Integration

Deep-Image.ai integration

Deep-Image.ai is an AI image enhancement API. Upscale an image (by percentage or to a pixel size), denoise, deblur, fix lighting, colors and white balance, enhance faces, remove, replace or generate a background, resize with padding or cropping, apply real-estate or e-commerce presets, and export as JPEG, PNG or WebP. Jobs can run in one call that waits up to 25 seconds, or be scheduled and awaited; finished results can be read or deleted, and the account's credit balance read. Each processed image consumes Deep-Image credits from the account's plan. Uploading a local file (form-data) and the cloud storage connectors are not exposed: pass a public image URL or base64 data. Authentication is an API key from the Deep-Image profile (API page), sent in the X-API-KEY header.

Connect Deep-Image.ai How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Deep-Image.ai.Built from the 5 Deep-Image.ai tools below, on the connection you add once.

What you can do with Deep-Image.ai

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.

Image, 2 operations

process_imageProcess imagePOSTProcesses an image as a scheduled job, for work that may exceed 25 seconds, and returns the finished job with result_url. Billed: consumes Deep-Image credits per image. Waits for the job and returns the finished result; gives up after 10 minutes.
process_image_and_waitProcess image and waitPOSTProcesses an image and waits up to 25 seconds: returns result_url when status is complete, else the job id to read later with get_job_result. Billed: consumes Deep-Image credits per image.

Job, 2 operations

delete_job_resultDelete job resultDELETEDeletes the processed images of a completed job from Deep-Image storage. Irreversible: result_url stops working.
get_job_resultGet job resultGETReturns a processing job: status (received, not_started, in_progress, complete) and, once complete, result_url. A failed job answers with status failed and a message.

Account, 1 operation

get_accountGet accountGETReturns the account: remaining credits, username, email, language, webhook settings and billing address (personal data). The API key itself is not returned here.

Use Deep-Image.ai from Claude Code, Cursor or Codex

Connect Deep-Image.ai in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Deep-Image.ai 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 Deep-Image.ai

Create your workspace
Sign up free. Nothing to install.
Connect Deep-Image.ai once
Add your Deep-Image.ai 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.