mcpField
Y
yutori-browse

yutori-browse

github.com/yutori-aiProductivity25106 installsUpdated 4w ago
Repository

About yutori-browse

A skill for automating browser tasks through Yutori's Navigator agent. It guides users from defining a task and its steps to checking the result, with options for authentication, structured extraction, and completion notifications.

Key features

  1. 01Natural-language task planning
  2. 02Browser task execution
  3. 03Authentication-aware workflows
  4. 04Structured data extraction
  5. 05Result polling and validation
  6. 06Webhook completion notifications

Use cases

  1. 01Completing website forms and actions
  2. 02Extracting fields from web pages
  3. 03Running authenticated browser workflows

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/yutori-ai/yutori-mcp --skill yutori-browse

After installing, type/yutori-browsein Claude Code to confirm it loaded.

Details

From the project README

Browser Automation

Help the user automate browser-based tasks using Yutori's Navigator agent.

Process

  1. Understand the task

    • What website needs to be automated?
    • What actions are required? (clicking, typing, extracting data)
    • Does it require login or authentication?

  2. Define the task clearly

    • Break complex workflows into clear steps
    • Specify what data to extract if applicable
    • Note any buttons or elements to interact with

  3. Start the browsing task Use run_browsing_task with:

    • task: Clear natural language instructions
    • start_url: The URL to begin browsing
    • max_steps: 25 (default) to 100 for complex flows
    • require_auth: true: For login forms or other authenticated workflows
    • browser: "local": When the task should run through Yutori Local with the user's desktop session
    • output_fields: For structured data extraction (e.g., ["name", "price", "url"])
    • webhook_url: HTTPS URL for completion notification
    • webhook_format: scout (default), slack, or zapier

  4. Poll for results

    • Browsing typically takes 30-120 seconds depending on complexity
    • Use get_browsing_task_result to check status
    • Poll every 10-15 seconds until complete

  5. Review and validate

    • Check the extracted data or confirmation
    • Verify the task completed as expected

Task Writing Tips

  • Be specific about UI elements: "Click the blue 'Submit' button"
  • Reference visible text when possible
  • For forms, specify which fields get which values

$ARGUMENTS

Comments

Markdown supported