Integration

Claid.ai integration

Claid.ai is an AI image editing and generation API for product, e-commerce, real-estate and food photos. Edit an image by URL or uploaded file (upscale, restore, remove or replace the background, resize, crop, pad, adjust colors and lighting, blur car plates), run edits asynchronously or on a whole storage folder, generate images from text, place a product in an AI-generated scene, edit an image from a text instruction, dress a fashion model in clothing photos, and animate an image into a short video. Cloud storage connectors (Amazon S3, Google Cloud Storage, web folders) can be created and managed to read inputs and write results. Every processing call consumes credits from the Claid account. Webhook settings are configured in the Claid dashboard and are not exposed. Authentication is an API key from the Claid dashboard (API keys page), sent as a Bearer token in the Authorization header.

Connect Claid.ai How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Claid.ai.Built from the 20 Claid.ai tools below, on the connection you add once.

What you can do with Claid.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.

Storage, 5 operations

create_storageCreate storagePOSTConnects a storage (Amazon S3, Google Cloud Storage or a web folder) under a name used in storage://<name>/ input and output paths. Returns the storage with its access key id, never the secret.
delete_storageDelete storageDELETEDisconnects a storage from the Claid account. Irreversible: storage:// paths using its name stop working.
get_storageGet storageGETReads one connected storage: name, type and parameters (bucket, path and the credentials access key id, or base_url). The secret key is never returned.
list_storagesList storagesGETLists the storages connected to the Claid account: id, name (used in storage://<name>/ paths), type and parameters (bucket and path, or base_url).
update_storageUpdate storagePATCHChanges a connected storage's name, type or connection parameters; only the fields sent are changed. Returns the updated storage.

Generate, 3 operations

generate_imagesGenerate imagesPOSTGenerates images from a text prompt and waits: returns data.output, one item per image with its tmp_url. Billed: 1 credit per image; set options.number_of_images to 1 for the cheapest call (vendor default 4).
generate_video_from_imageGenerate video from imagePOSTBilled: 35 credits per 5 s video, 70 per 10 s. Animates an image into an MP4 video; returns result.output_object.tmp_url. Fails on ERROR or CANCELLED. Waits for the job and returns the finished result; gives up after 10 minutes.
get_video_jobGet video jobGETReads a video job started by generate_video_from_image: status, errors, and once DONE result.output_object with the tmp_url of the MP4 video.

Ai edit, 2 operations

ai_edit_imageAi edit imagePOSTBilled: 2 credits per output image. Edits an image from a text instruction; returns result.output_objects with tmp_url links. Fails on ERROR or CANCELLED. Waits for the job and returns the finished result; gives up after 10 minutes.
get_ai_edit_jobGet ai edit jobGETReads an AI edit job started by ai_edit_image: status, errors, and once DONE result.output_objects with the tmp_url of each edited image.

Ai fashion model, 2 operations

generate_fashion_model_imagesGenerate fashion model imagesPOSTBilled: 2 credits per output image. Dresses a fashion model in the given clothing images; returns result.output_objects with tmp_url links. Fails on ERROR or CANCELLED. Waits for the job and returns the finished result; gives up after 10 minutes.
get_fashion_model_jobGet fashion model jobGETReads a fashion model job started by generate_fashion_model_images: status, errors, and once DONE result.output_objects with the tmp_url of each generated image.

Async, 2 operations

edit_image_asyncEdit image asyncPOSTBilled (Claid credits). Edits one image by URL as a background job; returns the job with result.output_object.tmp_url. Fails on status ERROR or CANCELLED. Waits for the job and returns the finished result; gives up after 10 minutes.
get_image_edit_jobGet image edit jobGETReads an image edit job started by edit_image_async: status (ACCEPTED, WAITING, PROCESSING, PAUSED, DONE, ERROR or CANCELLED), errors, and once DONE result.output_object with the tmp_url of the edited image.

Batch, 2 operations

edit_images_batchEdit images batchPOSTBilled per image. Edits every image of a storage folder as one background job; returns results with one output_object per image. Fails on ERROR or CANCELLED. Waits for the job and returns the finished result; gives up after 10 minutes.
get_batch_edit_jobGet batch edit jobGETReads a batch edit job started by edit_images_batch: status, errors per image and results (input_object and output_object for each processed image).

Create, 1 operation

create_product_sceneCreate product scenePOSTPlaces a product image in an AI-generated scene (from a prompt, a template image or a background effect) and waits: returns data.output with one tmp_url per image. Billed: 3 credits per image (plus 0.5 when the prompt is generated).

Edit, 1 operation

edit_imageEdit imagePOSTEdits one image by URL and waits for the result: returns data.output.tmp_url (kept 24 hours) or the storage location. Billed: consumes Claid credits. For a local file use edit_uploaded_image.

Storage type, 1 operation

list_storage_typesList storage typesGETLists the storage types a storage connector can have: web_folder, s3 (Amazon S3) and gcs (Google Cloud Storage).

Upload, 1 operation

edit_uploaded_imageEdit uploaded imagePOSTEdits an uploaded image file and waits for the result: returns data.output.tmp_url (kept 24 hours) or the storage location. Billed: consumes Claid credits. For an image at a URL use edit_image.

Use Claid.ai from Claude Code, Cursor or Codex

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

Create your workspace
Sign up free. Nothing to install.
Connect Claid.ai once
Add your Claid.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.