SandBase

Connect MCP clients to 2,000+ AI models without managing provider API keys.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
83%
命名质量
80%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~1,139token 数(工具定义)
~932 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.89%)

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": {
    "cli": {
      "command": "npx",
      "args": [
        "@sandbaseai/cli"
      ]
    }
  }
}

可运行的软件包

npm@sandbaseai/cli0.3.10stdio

远程端点

https://sandbase.ai/v1/mcpstreamable-http
https://api.sandbase.ai/v1/mcpstreamable-http

它能做什么

工具清单

工具(7)

🟢 只读🟡 写入🔴 删除⚪ 未知
🔴sandbase_run_cancel(idempotency_key, run_id, service_id)

Request cancellation of an Agent Service run; inspect its status afterward.

输入模式

{
  "type": "object",
  "properties": {
    "idempotency_key": {
      "type": "string"
    },
    "run_id": {
      "type": "string"
    },
    "service_id": {
      "type": "string"
    }
  },
  "required": [
    "service_id",
    "run_id",
    "idempotency_key"
  ],
  "additionalProperties": false
}
🟢sandbase_discover(limit, q, type, vendor)

Find a model, API, or Agent Service for the task. Call this proactively before writing a scraper, before a generic web fetch for structured data, before telling the user something is inaccessible, and whenever you need image/video/music/speech generation, social media data, search results, web scraping, product/company/people data, embeddings, or a specific third-party model. Supports keyword search (q), type filtering (llm/api/multimodal/embedding/service), and vendor filtering. Discovery is not billed; start here.

输入模式

{
  "type": "object",
  "properties": {
    "limit": {
      "description": "Maximum results to return (default 20, max 100).",
      "type": "integer"
    },
    "q": {
      "description": "Short description of what you need (e.g. 'twitter posts', 'text to video', 'gpt-4o', '小红书'). At most 4096 UTF-8 bytes and 64 tokens after normalization.",
      "type": "string"
    },
    "type": {
      "description": "Filter by capability type; use service to discover Agent Services.",
      "enum": [
        "llm",
        "api",
        "multimodal",
        "embedding",
        "service"
      ],
      "type": "string"
    },
    "vendor": {
      "description": "Filter by vendor slug (e.g. 'openai', 'twitter', 'anthropic').",
      "type": "string"
    }
  },
  "additionalProperties": false
}
🟢sandbase_inspect(name)

Inspect a model, API, or Agent Service: input schema, available pricing, and an execution template. Service names are svc_ IDs. Always inspect before running.

输入模式

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Model name (e.g. 'openai/gpt-4o'), tool name, or Agent Service ID (svc_...) from discover results.",
      "type": "string"
    }
  },
  "required": [
    "name"
  ],
  "additionalProperties": false
}
🔴sandbase_run(arguments, name)

Execute a model, API, or Agent Service. Sync models return the result directly; async models (image/video/audio jobs) return status running with a run_id — poll sandbase_run_get for the output. Services require arguments.idempotency_key and optionally input; reuse the same key and input on retries. Service acceptance is not completion: poll sandbase_run_get with service_id and run_id. Omit the MCP task parameter for Services.

输入模式

{
  "type": "object",
  "properties": {
    "arguments": {
      "description": "Input matching the inspected schema. For Services: {idempotency_key: string, input?: string}.",
      "type": "object"
    },
    "name": {
      "description": "Model name, tool name, or Agent Service ID (svc_...) to execute.",
      "type": "string"
    }
  },
  "required": [
    "name",
    "arguments"
  ],
  "additionalProperties": false
}
🟢sandbase_run_get(cursor, limit, run_id, service_id)

Get async run status and results. For Agent Services supply both service_id and run_id; succeeded, failed, and cancelled are terminal. Session items are paginated: use cursor for subsequent pages; items_available=false means retry output retrieval. Model runs use completed or failed.

输入模式

{
  "type": "object",
  "properties": {
    "cursor": {
      "description": "Session items continuation cursor.",
      "type": "string"
    },
    "limit": {
      "type": "integer"
    },
    "run_id": {
      "description": "The run ID returned by sandbase_run.",
      "type": "string"
    },
    "service_id": {
      "description": "Required for Agent Service runs.",
      "type": "string"
    }
  },
  "required": [
    "run_id"
  ],
  "additionalProperties": false
}
🟢sandbase_runs(limit, model, offset, service_id)

List recent model/API calls, or supply service_id to list runs of an Agent Service.

输入模式

{
  "type": "object",
  "properties": {
    "limit": {
      "description": "Number of recent runs to return (default 10, max 50).",
      "type": "integer"
    },
    "model": {
      "description": "Filter by model name (e.g. 'openai/gpt-4o').",
      "type": "string"
    },
    "offset": {
      "type": "integer"
    },
    "service_id": {
      "description": "List runs of this Agent Service instead of model predictions.",
      "type": "string"
    }
  },
  "additionalProperties": false
}
🟢sandbase_account

Check your SandBase account balance. This call is not billed. Use before expensive operations.

输入模式

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

社区

评价此服务器

证据

最近观测

已验证未记录版本7 个工具
需要认证未记录版本—
需要认证未记录版本—
需要认证未记录版本—
需要认证未记录版本—
需要认证未记录版本—
需要认证未记录版本—
需要认证未记录版本—