Skip to content
WebMCP Kit
Esc
↑↓navigate↵open⌘Jpreview
On this page

/webmcp-kit:implement

Add WebMCP tools to your site.

Adds WebMCP tools to the website repo you’re working in. Plans first, writes only after you approve, verifies in a browser.

/webmcp-kit:implement

Run it from the root of the site’s repo. You can add a request, such as /webmcp-kit:implement add booking tools.

Already have WebMCP tools? Use connect-existing-tools to connect them to AgentLane.

When to use it

  • Making a site agent-ready for the first time.
  • Re-running after a redesign or new feature — existing tools keep their identity via stableKey.
  • Someone asked you to “add WebMCP tools” or “expose this site to browser agents”.

What you review

The plan (Phase D — see How it works for all six phases) shows, per tool:

  • Name and description, verbatim. The description is what an agent reads to decide when to call the tool — it ships exactly as approved, so word it like it matters.
  • Wiring — the concrete code path the tool will call (a data-layer function, a same-origin route).
  • Availability — which pages and auth states register the tool.

Tools come in two confidence levels:

  • Decided — a must-have journey with a clearly safe wiring path. Listed for your review.
  • Needs your input — anything ambiguous. Comes as a specific question with a stated default, never a silent guess.

Journeys with no safe client path are listed as needs developer wiring — the plugin tells you what’s missing instead of faking it.

What it writes

After approval, in your repo’s own language and conventions:

  • Tool modules — one or more files of defineTool definitions. Side-effect-free: importing them registers nothing.
  • One entry module per scope — the single place that calls registerTools and owns the tools’ lifetime.
  • The SDK dependency — wired the way your repo needs (registry package or vendored copy; transpilePackages added for Next.js when required).

Then verification runs (same ladder as the verify skill), and the work lands on a webmcp/tools-v0 branch with the plan and per-tool results as the PR body.

Review mode

Interactive runs use the Explorer, a local page where you review the tools and approve the plan. It keeps the plan and review state in .webmcp/; your site’s code is unchanged until you approve.

Prefer chat? Run /webmcp-kit:implement --no-interactive-loop. The same approval step happens in the conversation.

Connect to AgentLane

After verification, the skill offers to connect your tools to AgentLane so you can see them and their activity. You can skip this and keep the tools as they are.

Headless runs

Use --non-interactive, or explicitly ask to proceed without approval. The skill uses the stated defaults, records the plan and assumptions in the PR, and skips the Explorer and AgentLane connection. If you haven’t asked for this mode, it waits for approval. Silence is not approval.

Was this page helpful?