Integration

LetzAI integration

LetzAI is a generative media platform from Luxembourg. Generate images from text (LetzAI and partner models such as Flux, Nano Banana, GPT Image and Seedream, plus models trained on LetzAI and called as @tags in the prompt), edit images from an instruction, upscale images and videos, generate videos from text or images, edit videos, and generate speech, music and sound effects. Every create tool waits for the job and returns the finished file URLs; jobs are billed in LetzAI credits from your account or an organization, so price one first with quote_generation and look up model ids with get_model_catalog. You can also list and search your images, videos and sounds, upload your own files as inputs, manage privacy, read organization credit balances and work with boards. The enterprise Model Training routes, the canvas and studio design editors, the in-app agent runs, skills, OAuth and realtime routes are not exposed. Authentication is a LetzAI API key (created on the subscription page; a subscription is required) sent as a Bearer token in the Authorization header.

Connect LetzAI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in LetzAI.Built from the 46 LetzAI tools below, on the connection you add once.

What you can do with LetzAI

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.

Video edit, 6 operations

create_video_editCreate video editPOSTEdit videos (LetzAI ids or URLs) from an instruction; billed in credits. Returns videoChoices; keep one with save_video_edit_choice. Waits for the job and returns the finished result; gives up after 10 minutes.
delete_video_editDelete video editDELETEDelete one of your video edits permanently.
get_video_editGet video editGETGet one of your video edits by id: its status and output videoChoices.
interrupt_video_editInterrupt video editPUTStop one of your video edits while it is still running.
list_video_editsList video editsGETList your video edits, filtered by status, with page and limit.
save_video_edit_choiceSave video edit choicePATCHKeep one of the output choices of a video edit; savedVideoId is then set on the edit.

User asset, 5 operations

create_user_assetCreate user assetPOSTRegister a file of your own (image, video or audio) and get a pre-signed uploadUrl to PUT its bytes to; afterwards imageUrl is usable as an input to edits, upscales and videos.
delete_user_assetDelete user assetDELETEDelete one of your uploaded files permanently.
get_user_assetGet user assetGETGet one uploaded file by id, with its public imageUrl.
list_user_assetsList user assetsGETList the files you uploaded, newest first (at most 100 per page).
update_user_assetUpdate user assetPATCHChange the caption of one of your uploaded files. Leave caption out to keep the current one.

Audio, 4 operations

create_audioCreate audioPOSTGenerate speech from text, music or a sound effect; billed in credits (see quote_generation). Returns the job with audioUrl once ready. Waits for the job and returns the finished result; gives up after 10 minutes.
delete_audioDelete audioDELETEDelete one of your audio jobs permanently.
get_audioGet audioGETGet one of your audio jobs by id: its status and, once ready, audioUrl.
list_audiosList audiosGETList your generated audio, newest first, filtered by status or kind.

Image, 4 operations

create_imageCreate imagePOSTGenerate an image from a text prompt; billed in LetzAI credits (price it with quote_generation first). Returns the image with its file URL in imageVersions.original. Waits for the job and returns the finished result; gives up after 10 minutes.
get_imageGet imageGETGet one image by id: its status, progress and, once ready, the file URLs in imageVersions.
interrupt_imageInterrupt imagePUTStop an image generation that is still new or generating; its status becomes interrupted.
list_imagesList imagesGETList images visible to you (yours and public ones), newest per sortBy and sortOrder, filtered by user, model, status or privacy. Returns up to limit images per page.

Upscale, 4 operations

create_upscaleCreate upscalePOSTUpscale a LetzAI image, an image URL or a video to a higher resolution; billed in credits (see quote_generation). Returns the upscale with imageVersions.original. Waits for the job and returns the finished result; gives up after 10 minutes.
delete_upscaleDelete upscaleDELETEDelete one of your upscales permanently.
get_upscaleGet upscaleGETGet one upscale by id: its status and, once ready, the file URLs in imageVersions.
list_upscalesList upscalesGETList upscales, filtered by creator, source image or status, with page and limit.

Board, 3 operations

create_boardCreate boardPOSTCreate a board (a shared collection of images and videos) that you own and administer. At most 20 boards per hour; more returns 429.
get_boardGet boardGETGet one board by id: name, description, owner, thumbnail, member count, visibility and safety. Non-public boards are visible to members only.
list_boardsList boardsGETList boards visible to you: every public board plus the private boards you are a member of, with search and membership filters.

Image edit, 3 operations

create_image_editCreate image editPOSTEdit an image from an instruction (context editing or skin fix), from a LetzAI image or public URLs; billed in credits. Returns the edit and its result image. Waits for the job and returns the finished result; gives up after 10 minutes.
get_image_editGet image editGETGet one image edit by id: its status and, once ready, the result image.
list_image_editsList image editsGETList your image edits, filtered by status, with page and limit.

Video, 3 operations

create_videoCreate videoPOSTGenerate a video from text, from an image, or between two frames; billed in credits (see quote_generation). Returns it with videoVersions.original. Waits for the job and returns the finished result; gives up after 10 minutes.
get_videoGet videoGETGet one video by id: its status, progress and, once ready, the file URL in videoVersions.original.
list_videosList videosGETList videos visible to you, filtered by creator, status, prompt, size or model, with page and limit.

Model, 2 operations

get_modelGet modelGETGet one LetzAI model by id: its name (the @tag), class, status and training progress.
list_modelsList modelsGETList LetzAI models (trained people, objects and styles) you can use in prompts as @tags, with search, class and privacy filters.

Organization, 2 operations

get_organizationGet organizationGETGet one organization you belong to by id.
list_organizationsList organizationsGETList the organizations you belong to: the accounts you can bill by passing an id as organizationId when generating.

Board feed, 1 operation

list_board_feedList board feedGETList the finished images and videos of a board as one ranked, paginated list. Non-public boards are visible to members only.

Feed, 1 operation

list_my_feedList my feedGETEverything you generated (images, videos, sounds), private included, newest first by default. Cursor paging via pagination.nextCursor.

Generation quote, 1 operation

quote_generationQuote generationPOSTEstimate the credits a generation would cost before running it. Nothing is reserved or charged; the real charge is set when the job finishes.

Image privacy, 1 operation

update_image_privacyUpdate image privacyPUTChange the privacy of one of your ready images. Public images appear on the LetzAI feed under your account.

Image prompt privacy, 1 operation

update_image_prompt_privacyUpdate image prompt privacyPUTHide or show the prompt of one of your images in public listings.

Media, 1 operation

search_mediaSearch mediaGETSearch finished images and videos by prompt, user, model, date range and type: your own (private included) and everyone's public ones. Cursor paging via pagination.nextCursor.

Model catalog, 1 operation

get_model_catalogGet model catalogGETGet the LetzAI model catalogue: every image, video, upscale, audio and text model with its capabilities, limits and prices, keyed by model id. No API key needed.

Organization credit balance, 1 operation

list_organization_credit_balancesList organization credit balancesGETGet the unexpired credit balances of an organization you belong to, per credit type, as you can spend them.

Video privacy, 1 operation

update_video_privacyUpdate video privacyPUTChange the privacy of one of your videos. Public videos appear on the LetzAI feed under your account.

Video prompt privacy, 1 operation

update_video_prompt_privacyUpdate video prompt privacyPUTHide or show the prompt of one of your videos in public listings.

Use LetzAI from Claude Code, Cursor or Codex

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

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