative sentences of a text, in original order.

输入模式

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    },
    "sentences": {
      "type": "integer",
      "description": "Number of sentences (default 3, max 10)",
      "default": 3
    }
  },
  "required": [
    "text"
  ]
}
⚪markdown_to_html(markdown)

Convert Markdown to HTML (headings, bold, italic, code, links, lists, quotes).

输入模式

{
  "type": "object",
  "properties": {
    "markdown": {
      "type": "string"
    }
  },
  "required": [
    "markdown"
  ]
}
⚪html_to_text(html, max_chars)

Strip HTML tags/scripts/styles and return clean readable text.

输入模式

{
  "type": "object",
  "properties": {
    "html": {
      "type": "string"
    },
    "max_chars": {
      "type": "integer",
      "default": 12000
    }
  },
  "required": [
    "html"
  ]
}
🟢hash_text(text, algorithm)

Compute a cryptographic hash of text (sha-256, sha-384, or sha-512), returned as hex.

输入模式

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    },
    "algorithm": {
      "type": "string",
      "enum": [
        "sha-256",
        "sha-384",
        "sha-512"
      ],
      "default": "sha-256"
    }
  },
  "required": [
    "text"
  ]
}
⚪encode_text(text, format)

Encode text as base64, base64url, url-encoding, or hex.

输入模式

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    },
    "format": {
      "type": "string",
      "enum": [
        "base64",
        "base64url",
        "url",
        "hex"
      ],
      "default": "base64"
    }
  },
  "required": [
    "text"
  ]
}
⚪uuid_generate(count)

Generate cryptographically random UUID v4 values.

输入模式

{
  "type": "object",
  "properties": {
    "count": {
      "type": "integer",
      "description": "How many (1-100, default 1)",
      "default": 1
    }
  }
}
🟡date_math(operation, date, date1, date2, value, ...)

Date utilities: now (current UTC time), add (add a duration to a date), diff (difference between two dates), weekday (day name for a date).

输入模式

{
  "type": "object",
  "properties": {
    "operation": {
      "type": "string",
      "enum": [
        "now",
        "add",
        "diff",
        "weekday"
      ],
      "default": "now"
    },
    "date": {
      "type": "string",
      "description": "ISO date for add/weekday"
    },
    "date1": {
      "type": "string"
    },
    "date2": {
      "type": "string"
    },
    "value": {
      "type": "number",
      "description": "Amount for add"
    },
    "unit": {
      "type": "string",
      "description": "millisecond/second/minute/hour/day/week",
      "default": "day"
    }
  }
}
⚪unit_convert(value, from, to)

Convert between units: length (mm/cm/m/km/in/ft/yd/mi), weight (mg/g/kg/oz/lb), temperature (c/f/k), data (b/kb/mb/gb/tb).

输入模式

{
  "type": "object",
  "properties": {
    "value": {
      "type": "number"
    },
    "from": {
      "type": "string"
    },
    "to": {
      "type": "string"
    }
  },
  "required": [
    "value",
    "from",
    "to"
  ]
}
⚪json_format(json, style)

Validate JSON and reformat it: pretty (indented), minify, or custom indent width.

输入模式

{
  "type": "object",
  "properties": {
    "json": {
      "type": "string"
    },
    "style": {
      "type": "string",
      "description": "'pretty', 'minify', or an indent number",
      "default": "pretty"
    }
  },
  "required": [
    "json"
  ]
}
⚪text_stats(text)

Text statistics: character/word/sentence counts, reading time, and Flesch reading-ease score.

输入模式

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    }
  },
  "required": [
    "text"
  ]
}
⚪random_token(length, charset)

Generate a cryptographically random token string (for ids, passwords, nonces).

输入模式

{
  "type": "object",
  "properties": {
    "length": {
      "type": "integer",
      "default": 32
    },
    "charset": {
      "type": "string",
      "description": "alphanumeric, hex, urlsafe, numeric, ascii, or a custom character string",
      "default": "alphanumeric"
    }
  }
}
🟢get_terms

Read the AgentToolbox Terms of Use (as-is, liability-capped). Call this before relying on any tool in production.

输入模式

{
  "type": "object",
  "properties": {}
}

社区

评价此服务器

证据

最近观测

已验证未记录版本13 个工具