Grok MCP Plugin

@Bob-lance

代码仓库

基本信息

分类

开发工具

许可证

MIT

传输方式

stdio

作者

Bob-lance

关于 Grok MCP Plugin

MCP server for Grok AI API integration

Grok MCP Plugin 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "grok-mcp": {
      "command": "node",
      "args": [
        "build/index.js"
      ],
      "env": {
        "XAI_API_KEY": "your-grok-api-key"
      }
    }
  }
}

Grok MCP Plugin 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Grok MCP Plugin?

Grok MCP Plugin is a Model Context Protocol (MCP) server that provides seamless access to Grok AI’s chat, vision, and function‑calling capabilities directly from Cline. It is built for developers using Cline with MCP support who want to integrate Grok AI into their workflows.

How to use Grok MCP Plugin?

Install Node.js (v16+), obtain a Grok AI API key from console.x.ai, and ensure Cline has MCP support. Clone the repo, run npm install && npm run build, then add the MCP server configuration to your Cline MCP settings (e.g., ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json). Use the three exposed tools via Cline’s <use_mcp_tool> syntax.

Key features of Grok MCP Plugin

Chat completion with Grok language models
Image understanding using Grok’s vision capabilities
Function calling based on user input
Supports both image URLs and base64‑encoded images
Configurable temperature, max tokens, and model selection

Use cases of Grok MCP Plugin

Generate text responses from Grok AI inside Cline
Analyze images with natural language prompts
Automate tasks by having Grok invoke external functions
Build AI‑powered assistants integrated with Cline

常见问题

What are the prerequisites to use this plugin?

Node.js v16 or higher, a Grok AI API key from console.x.ai, and Cline with MCP support.

How do I configure the plugin’s API key?

Set the `XAI_API_KEY` environment variable in your Cline MCP settings configuration under the `env` object.

What tools does the plugin expose?

Three tools: `chat_completion` for text generation, `image_understanding` for vision analysis, and `function_calling` for invoking functions.

Can I provide images as base64 instead of a URL?

Yes. Use the `base64_image` parameter (without the `data:image` prefix) instead of `image_url`.

What models are used by default?

Chat completion defaults to `grok-3-mini-beta`, image understanding defaults to `grok-2-vision-latest`. Both can be overridden.

开发工具分类下的更多 MCP 服务器

Kilobat

seifip

Open-source Mac network diagnostics for AI agents and humans. Check connectivity, Wi-Fi, hotspots and traffic from the terminal or MCP.

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Mcp-Warden

ermoluk

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

DocBin

Give an agent a place to put large output. Instead of returning 40k characters of a build log into the conversation, it posts the file to DocBin and hands back one short URL. Docs render with syntax highlighting and mark

Official Porkbun MCP Server

Porkbun LLC

Official Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac