Skip to main content
Glama

grok-mcp

封装 xAI Grok API 的 MCP 服务器。允许 Claude 和其他 AI 智能体将思考、规划和实时搜索任务委托给 Grok。

设置

npm install -g grok-mcp

或者直接使用 npx:

npx grok-mcp

你需要从 console.x.ai 获取 xAI API 密钥。

在 Claude Code 中配置

添加到你项目的 .mcp.json 中:

{
  "mcpServers": {
    "grok": {
      "type": "stdio",
      "command": "npx",
      "args": ["grok-mcp"],
      "env": {
        "XAI_API_KEY": "your-xai-api-key"
      }
    }
  }
}

工具:ask_grok

支持多种用例的单一工具。

参数

参数

类型

必需

描述

prompt

string

给 Grok 的问题或任务

system_prompt

string

自定义系统提示词

model

string

使用的模型(默认:grok-4.20-reasoning

web_search

boolean

启用实时网页搜索

x_search

boolean

启用 X/Twitter 搜索

可用模型

  • grok-4.20-reasoning — 旗舰推理模型(默认)

  • grok-4.20-non-reasoning — 快速,无推理

  • grok-4.20-multi-agent — 多智能体模式,非常适合架构和规划

  • grok-4.1-fast-reasoning — 更经济的推理模型

  • grok-4.1-fast-non-reasoning — 最便宜,速度快

示例

提问:

prompt: "What are the trade-offs between microservices and monoliths?"

深度架构规划(多智能体):

prompt: "Design a system architecture for a real-time collaborative editor"
model: "grok-4.20-multi-agent"

搜索网页:

prompt: "What happened in tech news today?"
web_search: true

搜索 X/Twitter:

prompt: "What are people saying about the new React release?"
x_search: true

许可证

MIT

-
security - not tested
F
license - not found
-
quality - not tested

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/PKWadsy/grok-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server