AI Agents

AI coding agents such as Claude Code, OpenAI Codex, and Cursor can connect to Transloadit and use all 81 Robots to upload, encode, and transform files. There are three ways to integrate: through the MCP server, through Agent Skills, and through llms.txt for context.

MCP server

The Model Context Protocol (MCP) gives agents direct access to Transloadit tools: creating Assemblies, listing Templates, uploading inputs, and more.

Hosted (recommended)

Connect to the Transloadit-hosted MCP endpoint. No installation needed — just add the URL and a Bearer token to your client config.

Generate a token

Use the Transloadit CLI to mint a short-lived Bearer token (valid for six hours):

npx -y @transloadit/node auth token --aud mcp

This prints a token you can paste into the config snippets below. You can also mint tokens programmatically via POST /token if you prefer.

Client configuration

Claude Desktop / Claude Code (claude_desktop_config.json or .mcp.json):

{
  "mcpServers": {
    "transloadit": {
      "type": "streamableHttp",
      "url": "https://api2.transloadit.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TRANSLOADIT_AUTH_TOKEN"
      }
    }
  }
}

Cursor (Settings > MCP):

Add the same URL as a streamable HTTP server with the Authorization header.

VS Code / Copilot (.vscode/mcp.json):

{
  "servers": {
    "transloadit": {
      "type": "http",
      "url": "https://api2.transloadit.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TRANSLOADIT_AUTH_TOKEN"
      }
    }
  }
}

Self-hosted

Run the MCP server locally via stdio for development or air-gapped environments. Because it has direct access to your Auth Key and Secret, it mints tokens automatically — no manual token step needed.

TRANSLOADIT_KEY=MY_AUTH_KEY TRANSLOADIT_SECRET=MY_SECRET_KEY npx -y @transloadit/mcp-server stdio

Or start an HTTP endpoint on your own infrastructure:

npx -y @transloadit/mcp-server http --host 127.0.0.1 --port 5723

See the MCP Server SDK page and the GitHub README for the full reference.

Agent Skills

Agent Skills are markdown files (SKILL.md) that teach agents how to accomplish tasks step by step. While the MCP server gives agents abilities, Skills teach them how to use those abilities well — with workflows, templates, and best practices built in.

Install with the Skills CLI

npx skills add transloadit/skills

This installs all 6 Transloadit skills into your project:

docs-transloadit-robots — Offline lookup for Transloadit Robots and their parameter docs/examples via the `transloadit` CLI. Use to draft or validate `steps` JSON without guessing robot names/params.
integrate-asset-delivery-with-transloadit-smartcdn-in-nextjs — Add Transloadit Smart CDN URL signing to a Next.js App Router project (server-side signing route + optional client demo page).
integrate-uppy-transloadit-s3-uploading-to-nextjs — Add Uppy Dashboard + Transloadit uploads to a Next.js (App Router) app, with server-side signature generation and optional /s3/store export.
transform-encode-hls-video-with-transloadit — One-off HLS encoding (local video -> HLS renditions + playlist) using Transloadit via the `transloadit` CLI. Prefer builtin templates (`builtin/encode-hls-video@latest`) and download outputs locally via `-o`.
transform-generate-image-with-transloadit — One-off image generation (prompt -> image file) using Transloadit via the `transloadit` CLI. Prefer builtin templates (`builtin/generate-image@latest`) and download outputs locally via `-o`.
transloadit — Main entry-point skill for Transloadit. Route to the right `integrate-*`, `transform-*`, or `docs-*` skill, and prefer executing via `npx -y @transloadit/node ...` (CLI) for deterministic behavior.

Auto-discovery

The skills catalog is also discoverable at transloadit.com/.well-known/skills/index.json, following the Agent Skills Discovery RFC. This means you can also install with:

npx skills add https://transloadit.com

Manual installation

Clone or symlink the transloadit/skills repo into your agent's skills directory:

Agent	Path
Claude Code	`.claude/skills/`
OpenAI Codex	`.codex/skills/`
Gemini CLI	`.gemini/skills/`
Cursor	`.cursor/skills/`
Windsurf	`.codeium/windsurf/skills/`

llms.txt

Transloadit publishes an llms.txt file — a structured index of all Robot documentation following the llms.txt standard. Agents and LLMs can fetch this file to get an up-to-date overview of every Robot, its parameters, and links to the full docs.

A detailed variant is available at llms-full.txt, which includes complete Robot documentation inline rather than linking out.

Which approach should I use?

Approach	Best for	Setup time
Hosted MCP	Production agent workflows, team setups	2 minutes
Self-hosted MCP	Air-gapped environments, local dev	5 minutes
Agent Skills	Teaching agents Transloadit best practices and patterns	2 minutes
llms.txt	Giving any LLM context about Transloadit Robots	Zero (just fetch the URL)

These approaches complement each other. Use the hosted MCP server for tool access, install skills for workflow guidance, and point your LLM at llms.txt when it needs Robot documentation.