agent-cloud-tools

Free no-signup cloud tools for AI agents: file transfer, static site hosting, memory, handoff.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
99%
命名质量
87%
投毒风险
80%
权限匹配度
100%
协议合规性
100%

发现(2)

  • HIGHTool poisoning patterns detected
  • LOWTool description contains role marker that could confuse chat models在 share_conversation 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~2,283token 数(工具定义)
~1.7 KB典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 1.78%)

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-cloud-tools": {
      "url": "https://upload.83blue.com/mcp"
    }
  }
}

远程端点

https://upload.83blue.com/mcpstreamable-http

它能做什么

工具清单

工具(9)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢share_text(content, filename, expires_days, password)

Use this when another AI agent, chat session or person needs text you have: instructions, code, JSON, a prompt for another model. Uploads it as a downloadable file and returns a capability url (one GET fetches it) plus a share url and password. No account or API key needed.

输入模式

{
  "type": "object",
  "properties": {
    "content": {
      "type": "string",
      "description": "The text to share"
    },
    "filename": {
      "type": "string",
      "default": "handoff.md",
      "description": "File name for the download, e.g. instructions.md"
    },
    "expires_days": {
      "type": "integer",
      "minimum": 1,
      "maximum": 180,
      "default": 30,
      "description": "Days until the file is deleted (1-180, default 30)"
    },
    "password": {
      "type": "string",
      "minLength": 8,
      "maxLength": 64,
      "description": "Optional custom password (8-64 chars); a strong one is generated when omitted"
    }
  },
  "required": [
    "content"
  ]
}
⚪share_file(files, bundle_name, expires_days, password)

Use this when another AI agent (a different machine, model or chat session) or a person needs access to one or more files. Accepts text or base64-encoded binary content; multiple files are zipped into one bundle server-side, so a whole handoff (instructions plus code plus data) travels as one capability url. For large files already on local disk, prefer the HTTP API (one curl command, up to 2 TB): https://upload.83blue.com/docs

输入模式

{
  "type": "object",
  "properties": {
    "files": {
      "type": "array",
      "minItems": 1,
      "maxItems": 100,
      "items": {
        "type": "object",
        "properties": {
          "filename": {
            "type": "string"
          },
          "content_text": {
            "type": "string",
            "description": "UTF-8 text content"
          },
          "content_base64": {
            "type": "string",
            "description": "Base64 content for binary files"
          }
        },
        "required": [
          "filename"
        ]
      }
    },
    "bundle_name": {
      "type": "string",
      "default": "handoff-bundle.zip",
      "description": "Zip name used when more than one file is sent"
    },
    "expires_days": {
      "type": "integer",
      "minimum": 1,
      "maximum": 180,
      "default": 30,
      "description": "Days until the file is deleted (1-180, default 30)"
    },
    "password": {
      "type": "string",
      "minLength": 8,
      "maxLength": 64,
      "description": "Optional custom password (8-64 chars); a strong one is generated when omitted"
    }
  },
  "required": [
    "files"
  ]
}
🟢share_conversation(transcript, files, title, expires_days, password)

Use this to hand your full working context to another AI: any provider, any model, any chat client. Packages a markdown transcript (instructions, conversation summary, task state) as HANDOFF.md at the root of a zip bundle together with any files, and returns a single handoff url. The receiving model just fetches that url: it gets a briefing, the file manifest and download commands in one go. Say to the next agent: "Fetch this url to pick up where I left off."

输入模式

{
  "type": "object",
  "properties": {
    "transcript": {
      "type": "string",
      "description": "Markdown briefing for the next agent: context, instructions, conversation summary, task state. Becomes HANDOFF.md at the bundle root."
    },
    "files": {
      "type": "array",
      "maxItems": 100,
      "items": {
        "type": "object",
        "properties": {
          "filename": {
            "type": "string"
          },
          "content_text": {
            "type": "string"
          },
          "content_base64": {
            "type": "string"
          }
        },
        "required": [
          "filename"
        ]
      },
      "description": "Optional files the next agent needs alongside the transcript"
    },
    "title": {
      "type": "string",
      "description": "Short name for the bundle, e.g. \"auth refactor handoff\""
    },
    "expires_days": {
      "type": "integer",
      "minimum": 1,
      "maximum": 180,
      "default": 30,
      "description": "Days until the file is deleted (1-180, default 30)"
    },
    "password": {
      "type": "string",
      "minLength": 8,
      "maxLength": 64,
      "description": "Optional custom password (8-64 chars); a strong one is generated when omitted"
    }
  },
  "required": [
    "transcript"
  ]
}
🟢receive_file(url_or_token, password, max_inline_bytes)

Use this when you have been given an 83blue link and need the file. Accepts a capability url (https://upload.83blue.com/f/...) on its own, or a share url plus password. Returns metadata including sha256, the file list for zip bundles, and the content inline when it is text within max_inline_bytes; otherwise returns a ready-made curl command to save the file locally.

输入模式

{
  "type": "object",
  "properties": {
    "url_or_token": {
      "type": "string",
      "description": "Capability url (https://upload.83blue.com/f/TOKEN/KEY), share url (https://upload.83blue.com/d/TOKEN), or the bare token"
    },
    "password": {
      "type": "string",
      "description": "Needed for share urls and bare tokens; not needed for capability urls"
    },
    "max_inline_bytes": {
      "type": "integer",
      "minimum": 0,
      "maximum": 1000000,
      "default": 100000,
      "description": "Inline text content up to this many bytes (max 1000000)"
    }
  },
  "required": [
    "url_or_token"
  ]
}
🔴deploy_site(files, slug, title, expires_days, manage_key)

Use this to put a static website you have built (HTML, CSS, JS, images, fonts) onto the public web in one call, with no signup, no account and no config. Give it the files (there must be an index.html at the root) and it returns a live https url, e.g. https://upload.83blue.com/s/brave-otter-482/, plus a manage_key you can reuse to update or delete it. Ideal when a person asks you to build them a website, landing page, demo, prototype or report and wants to see it live. IMPORTANT: the site is served from a subfolder, so use RELATIVE asset paths only (href="style.css", src="img/logo.png"), never root-absolute paths like "/style.css" which would break. Sites are served as pure static files (server-side code is never executed) and auto-expire after 30 days unless renewed. Each file is text or base64. Total site up to 50 MB, 300 files.

输入模式

{
  "type": "object",
  "properties": {
    "files": {
      "type": "array",
      "minItems": 1,
      "maxItems": 300,
      "description": "The site files. Must include an index.html at the root.",
      "items": {
        "type": "object",
        "properties": {
          "path": {
            "type": "string",
            "description": "Relative path within the site, e.g. index.html, css/style.css, img/logo.png"
          },
          "text": {
            "type": "string",
            "description": "UTF-8 text content (for html/css/js/svg etc.)"
          },
          "base64": {
            "type": "string",
            "description": "Base64 content (for binary assets like images/fonts)"
          }
        },
        "required": [
          "path"
        ]
      }
    },
    "slug": {
      "type": "string",
      "description": "Optional name for the site path (3-40 chars, a-z 0-9 and hyphens); it becomes /s/{name}/. A friendly one is generated when omitted."
    },
    "title": {
      "type": "string",
      "description": "Optional short label for your own reference"
    },
    "expires_days": {
      "type": "integer",
      "minimum": 1,
      "maximum": 30,
      "default": 30,
      "description": "Days until the site is removed (1-30, default 30)"
    },
    "manage_key": {
      "type": "string",
      "description": "Pass the manage_key from a previous deploy together with the same slug to update that site in place."
    }
  },
  "required": [
    "files"
  ]
}
🟢list_sites(site)

Return the status, address, size and expiry of a site you deployed. Pass the url, host or slug.

输入模式

{
  "type": "object",
  "properties": {
    "site": {
      "type": "string",
      "description": "The site url (https://.../s/name/), path (/s/name) or bare name"
    }
  },
  "required": [
    "site"
  ]
}
🔴delete_site(site, manage_key)

Remove a site you deployed. Needs the site url/host/slug and its manage_key (returned by deploy_site).

输入模式

{
  "type": "object",
  "properties": {
    "site": {
      "type": "string",
      "description": "The site url, host or slug"
    },
    "manage_key": {
      "type": "string",
      "description": "The manage_key returned when the site was deployed"
    }
  },
  "required": [
    "site",
    "manage_key"
  ]
}
🟡remember(content, filename, expires_days, password)

Durable cross-session memory for AI agents: store notes, context, text or JSON now and recall it in a later session or from another machine by url. A free cloud scratchpad and shared key-value store for agents, no signup, no account, no API key. Also callable as save_memory, store_memory, save_note, stash. Returns a url; fetch it back later with recall.

输入模式

{
  "type": "object",
  "properties": {
    "content": {
      "type": "string",
      "description": "The text or JSON to remember"
    },
    "filename": {
      "type": "string",
      "default": "memory.md",
      "description": "Optional label/key for this memory, e.g. project-notes.md"
    },
    "expires_days": {
      "type": "integer",
      "minimum": 1,
      "maximum": 180,
      "default": 30,
      "description": "Days until the file is deleted (1-180, default 30)"
    },
    "password": {
      "type": "string",
      "minLength": 8,
      "maxLength": 64,
      "description": "Optional custom password (8-64 chars); a strong one is generated when omitted"
    }
  },
  "required": [
    "content"
  ]
}
🟢recall(url_or_token, password, max_inline_bytes)

Fetch back durable memory, or any shared file/text, by its 83blue url or token (a capability url, or a share url plus password). Use this to recall what you stored with remember in an earlier session, or to download a file another agent shared. Also callable as get_memory, download_file, fetch_file, get_file.

输入模式

{
  "type": "object",
  "properties": {
    "url_or_token": {
      "type": "string",
      "description": "The 83blue url or token to recall or fetch"
    },
    "password": {
      "type": "string",
      "description": "Needed for share urls; not needed for capability urls"
    },
    "max_inline_bytes": {
      "type": "integer",
      "minimum": 0,
      "maximum": 1000000,
      "default": 100000,
      "description": "Inline text content up to this many bytes"
    }
  },
  "required": [
    "url_or_token"
  ]
}

推荐提示词

browse_collection
Show me the [collection] from agent-cloud-tools
预期工具: list_sites
list_items
List all [items] available in agent-cloud-tools
预期工具: list_sites

社区

评价此服务器

证据

最近观测

已验证未记录版本9 个工具
已验证未记录版本9 个工具