Integration

xAI integration

AI API from xAI (Elon Musk's AI company) powering Grok models. Access state-of-the-art language models with reasoning, coding, and vision capabilities, plus the Grok Imagine suite for image and video generation. OpenAI-compatible API with built-in web search and code execution. Perfect for AI applications, chatbots, and generative media pipelines.

Connect xAI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in xAI.Built from the 11 xAI tools below, on the connection you add once.

Common xAI use cases

Capability check
Cleanup
Chatbots
Model info
Fine-tuning
Real-time info
File management
Model discovery
Generate marketing visuals from a brief
Swap product backgrounds for catalog shots

What you can do with xAI

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

File, 3 operations

delete_fileDelete fileDELETEDeletes an uploaded file.
list_filesList filesGETLists all uploaded files.
upload_fileUpload filePOSTUploads a file for use with the API.

Image, 2 operations

edit_imageEdit imagePOSTEdits an existing image from a natural-language instruction.
generate_imageGenerate imagePOSTGenerates images from a text prompt using Grok Imagine.

Model, 2 operations

get_modelGet modelGETRetrieves details of a specific model.
list_modelsList modelsGETLists all available Grok models.

Video, 2 operations

generate_videoGenerate videoPOSTGenerates a video from a text prompt or a start image using Grok Imagine.
get_videoGet videoGETRetrieves the status and download URL of a video generation job.

Completion, 1 operation

create_chat_completionCreate chat completionPOSTGenerates a chat completion using Grok models.

Tool response, 1 operation

create_responseCreate responsePOSTCreates a response with server-side tools.

Use xAI from Claude Code, Cursor or Codex

Connect xAI in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its xAI operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect xAI

Create your workspace
Sign up free. Nothing to install.
Connect xAI once
Add your xAI connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.