# AI Agents AI coding agents such as Claude Code, OpenAI Codex, and Cursor can connect to Transloadit and use all 88 Robots to upload, encode, and transform files. There are three ways to integrate: the MCP server for runtime tool access, Agent Skills for repeatable workflows, and llms.txt for documentation context. ## MCP server The [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) gives agents direct runtime access to Transloadit tools. ![Demo: encoding videos to HLS adaptive streaming through the Transloadit MCP Server in Claude](/_next/static/media/mcp-demo.0_tw8arokc4ks.gif?dpl=dpl_B5mt5tVSoART1DMQTCiYtAsGkGSU) For most teams, the fastest happy path is self-hosted MCP via stdio: ![](/_next/static/media/copy.04p1cju9qekk_.svg?dpl=dpl_B5mt5tVSoART1DMQTCiYtAsGkGSU) ```bash TRANSLOADIT_KEY=MY_AUTH_KEY TRANSLOADIT_SECRET=MY_SECRET_KEY npx -y @transloadit/mcp-server stdio ``` If you cannot run `npx` in your environment, use the hosted endpoint`https://api2.transloadit.com/mcp` with `Authorization: Bearer `. Generate the token in another trusted environment (for example your backend, CI, or local shell), then pass it to your agent runtime: ![](/_next/static/media/copy.04p1cju9qekk_.svg?dpl=dpl_B5mt5tVSoART1DMQTCiYtAsGkGSU) ```bash npx -y @transloadit/node auth token --aud mcp ``` You can also mint tokens via [POST /token](/docs/api/token-post.md) or the[Node.js SDK](/docs/sdks/node-sdk.md). For client config examples (Claude, Cursor, VS Code/Copilot), auth details, tool docs, limits, and hosted vs self-hosted behavior, see the [MCP Server SDK page](/docs/sdks/mcp-server.md). ## Agent Skills [Agent Skills](https://agentskills.io/) are markdown files (`SKILL.md`) that teach agents how to accomplish tasks step by step. ![Demo: encoding videos to HLS adaptive streaming through Transloadit Agent Skills in Claude](/_next/static/media/skills-demo.17qq6b.p2vo_b.gif?dpl=dpl_B5mt5tVSoART1DMQTCiYtAsGkGSU) In practical terms, an MCP server is an API surface an agent can call at runtime (via a local or hosted MCP process), while skills are version-controlled playbooks that tell an agent what to do, in what order, and how to verify it. Skills do not add new tool access by themselves. They codify how you want the agent to use the tools available in your environment (MCP, CLI, SDKs) in a consistent way. * Use **MCP** for embedded, repeatable execution (uploads, Assemblies, polling, results). * Use **skills** for human-directed, one-off work (setup, scaffolding, templates, migrations). They also complement each other. A skill can standardize a workflow and then instruct the agent to use MCP (or a local CLI fallback) for the actual execution. ### Install with the Skills CLI ![](/_next/static/media/copy.04p1cju9qekk_.svg?dpl=dpl_B5mt5tVSoART1DMQTCiYtAsGkGSU) ```bash npx skills add transloadit/skills ``` This installs all 7 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\`. * **transform-remove-background-with-transloadit**: One-off background removal (local image -> transparent PNG) using Transloadit via the \`transloadit\` CLI. Use a minimal \`/image/bgremove\` steps JSON and download the result to an explicit \`.png\` path 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](/.well-known/skills/index.json), following the[Agent Skills Discovery RFC](https://agentskills.io/specification). This means you can also install with: ![](/_next/static/media/copy.04p1cju9qekk_.svg?dpl=dpl_B5mt5tVSoART1DMQTCiYtAsGkGSU) ```bash npx skills add https://transloadit.com ``` ### Manual installation Clone or symlink the [transloadit/skills](https://github.com/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](/llms.txt) file, a structured index of all Robot documentation following the [llms.txt standard](https://llmstxt.org/). 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](/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.