// SCAN REPORT

AutoProbeMCP

14 tools. 8 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

8 can modify or destroy data

6 read-only

14 tools total

Community server · catalogue entry verified 29/06/2026

How to control AutoProbeMCP ↓

TOOL MAP

What AutoProbeMCP exposes to your agents

Read (6) Write / Execute (8) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous AutoProbeMCP tools

Execute · Medium evaluate_javascript Execute JavaScript in the browser context Execute · Medium launch_browser Launch a new browser instance (chromium, firefox, or webkit) Execute · Medium navigate Navigate to a URL Execute · Medium wait_for_element Wait for an element to appear or disappear

8 of AutoProbeMCP's 14 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control AutoProbeMCP

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

Rate limit write operations

{
  "click_element": {
    "limits": [
      {
        "counter": "click_element_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_screenshot": {
    "limits": [
      {
        "counter": "analyze_screenshot_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 AutoProbeMCP — 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 AUTOPROBEMCP →

Instant setup, no code required.

FULL CATALOGUE

All 14 AutoProbeMCP tools

EXECUTE 4 tools

Execute evaluate_javascript Execute JavaScript in the browser context Execute launch_browser Launch a new browser instance (chromium, firefox, or webkit) Execute navigate Navigate to a URL Execute wait_for_element Wait for an element to appear or disappear

WRITE 4 tools

Write click_element Click on an element by CSS selector Write close_browser Close the current browser instance Write scroll Scroll the page in the specified direction Write type_text Type text into an input field

READ 6 tools

Read analyze_screenshot Take a screenshot and analyze it with AI (Gemma3) to describe what is visible on the page Read check_scrollability Check if the page is scrollable in the specified direction Read get_console_logs Get console logs from the browser Read get_element_text Get text content of an element Read get_page_info Get information about the current page Read screenshot Take a screenshot of the current page

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about AutoProbeMCP

How do I prevent bulk modifications through AutoProbeMCP? +

The AutoProbeMCP server has 4 write tools including click_element, close_browser, scroll. 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 AutoProbeMCP.

How many tools does the AutoProbe MCP server expose? +

14 tools across 3 categories: Execute, Read, Write. 6 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on AutoProbeMCP? +

Register the AutoProbe 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 AutoProbeMCP tool call.

Deterministic rules across all 14 AutoProbeMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AUTOPROBEMCP →

Instant setup, no code required.

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