domains / families / agent-tooling / add-webmcp

add-webmcp

separate

Analyze an existing web application, identify safe user-visible capabilities across routes, forms, server actions, handlers, and schemas, then implement first-party WebMCP tools and validate discovery and invocation with Stagehand. Use when the user asks to make a codebase agent-ready, expose website features as WebMCP tools, or add WebMCP directly to an app rather than generating a standalone injection script from a URL.

When to use

• make a codebase agent-ready
• expose website features as WebMCP tools
• add WebMCP directly to an app
• implement first-party WebMCP tools
• validate discovery and invocation with Stagehand

When not to use

• generating a standalone injection script from a URL
• introducing a hosted proxy
• introducing a third-party runtime
• using webmcp-gen for standalone init scripts

Skill page

Source