> ## Documentation Index > Fetch the complete documentation index at: https://docs.salad.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > For autonomous tasks, use live SaladCloud API responses for current state, availability, quotas, models, and other dynamic values. Use current OpenAPI specifications where provided for paths, schemas, required fields, and enums. Never invent endpoints, fields, prices, availability, quotas, models, or state. Prefer API workflows over Portal steps. Read before changing and never expose credentials, signed media URLs, prompts, or sensitive outputs. Retry only safe or idempotent operations with bounded backoff, honoring Retry-After. Verify every write with a read. Stop rather than repeat an uncertain non-idempotent or billable request. AI Gateway uses an organization-specific Bearer key and live /v1/models discovery. Do not delete, cancel, stop, or reduce capacity without explicit user intent. Bind shared operation IDs to the selected product path. Treat Container Engine instances as interruptible and local state as ephemeral. Install the SaladCloud skills (npx skills add https://docs.salad.com), start from the salad skill and /agents/overview; docs MCP: https://docs.salad.com/mcp. # Build with AI Agents > Connect Claude Code, Codex, Cursor, or any MCP-capable agent to SaladCloud: install the skills, add the docs MCP server, hand over an API key safely, and know which runbooks the agent should follow. *Last Updated: September 21, 2026* > If you are an agent reading this page: install the SaladCloud skills with `npx skills add https://docs.salad.com`, > then start from the [Agent Operations Overview](/agents/overview) before any autonomous Container Engine, AI > Gateway, or Transcription task. Use live API responses for account state and the current OpenAPI specifications for > request shapes. Never print the value of `SALAD_API_KEY`. "AI agent" means three different things on SaladCloud. Pick the one you are here for. Claude Code, Codex, Cursor, or a custom agent deploys, scales, monitors, and troubleshoots your container groups, transcription jobs, or AI Gateway requests through the SaladCloud API. This page is for you. The agent writes your Dockerfile, your health probes, your reallocation handling. It needs to know how a container behaves on this network. This page tells it where to look. You want Aider, Cline, Goose, OpenClaw, or the Vercel AI SDK to use an LLM served by SaladCloud. That is the [AI Gateway integrations](/ai-gateway/integrations/overview) section, not this page. ## Install the SaladCloud skills SaladCloud publishes [Agent Skills](https://agentskills.io) — task-specific instruction files in the open `SKILL.md` format that Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Goose, and most other coding agents load on demand. Each skill tells the agent which API operations to use for one job, what to read before writing, and when to stop and ask you. Point the [skills CLI](https://www.npmjs.com/package/skills) at the docs site and pick what you want: ```bash theme={null} npx skills add https://docs.salad.com ``` That prompts you for which skills to install and which agents to install them into, scoped to the current project. To take everything, for every agent the CLI detects, with no prompts: ```bash theme={null} npx skills add https://docs.salad.com --all --global ``` The skills are discovered from `https://docs.salad.com/.well-known/agent-skills/index.json`, so the same command picks up new and updated skills when you run it again. To see what is available without installing anything, open that index or the [Agent Operations](/agents/overview) section, which holds the runbooks the skills are built on. | Skill | What it does | | ------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------- | | `salad` | Router: what SaladCloud is, which source to trust, and which of the skills below to load | | `salad-container-engine-preflight` | Resolves organization, project, quota, GPU class, and availability before any deployment action | | `salad-container-engine-deploy` | Creates a container group, or safely merge-patches one that already exists | | `salad-container-engine-operate` | Starts, stops, scales, and inspects instances of a running container group | | `salad-container-engine-troubleshoot` | Reads system events, logs, and instance state to diagnose a failing group | | `salad-job-queue-autoscaling` | Configures a job queue and queue-based autoscaling | | `salad-ai-gateway-request` | Picks an available model and sends an AI Gateway completion safely | | `salad-ai-gateway-troubleshoot` | Diagnoses failed or unexpected AI Gateway requests | | `salad-transcription-preflight`, `salad-transcription-job`, `salad-transcription-lite-job` | Chooses between Transcription API and Transcription Lite, then submits and monitors a job | | `salad-transcription-troubleshoot` | Diagnoses a transcription job that failed or stalled | | `salad-container-image` | Teaches a coding agent how a container must behave on Salad before it writes the Dockerfile | If your agent supports plugin marketplaces or you prefer a manual install, every skill is also an individual file under `https://docs.salad.com/.well-known/agent-skills//skill.md`. ## Add the documentation MCP server The documentation itself is an [MCP](https://modelcontextprotocol.io) server at `https://docs.salad.com/mcp`. It needs no authentication and gives the agent three tools: search the docs, browse them as a filesystem, and report a page that is wrong or missing. Pair it with the skills so the agent can look up the page a skill points at instead of guessing. ```bash Claude Code theme={null} claude mcp add --transport http --scope user salad-docs https://docs.salad.com/mcp ``` ```json Cursor (.cursor/mcp.json) theme={null} { "mcpServers": { "salad-docs": { "url": "https://docs.salad.com/mcp" } } } ``` ```json VS Code (.vscode/mcp.json) theme={null} { "servers": { "salad-docs": { "type": "http", "url": "https://docs.salad.com/mcp" } } } ``` ```toml Codex (~/.codex/config.toml) theme={null} [mcp_servers.salad-docs] url = "https://docs.salad.com/mcp" ``` `--scope user` puts the server in every project; drop it and Claude Code adds it to the current project only. Codex accepts `codex mcp add salad-docs --url https://docs.salad.com/mcp`, which writes the same TOML block for you. This server reads documentation only. It does not call the SaladCloud API on your behalf; for that, the agent uses your API key directly, as described next. ## Give the agent an API key — and understand what you are handing over Every SaladCloud API call is authenticated with the `Salad-Api-Key` header. Read [Using the API](/reference/api-usage) first; the facts that matter for agents are these: * **The key is yours, not the organization's.** Each user has one API key, and it grants access to every organization, project, and container group that user can reach in the Portal. An agent holding your key can act everywhere you can. There is no read-only or single-organization key today. * **Scope the blast radius with a dedicated account.** If your agent should only touch one organization, invite a separate member account to that organization and give the agent that account's key. Rotating it later will not break your own tooling. * **Keep it in the environment, never in the prompt.** Set `SALAD_API_KEY` as a secret environment variable and let the agent read it from there. The skills and runbooks are written to use that variable and to never print its value. Do not paste the key into a chat, a repository, or an `AGENTS.md`. * **Rotate with a grace period.** When you change the key from the Portal's **API Access** page you can keep the previous key valid for an hour, a day, or a week, so an agent mid-task does not fail the moment you rotate. * **Quota is your spend ceiling.** Billing is by replica running time, and each organization has a [replica quota](/container-engine/reference/quotas) across all container groups. That quota is the hard limit on how much an agent can spin up; set it deliberately before letting an agent scale things. * **AI Gateway is a different key.** [Salad AI Gateway](/ai-gateway/explanation/overview) uses an organization-specific Bearer token (`SALAD_AI_GATEWAY_API_KEY`), not your SaladCloud API key. The agent runbooks keep the two apart; make sure your environment does too. ## What the agent should read The [Agent Operations](/agents/overview) section is written for the agent, not for you. It sets source precedence (a live API response beats the OpenAPI specification, which beats a runbook, which beats a tutorial), lists the actions that require your explicit go-ahead (stopping, deleting, scaling down, reallocating an instance, repeating anything billable), and defines retry, verification, and stop rules. The installed skills point into it; if you are writing your own agent, start there too. Three more things every agent can use: * **`llms.txt`** at [docs.salad.com/llms.txt](https://docs.salad.com/llms.txt) indexes every page with a one-line description and opens with the agent instructions above. * **Any page as Markdown.** Append `.md` to a page URL (for example `https://docs.salad.com/reference/api-usage.md`) to get clean Markdown instead of HTML. * **OpenAPI specifications** for the public API, IMDS, Transcription API, and Transcription Lite live in the [`api-specs` directory](https://github.com/SaladTechnologies/salad-cloud-docs/tree/main/api-specs) of this documentation's repository. They are authoritative for paths, schemas, required fields, and enums. ## Building for SaladCloud with a coding agent A coding agent that has never deployed here will make the same mistakes a new engineer makes: assume the disk persists, assume the instance stays up, assume one replica is enough, forget IPv6, ship a 40 GB image. The `salad-container-image` skill (installed with the command above) carries the rules; these are the pages it is built from: * [Before you deploy](/container-engine/explanation/core-concepts/faqs#what-should-i-be-aware-of-before-deploying-a-workload-to-salad) — instances are interrupted without warning and reallocated automatically; cold starts are slow; build for `amd64`. * [IMDS](/container-engine/explanation/infrastructure-platform/imds) — how a running container learns its own status and asks to be reallocated. * [Health probes](/container-engine/explanation/infrastructure-platform/health-probes) — startup, liveness, and readiness, and what a misconfigured probe looks like from the outside. * [Networking](/container-engine/explanation/infrastructure-platform/networking) — one port through the Container Gateway, IPv6 required inside the container. * [Troubleshooting](/container-engine/how-to-guides/troubleshooting) — image size limits, pull failures, and the states a stuck instance sits in. * [Job queues](/container-engine/explanation/infrastructure-platform/autoscaling) — the worker contract for queue-autoscaled groups. ## Tell us what broke Agents find documentation gaps faster than people do. The docs MCP server's feedback tool, or the [support page](/support), reaches the team that maintains these pages and the skills.