mcp

Integrates Wolfram Language and Wolfram|Alpha accessing curated data and sophisticated algorithms.

我该使用它吗

质量与安全性

B
描述质量
100%
模式完整度
100%
命名质量
50%
投毒风险
80%
权限匹配度
100%
协议合规性
100%

发现(5)

  • HIGHTool description contains imperative instruction在 WolframLanguageEvaluator 中
  • HIGHTool poisoning patterns detected
  • LOWTool 'WolframContext' doesn't follow camelCase/snake_case在 WolframContext 中
  • LOWTool 'WolframLanguageEvaluator' doesn't follow camelCase/snake_case在 WolframLanguageEvaluator 中
  • LOWTool 'WolframAlpha' doesn't follow camelCase/snake_case在 WolframAlpha 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~509token 数(工具定义)
~534 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.40%)

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": {
    "mcp": {
      "url": "https://agenttools.wolfram.com/mcp"
    }
  }
}

远程端点

https://agenttools.wolfram.com/mcpstreamable-http

它能做什么

工具清单

工具(3)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢WolframContext(context)

Uses semantic search to retrieve any relevant information from Wolfram. Always use this tool at the start of new conversations or if the topic changes to ensure you have up-to-date relevant information. This uses semantic search, so the context argument should be written in natural language (not a search query) and contain as much detail as possible (up to 250 words).

输入模式

{
  "type": "object",
  "properties": {
    "context": {
      "type": "string",
      "description": "A detailed summary of what the user is trying to achieve or learn about."
    }
  },
  "required": [
    "context"
  ]
}
🟢WolframLanguageEvaluator(code, timeConstraint)

Evaluates Wolfram Language code for the user in a Wolfram Language kernel. If a formatted result is provided as a markdown link, use that in your response instead of typing out the output. Parse natural language input with `\[FreeformPrompt]["query"]`, which is analogous to ctrl+= input in notebooks. Natural language input is parsed before evaluation, so it works like macro expansion. You should ALWAYS use this natural language input to obtain things like `Quantity`, `DateObject`, `Entity`, etc. This is a stateless kernel, so you cannot reuse definitions from previous evaluations.

输入模式

{
  "type": "object",
  "properties": {
    "code": {
      "type": "string",
      "description": "The Wolfram Language code to evaluate."
    },
    "timeConstraint": {
      "type": "number",
      "description": "The time constraint for the evaluation (default is 60 seconds)."
    }
  },
  "required": [
    "code"
  ]
}
🟢WolframAlpha(query)

Use natural language queries with Wolfram|Alpha to get up-to-date computational results about entities in chemistry, physics, geography, history, art, astronomy, and more.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Wolfram Alpha query"
    }
  },
  "required": [
    "query"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本3 个工具
已验证未记录版本3 个工具