Integration

Transloadit integration

Transloadit processes files in the cloud: resize and convert images, encode video and audio, generate thumbnails, run OCR, virus scans and document conversion, import from URLs and export to storage. Create Assemblies (processing jobs) from inline Steps or saved Templates and follow them until they complete, replay Assemblies and their notifications, manage Templates, read Assembly statistics, priority job slots and monthly bills, and list, move and delete assets in the Storage library (alpha). Auth Key management, the Template Credentials store (third-party storage secrets), resumable tus uploads and the token route are not exposed. Authentication is OAuth 2.0 client credentials: the Auth Key is the client id and the Auth Secret the client secret, exchanged for a bearer token that carries every scope the key grants.

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Transloadit.Built from the 25 Transloadit tools below, on the connection you add once.

What you can do with Transloadit

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.

Assembly, 5 operations

  • cancel_assemblyCancel assemblyDELETECancels an Assembly still uploading or executing. Returns its status: ok ASSEMBLY_CANCELED if it was running, its previous outcome if already finished. Error ASSEMBLY_CANCEL_UNAVAILABLE: check get_assembly before retrying.
  • create_assemblyCreate assemblyPOSTStarts an Assembly (a processing job) from inline steps or a template_id, on an uploaded file or imported URLs. Returns at once (ok ASSEMBLY_EXECUTING): call get_assembly until ok is ASSEMBLY_COMPLETED; an error field means it failed.
  • create_assembly_with_idCreate assembly with idPUTLike create_assembly, under a new id you choose (32 lowercase hex characters, never used before). Not a retry guard: a reused id is refused. Returns at once: call get_assembly until ok is ASSEMBLY_COMPLETED; an error field means it failed.
  • get_assemblyGet assemblyGETReturns an Assembly's status and results. ok is ASSEMBLY_UPLOADING, ASSEMBLY_EXECUTING, ASSEMBLY_COMPLETED, ASSEMBLY_CANCELED or REQUEST_ABORTED; on failure error is set instead. Output files are in results, grouped by Step name, each with ssl_url.
  • list_assembliesList assembliesGETLists Assemblies of the Workspace, newest first, by default only those created in the last seven days. Filter by status type, Template, region, date range or keyword; returns count and items with each Assembly's id, status (ok or error) and timing.

Template, 5 operations

  • create_templateCreate templatePOSTCreates a Template from Assembly Instructions so Assemblies can use it by template_id. Scheduling (cron) is always off on creation. Returns the new Template with its id.
  • delete_templateDelete templateDELETEDeletes a Template. Assemblies that reference it by template_id fail afterwards.
  • get_templateGet templateGETReturns one Template: id, name, content (the Assembly Instructions) and its settings (status retention, signature requirement, cron schedule).
  • list_templatesList templatesGETLists the Workspace's Templates (saved Assembly Instructions), optionally with Transloadit's Builtin Templates. Returns count and items with id, name, content (the Instructions) and settings; pass the id or name as template_id in create_assembly.
  • update_templateUpdate templatePUTChanges a Template: only the keys sent change. Can also enable its cron schedule (preview) with cron_enabled, cron_schedule_with_seconds, cron_region and cron_auth_key_id, which then starts billed Assemblies on that schedule.

Asset, 4 operations

  • delete_dam_assetDelete dam assetDELETEDeletes a Storage asset from the Workspace library (alpha). Idempotent: deleting it again answers the same. Returns asset_id and deleted_at.
  • get_dam_assetGet dam assetGETReturns one Storage asset (alpha): path, mime, size, dimensions, hashes and version_id, for the current version or a retained one.
  • list_dam_assetsList dam assetsGETLists assets in the Workspace Storage library (alpha), one page at a time, optionally under a path prefix. Returns assets (asset_id, path, mime, size, hashes, version_id) and next_cursor; call again with that cursor until it is null.
  • move_dam_assetMove dam assetPATCHMoves a Storage asset to another folder and/or renames it (alpha), without changing the stored file or its ids. Returns the updated asset.

Move, 2 operations

  • bulk_move_dam_assetsBulk move dam assetsPOSTMoves several Storage assets into one folder in one all-or-nothing operation (alpha). Returns the moved assets with their new folder_id and path.
  • move_dam_entryMove dam entryPOSTMoves or renames a Storage file or folder by path (alpha), keeping its asset and version ids. An occupied destination is refused, never overwritten. Returns the new path.

Replay, 2 operations

  • replay_assemblyReplay assemblyPOSTStarts a new Assembly from the inputs and Instructions of an earlier one (it is billed again), optionally with overridden steps, fields or notify_url. Returns the new assembly_id: follow it with get_assembly.
  • replay_assembly_notificationReplay assembly notificationPOSTSends an Assembly's completion notification to its notify_url again (or to another URL). Waits for the attempt by default; check its result with list_assembly_notifications.

Assembly notification, 1 operation

  • list_assembly_notificationsList assembly notificationsGETLists the delivery records of an Assembly's notification (the POST to its notify_url): the original delivery and saved manual replays, with url, status, response_code and error.

Assembly stats, 1 operation

  • get_assembly_statsGet assembly statsGETReturns Assembly statistics for a region over a time window of at most 91 days: totals (Assemblies, files, bytes, execution and queue time) plus series per period and error counts per error code.

Bill, 1 operation

  • get_billGet billGETReturns the Workspace bill for one month: plan, included and extra gigabytes, fees, discounts, credit, totals, billing address and invoice id. Check ok is BILL_FOUND: a month with no bill answers with error BILL_NOT_FOUND.

Cron run, 1 operation

  • list_template_cron_runsList template cron runsGETLists the recent scheduled runs (ticks) of a cron Template (alpha), newest first, within 30 days: when each was admitted and completed, its Assembly id and missed ticks. Page with next_before.

Delete, 1 operation

  • bulk_delete_dam_assetsBulk delete dam assetsPOSTDeletes several Storage assets in one all-or-nothing operation (alpha). Returns each asset_id with its deleted_at.

Job slot, 1 operation

  • list_priority_job_slotsList priority job slotsGETReturns the priority job slots the Workspace is using right now (count and slots).

Priority job slot stats, 1 operation

  • get_priority_job_slot_statsGet priority job slot statsGETReturns priority job slot usage over a time window of at most 91 days for a region: average and maximum slot counts, plus a series per period.

Use Transloadit from Claude Code, Cursor or Codex

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

  1. Create your workspace

    Sign up free. Nothing to install.

  2. Connect Transloadit once

    Add your Transloadit connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.

  3. 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.

Transloadit integration FAQ

What can you do with the Transloadit integration?

LiveContext exposes 25 operations on Transloadit, covering assembly, template, asset and move.

Popular integrations

Browse the whole catalog