A
security-
licenseA
qualityEnables AI assistants to interact with Figma files through the ModelContextProtocol, allowing viewing, commenting, and analyzing Figma designs directly in chat interfaces.
Last updated -
5
568
202
Mentioned only as the repository location, not as a service the MCP integrates with
Used for code examples, but not a service the MCP integrates with
Required as a runtime environment for the MCP server, but not a service the MCP integrates with
Grok MCP Plugin
A Model Context Protocol (MCP) plugin that provides seamless access to Grok AI's powerful capabilities directly from Cline.
Features
This plugin exposes three powerful tools through the MCP interface:
Chat Completion - Generate text responses using Grok's language models
Image Understanding - Analyze images with Grok's vision capabilities
Function Calling - Use Grok to call functions based on user input
Prerequisites
Node.js (v16 or higher)
A Grok AI API key (obtain from console.x.ai)
Cline with MCP support
Installation
Clone this repository:
git clone https://github.com/Bob-lance/grok-mcp.git cd grok-mcpInstall dependencies:
npm installBuild the project:
npm run buildAdd the MCP server to your Cline MCP settings:
For VSCode Cline extension, edit the file at:
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.jsonAdd the following configuration:
{ "mcpServers": { "grok-mcp": { "command": "node", "args": ["/path/to/grok-mcp/build/index.js"], "env": { "XAI_API_KEY": "your-grok-api-key" }, "disabled": false, "autoApprove": [] } } }Replace
/path/to/grok-mcpwith the actual path to your installation andyour-grok-api-keywith your Grok AI API key.
Usage
Once installed and configured, the Grok MCP plugin provides three tools that can be used in Cline:
Chat Completion
Generate text responses using Grok's language models:
<use_mcp_tool>
<server_name>grok-mcp</server_name>
<tool_name>chat_completion</tool_name>
<arguments>
{
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello, what can you tell me about Grok AI?"
}
],
"temperature": 0.7
}
</arguments>
</use_mcp_tool>
Image Understanding
Analyze images with Grok's vision capabilities:
<use_mcp_tool>
<server_name>grok-mcp</server_name>
<tool_name>image_understanding</tool_name>
<arguments>
{
"image_url": "https://example.com/image.jpg",
"prompt": "What is shown in this image?"
}
</arguments>
</use_mcp_tool>
You can also use base64-encoded images:
<use_mcp_tool>
<server_name>grok-mcp</server_name>
<tool_name>image_understanding</tool_name>
<arguments>
{
"base64_image": "base64-encoded-image-data",
"prompt": "What is shown in this image?"
}
</arguments>
</use_mcp_tool>
Function Calling
Use Grok to call functions based on user input:
<use_mcp_tool>
<server_name>grok-mcp</server_name>
<tool_name>function_calling</tool_name>
<arguments>
{
"messages": [
{
"role": "user",
"content": "What's the weather like in San Francisco?"
}
],
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The unit of temperature to use"
}
},
"required": ["location"]
}
}
}
]
}
</arguments>
</use_mcp_tool>
API Reference
Chat Completion
Generate a response using Grok AI chat completion.
Parameters:
messages(required): Array of message objects with role and contentmodel(optional): Grok model to use (defaults to grok-2-latest)temperature(optional): Sampling temperature (0-2, defaults to 1)max_tokens(optional): Maximum number of tokens to generate (defaults to 16384)
Image Understanding
Analyze images using Grok AI vision capabilities.
Parameters:
prompt(required): Text prompt to accompany the imageimage_url(optional): URL of the image to analyzebase64_image(optional): Base64-encoded image data (without the data:image prefix)model(optional): Grok vision model to use (defaults to grok-2-vision-latest)
Note: Either image_url or base64_image must be provided.
Function Calling
Use Grok AI to call functions based on user input.
Parameters:
messages(required): Array of message objects with role and contenttools(required): Array of tool objects with type, function name, description, and parameterstool_choice(optional): Tool choice mode (auto, required, none, defaults to auto)model(optional): Grok model to use (defaults to grok-2-latest)
Development
Project Structure
src/index.ts- Main server implementationsrc/grok-api-client.ts- Grok API client implementation
Building
npm run build
Running
XAI_API_KEY="your-grok-api-key" node build/index.js
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgements
Related MCP Servers
- Asecurity-licenseAqualityA Model Context Protocol server that provides AI assistants with access to Glean's enterprise knowledge features, including content search, people directory, and AI chat capabilities.Last updated -3150MIT License
- -security-license-qualityEnables AI assistants to interact with Slack workspaces through the Model Context Protocol, providing tools for reading/sending messages, managing channels, and accessing Slack API functionality.
- AsecurityAlicenseAqualityEnables interaction with the Grok AI through an MCP server, supporting chat completions, text completions, embeddings, and model operations with streaming capabilities.Last updated -5307MIT License