// SCAN REPORT

Yocoolab

22 tools. 6 can modify or destroy data without limits.

6 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

6 can modify or destroy data

16 read-only

22 tools total

Community server · catalogue entry verified 02/07/2026

How to control Yocoolab ↓

TOOL MAP

What Yocoolab exposes to your agents

Read (16) Write / Execute (6) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Yocoolab tools

Execute · Medium ai_analyze_page This tool invokes an external AI service to analyze a web page, which constitutes triggering an external operation. Write · Medium add_thread_message This tool creates new content (messages) in an existing feedback thread, making it a Write operation. Write · High create_pr_for_thread This tool creates or modifies a GitHub pull request and adds commits to a branch — both reversible write operations. Write · Medium mark_thread_addressed This tool creates or modifies data reversibly: it changes the status of a feedback thread to 'resolved' and optionally appends a message.

6 of Yocoolab's 22 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Yocoolab

PolicyLayer is an MCP gateway — it sits between your AI agents and Yocoolab, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "add_thread_message": {
    "limits": [
      {
        "counter": "add_thread_message_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "find_source_for_selection": {
    "limits": [
      {
        "counter": "find_source_for_selection_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Yocoolab — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON YOCOOLAB →

Instant setup, no code required.

FULL CATALOGUE

All 22 Yocoolab tools

EXECUTE 1 tools

Execute ai_analyze_page Ask the Yocoolab AI assistant to analyze a web page. Supports text questions with optional screenshot (vision)

WRITE 5 tools

Write add_thread_message Add a message to a feedback thread without changing its status. Use this to post updates like preview URLs, im Write create_pr_for_thread Create a GitHub pull request (or add a commit to the existing working branch) with code changes that address a Write mark_thread_addressed Mark a feedback thread as resolved. Optionally add a message explaining how it was addressed. Write pendo_track_event Send a custom track event to Pendo. Use this to track actions like feedback resolved, PR created from feedback Write reply_to_companion Send a reply back to the AI Companion panel in the Chrome extension. The reply will appear as an assistant mes

READ 16 tools

Read find_source_for_selection Searches the workspace for source files that likely define or render the selected UI element. Returns ranked c Read get_activity_summary Get a high-level summary of Claude Code activity: total events, active sessions, tool usage breakdown, files t Read get_ai_conversations List recent AI assistant conversations. Returns conversation IDs, page URLs, and message counts. Read get_companion_messages Check for new messages from the AI Companion panel in the Chrome extension. Returns pending messages and clear Read get_dashboard_url Get the URL for the real-time activity monitoring dashboard. Open in a browser to see live Claude Code activit Read get_deployment_preview Check if a preview deployment is available for a specific repo and branch. Returns the preview URL if deployed Read get_element_context Returns a comprehensive summary of a UI element, including its DOM context, computed styles, and ranked source Read get_files_touched List all files that have been read, written, or edited across Claude Code sessions. Shows file paths with sess Read get_latest_selection Returns the most recent element selection from the Chrome extension. Includes element selector, tag, text cont Read get_recent_events Get the most recent Claude Code activity events (tool calls, prompts, errors). Shows timestamps, tool names, a Read get_selection_history Returns the last N element selections from the Chrome extension, newest first. Useful for comparing multiple e Read get_thread_context Get full details of a feedback thread including all messages, UI element context (selector, coordinates, eleme Read list_open_threads List unresolved feedback threads for a repository. Returns thread summaries with context about what UI element Read pendo_get_feature_usage Query Pendo for feature usage analytics (click events, unique visitors) over a time range. Useful for understa Read pendo_get_page_analytics Query Pendo for page-level analytics (page views, unique visitors, avg time on page). Use the page_url from th Read pendo_list_guides List active in-app guides from Pendo. Optionally filter by page URL to see what guides are deployed on a speci

FAQ

Questions about Yocoolab

How do I prevent bulk modifications through Yocoolab? +

The Yocoolab server has 5 write tools including add_thread_message, create_pr_for_thread, mark_thread_addressed. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Yocoolab.

How many tools does the Yocoolab MCP server expose? +

22 tools across 2 categories: Read, Write. 16 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Yocoolab? +

Register the Yocoolab MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Yocoolab tool call.

Deterministic rules across all 22 Yocoolab tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON YOCOOLAB →

Instant setup, no code required.

22 Yocoolab tools catalogued and risk-classified — across an index of 43,000+ MCP servers.