AI onboarding

Use the bird CLI and Bird's skills when your coding agent can run shell commands. Use the hosted MCP server when your client calls tools instead. Both surfaces can search the docs, and agents without tools can read the published Markdown corpus. Start with the CLI unless your client requires MCP.

1. Set up your agent (CLI + skills)

Paste the setup prompt into your coding agent. It installs the bird CLI, signs you in with bird auth login, installs Bird's skills, and sends a test email to confirm the setup. The Claude Code, Codex, and Cursor buttons on Bird product pages copy a prompt tailored to each client. Set up your coding agent walks through the same flow.

2. Connect the MCP server (when it fits)

If your client calls tools instead of running a shell, point it at Bird's hosted MCP server. You only need the URL and a browser sign-in:

Przykład kodu

https://mcp.bird.com

The endpoint uses OAuth, so authenticate once in each client. Your browser opens a Bird consent screen where you sign in, choose a workspace and permissions, and approve access. You do not need an API key or a secret in the client configuration. Follow the connection steps for your client. The MCP server guide also covers the tool surface, delegated OAuth, and the local bird mcp option.

3. Give your agent the docs

If your agent has the Bird tools from step 1 or 2, it can already read these docs: docs_search finds pages by query and docs_read returns one as Markdown. From a shell those are bird docs search "ip warmup" and bird docs read <slug>. Prefer this to loading the corpus because the agent fetches only the current page it needs.

For agents that can't call tools, the whole site is published as Markdown:

/llms.txt: the index, a flat, link-rich summary of every page, a starting point the agent can follow links from.
/llms-full.txt: the full corpus, every doc page concatenated as Markdown, for agents that want the whole thing in context.

Both files are regenerated with every site deploy. You can also use the AI tools in a docs page's sidebar: Copy as Markdown copies that page, and Open llms-full.txt opens the corpus. The dashboard's email onboarding page provides the same Copy for AI shortcuts.

The email onboarding page in the Bird dashboard, with the API-key step, a runnable send snippet, and the Copy for AI action

The formats, sizing, and retrieval tips are covered in the llms.txt guide.

4. Try it

Once your agent is set up, give it a real task end to end:

Find my email with whoami, then send me a test email from onboarding@messagebird.dev and tell me when it's delivered.

The agent reads your address with whoami, sends from Bird's shared onboarding domain, and polls the status until the message reaches your inbox. The onboarding domain can send to verified members of your workspace without domain verification. For a deterministic check with no real inbox, send to delivered@messagebird.dev instead; see the testing sandbox.

Next steps

Self-serve signup: for an agent that needs its own Bird account rather than yours. Create the account, organization, and workspace from the terminal, no browser.
CLI for agents: the bird CLI's agent contract. JSON output, semantic exit codes, OAuth login.
Agent skills: the bird-ai marketplace plugin and what each client gets.
MCP server: the hosted endpoint, the full tool surface, the delegated OAuth model, and the local-stdio option.
llms.txt & Markdown docs: how the machine-readable corpus is built and how to retrieve from it.
Send your first email: complete the same email flow without an agent.