ShipEasy

AI Agent guides

URL-addressable runbooks an AI coding assistant can follow end-to-end — install the SDK, scan your code, push keys, ship a flag, run an experiment. Hand the agent a link, answer one auth prompt, watch it work.

ShipEasy · LLM Guides

Hand it to an AI agent. Done in minutes.

Plain-MDX runbooks at stable URLs, designed to be followed by Claude Code, Cursor, Windsurf, OpenCode, and anything else that speaks MCP. The agent calls typed ShipEasy tools — never your shell, never your secrets — and stops only when a human is required.

Production readyOn this page · 5 min readUpdated · May 3, 2026Works with · Claude Code · Cursor · Windsurf · OpenCode

ShipEasy ships every product behind a typed MCP server (shipeasy-mcp). The CLI installs it into your AI assistant's config, the agent discovers the tools, and these guides tell the agent the right sequence of calls to make for a given workflow. You answer one browser auth prompt; the agent does the rest.

Why URL-addressable runbooks

How it works

Install the MCP server

The CLI ships a one-shot installer that writes the right MCP config for whichever assistants it finds on your machine — ~/.claude/settings.json, .cursor/mcp.json, .windsurf/mcp.json.

npm install -g @shipeasy/cli
shipeasy mcp install

Under the hood it registers npx -y @shipeasy/mcp@latest as the shipeasy MCP server. The binary is shipeasy-mcp; it runs locally over stdio, never as a hosted endpoint.

Log in once

shipeasy login

The CLI runs an OAuth device-code flow against the ShipEasy worker (/auth/device/*) and stores a long-lived credential at ~/.shipeasy/credentials. The MCP server reads from the same file. The agent never sees your token — every tool call attaches the credential server-side.

Hand the agent a guide URL

Open your AI assistant in your project and say something like:

"Follow https://docs.shipeasy.ai/llms/i18n-strings to onboard this project to ShipEasy."

The agent fetches the page, reads the steps, and starts calling the appropriate mcp__shipeasy__* tools in order. It pauses for human input only at the points the runbook marks with STOP (typically: browser auth, ambiguous codemod cases).

What the MCP server exposes

The shipeasy-mcp binary advertises a typed tool surface grouped by product. Every guide on this site is a recipe for chaining these tools:

Field
Type
Description
auth_check
tool
Returns { authenticated: boolean, user, project }. First call in every workflow — if it returns false, the agent must ask the human to run shipeasy login.
auth_login / auth_logout
tool
Wrap the device-code flow. Login opens a browser; the human clicks once. The agent waits for the tool to return.
detect_project
tool
Inspects the working directory and returns frameworks, entry_points, and shipeasy.{i18n_sdk, loader_script_tag}. Lets the agent skip framework guesswork.
list_resources / get_resource
tool
Read-only views into the project — list profiles, keys, gates, configs, experiments. Cheap to call; the agent uses these to verify state between mutations.
i18n_*
11 tools
Polylang surface — install_loader, create_profile, scan_code, codemod_preview, codemod_apply, push_keys, create_key, translate_draft, validate_keys, publish_profile, discover_site.
exp_*
6 tools
Configs / experiments surface — create_gate, create_config, create_experiment, start_experiment, stop_experiment, experiment_status.
get_sdk_snippet
tool
Returns ready-to-paste init code for the detected framework, scoped to the current project's API key.
No tool runs your shell

MCP tools mutate ShipEasy state through the public API. Anything that touches your filesystem (the codemod, the loader install) runs the local CLI binary, which prints what it's about to do and respects --dry-run. There is no exec_arbitrary_command tool.

Available guides

Planned guides

These are scaffolded against the same MCP surface and ship as the underlying products stabilise. Watch this index — when the link goes live, it works.

Write your own guide

The guides are plain MDX. If your team has conventions — a specific source root, a review step, a Slack channel that needs pinging on publish — fork one, edit it, host it. The agent doesn't care where the URL points; it cares that the page describes a sequence of MCP tool calls.

Start from an existing guide

Copy content/docs/llms/i18n-strings.mdx from the docs repo. It's the canonical pattern: numbered steps, explicit tool names, explicit JSON args, explicit failure handling.

Mark every human stop

Use the literal token STOP in step titles where the agent must wait — browser auth, codemod approval, anything that mutates production. Agents are trained to honour this.

Reference tools by their MCP name

Use the canonical tool name (i18n_codemod_apply, not "the apply step"). Show the full JSON arg shape. Agents pattern-match on these.

Host it on a stable URL

Anywhere the agent can fetch — your docs site, a GitHub raw URL, a gist. Hand the URL to your team and to your agents.

Don't hardcode runbooks into your codebase

Resist the urge to paste a guide into CLAUDE.md or your project's AGENTS.md. The MCP tool surface evolves; the URL stays current; a copy goes stale immediately. Reference the URL, don't inline it.

READY?

Try the i18n runbook on a real project.

Install the CLI, install the MCP server, log in once, paste the URL into your AI assistant. Five minutes from a hardcoded-English app to a published source profile.

Install everything
$npm i -g @shipeasy/cli && shipeasy mcp install
Log in once
$shipeasy login
Then say to your agent
$Follow https://docs.shipeasy.ai/llms/i18n-strings
Works with Claude Code, Cursor, Windsurf, OpenCode, and any MCP-aware client.
Was this page helpful?✎ Edit on GitHub

On this page