The agent generates a grounded, read-only plan for a specific request against a public website, including evidence, risks, and confirmation requirements.
The agent uses plan_site_action to create a grounded, read-only plan for a user's request against a specific domain. The tool automatically indexes the site if needed. The output includes evidence, risks, confirmation requirements, and a durable receipt. This is strictly read-only and does not execute actions.
- Category: Operations and infrastructure
- Effect: Read-only
- MCP servers: AgentReady MCP (https://koskamo.com/explore/agentready-mcp)
- Source: Connect AI agents to any website — AgentReady (https://www.agentready.it.com/connect)
- Source quote: "plan_site_action(domain, request) Automatically indexes a public site when needed, then creates a grounded, read-only plan with evidence, risks, confirmation requirements, and a durable receipt."
- Playbook page: https://koskamo.com/explore/use-cases/create-a-read-only-action-plan-for-a-website
Prompt: Create a grounded, read-only plan for interacting with the GitHub repository agentready-mcp using the plan_site_action tool.