// SCAN REPORT

RunAutomation MCP Server

91 tools. 63 can modify or destroy data without limits.

4 destructive tools with no built-in limits. Policy required.

Last updated:

63 can modify or destroy data
28 read-only
91 tools total

Community server · catalogue entry verified 12/06/2026

How to control RunAutomation MCP Server ↓

TOOL MAP

What RunAutomation MCP Server exposes to your agents

Read (28) Write / Execute (59) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous RunAutomation MCP Server tools

Destructive · Medium clear_codegen_session Clearing a codegen session irreversibly destroys the recorded browser automation actions accumulated in that session. Destructive · Medium close_browser_session This tool irreversibly terminates a browser session and destroys all associated resources (browser instance, pages, context). Destructive · Medium playwright_close Closing the browser and releasing all resources is irreversible — any unsaved browser state, open pages, and session data are permanently destroyed. Destructive · Medium cleanup_idle_sessions Closing browser sessions cannot be undone; any unsaved session state, cookies, or in-progress automation work is permanently lost.

63 of RunAutomation MCP Server's 91 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control RunAutomation MCP Server

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

Deny destructive operations
{
  "clear_codegen_session": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "playwright_stop_video_recording": {
    "limits": [
      {
        "counter": "playwright_stop_video_recording_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "get_codegen_session": {
    "limits": [
      {
        "counter": "get_codegen_session_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register RunAutomation MCP Server — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON RUNAUTOMATION →

Free to start. No card required.

FULL CATALOGUE

All 91 RunAutomation MCP Server tools

DESTRUCTIVE 4 tools
Destructive clear_codegen_session Clear a code generation session without generating a test Destructive cleanup_idle_sessions Automatically close idle browser sessions that haven Destructive close_browser_session Close a specific browser session and cleanup all resources including browser instance, pages, and context. Destructive playwright_close Close the browser and release all resources
EXECUTE 50 tools
Execute playwright_delete Perform an HTTP DELETE request Execute playwright_batch_ai_visual_compare Run batch AI visual comparisons across multiple pages Execute playwright_emulate_device Emulate a mobile device with specific viewport, user agent, and capabilities. Supports all Playwright device p Execute playwright_evaluate Execute JavaScript in the browser console Execute playwright_expect_response Ask Playwright to start waiting for a HTTP response. This tool initiates the wait operation but does not wait Execute playwright_navigate Navigate to a URL Execute playwright_recover_session Recover a persisted session from disk after crash or restart Execute playwright_run_across_browsers Execute actions across multiple browsers in parallel. Tests cross-browser compatibility by running the same ac Execute playwright_run_cross_browser Run a test across multiple browsers (chromium, firefox, webkit) in parallel Execute playwright_run_tests_parallel Execute multiple test scenarios in parallel with configurable concurrency Execute playwright_start_coverage Start collecting JavaScript and CSS code coverage Execute playwright_start_video_recording Start recording video of browser session. Useful for test debugging and documentation. Execute playwright_wait_attribute Wait for element attribute to have specific value Execute playwright_wait_element_count Wait for specific number of elements matching a selector Execute playwright_wait_element_hidden Wait for element to become hidden or disappear Execute playwright_wait_network_idle Wait for network activity to become idle Execute playwright_wait_smart Intelligent wait for element with multiple conditions (visibility, stability, interactive state) Execute playwright_wait_url Wait for URL to match a specific pattern Execute start_codegen_session Start a new code generation session to record Playwright actions Execute playwright_ai_visual_compare AI-powered visual regression testing that intelligently ignores dynamic content like ads and timestamps Execute playwright_assert_css_property Assert CSS property value using computed styles Execute playwright_assert_element_count Assert exact count of elements matching a selector with flexible comparison Execute playwright_assert_element_state Assert element state (visible, hidden, enabled, disabled, editable, readonly, checked, unchecked) Execute playwright_assert_response Wait for and validate a previously initiated HTTP response wait operation. Execute playwright_assert_text_content Assert element text content with fuzzy search support (exact, contains, startsWith, endsWith, regex) Execute playwright_batch_visual_compare Compare multiple screenshots against their baselines in a single operation. Useful for comprehensive visual re Execute playwright_check_accessibility Run comprehensive accessibility scan using axe-core for WCAG compliance Execute playwright_cross_browser_screenshot Capture and compare screenshots across multiple browsers. Automatically detects visual differences between bro Execute playwright_download_and_extract_pdf Download a PDF file by clicking a trigger element and optionally extract its text content. Useful for testing Execute playwright_download_file Handle file downloads triggered by clicking an element. Waits for download to complete and saves the file. Execute playwright_expect_dialog Wait for a dialog to appear, validate its message, and handle it. Useful for testing alert/confirm/prompt dial Execute playwright_go_back Navigate back in browser history Execute playwright_go_forward Navigate forward in browser history Execute playwright_hover Hover an element on the page Execute create_browser_session Create a new browser session with isolated context. Enables parallel browser execution and multi-user scenario Execute playwright_click Click an element on the page Execute playwright_click_and_switch_tab Click a link and switch to the newly opened tab Execute playwright_copy_to_clipboard Copy text to the browser clipboard using the Clipboard API Execute playwright_drag Drag an element to a target location Execute playwright_drag_to_position Drag an element to specific coordinates on the page with smooth animation Execute playwright_fill fill out an input field Execute playwright_handle_dialog Set up a handler for the next browser dialog (alert, confirm, or prompt). The handler will be called when a di Execute playwright_iframe_click Click an element in an iframe on the page Execute playwright_iframe_fill Fill an element in an iframe on the page Execute playwright_patch Perform an HTTP PATCH request Execute playwright_post Perform an HTTP POST request Execute playwright_press_key Press a keyboard key Execute playwright_put Perform an HTTP PUT request Execute playwright_select Select an element on the page with Select tag Execute switch_browser_session Switch the current active session to a different browser session. All subsequent browser operations will use t
WRITE 9 tools
Write playwright_stop_video_recording Stop video recording and save the file with optional annotations Write end_codegen_session End a code generation session and generate the test file Write playwright_add_video_annotation Add a timestamped annotation/marker to the current video recording Write playwright_configure_video_settings Configure default video recording settings (output directory, quality, FPS) Write playwright_create_baseline Create a baseline screenshot for visual regression testing Write playwright_custom_user_agent Set a custom User Agent for the browser Write playwright_save_as_pdf Save the current page as a PDF file Write playwright_update_resource_limits Update resource limits and throttling configuration Write playwright_upload_file Upload a file to an input[type=
READ 28 tools
Read get_codegen_session Get information about a code generation session Read get_session_info Get detailed information about a specific browser session including uptime, current URL, console logs, and act Read list_browser_sessions List all active browser sessions with their details including session ID, browser type, current URL, and activ Read playwright_assert_attribute Assert element attribute value with flexible matching Read playwright_assert_request_made Assert that a network request was made matching URL pattern and optional method Read playwright_check_contrast Check color contrast ratio for WCAG compliance Read playwright_check_keyboard_navigation Check keyboard navigation and focusable elements on the page Read playwright_compare_coverage Compare coverage between baseline and current test runs Read playwright_console_logs Retrieve console logs from the browser with filtering options Read playwright_count_pdf_pages Count the number of pages in a PDF file and get PDF metadata information. Read playwright_extract_pdf_text Extract text content from a PDF file. Useful for verifying PDF generation and content validation. Read playwright_get Perform an HTTP GET request Read playwright_get_aria_snapshot Get ARIA accessibility tree snapshot of the page or element Read playwright_get_coverage Stop coverage collection and get results with detailed statistics Read playwright_get_element_position Get the position and dimensions of an element on the page Read playwright_get_persistence_stats Get statistics about persisted sessions on disk Read playwright_get_resource_usage Get current resource usage statistics (browsers, sessions, memory, queue) Read playwright_get_video_status Get current video recording status including duration and annotation count Read playwright_get_visible_html Get the HTML content of the current page. By default, all <script> tags are removed from the output unless rem Read playwright_get_visible_text Get the visible text content of the current page Read playwright_list_devices List all available device emulations supported by Playwright. Returns device names with their viewport sizes. Read playwright_read_clipboard Read text from the browser clipboard using the Clipboard API Read playwright_recover_all_sessions Recover all persisted sessions from disk Read playwright_screenshot Take a screenshot of the current page or a specific element Read playwright_validate_pdf_content Validate that a PDF contains specific text content. Returns success if text is found, error if not. Read playwright_visual_compare Compare a screenshot against a baseline image for visual regression testing. Detects pixel differences and gen Read playwright_collect_locators Collect all visible, unique locators from the current page and generate a Page Object Model (POM) file. Automa Read playwright_generate_coverage_report Generate coverage report in various formats from coverage data file
EXPLORE

Related servers

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

Sperax Ecosystem Crypto & DeFI MCP Server 1318 tools
adminautomation
Mcp Afip 1300 tools
adminautomation
Mcp Ap2 1300 tools
adminautomation
BNB Chain MCP 1240 tools
adminautomation
Nodebench 824 tools
adminautomation
Amazon Bedrock Knowledge Base Retrieval MCP Server 805 tools
adminautomation
Amazon Data Processing MCP Server 805 tools
adminautomation
Amazon ECS MCP Server 805 tools
adminautomation
FAQ

Questions about RunAutomation MCP Server

Can an AI agent delete data through the RunAutomation MCP Server MCP server? +

Yes. The RunAutomation MCP Server server exposes 4 destructive tools including clear_codegen_session, cleanup_idle_sessions, close_browser_session. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through RunAutomation MCP Server? +

The RunAutomation MCP Server server has 9 write tools including playwright_stop_video_recording, end_codegen_session, playwright_add_video_annotation. 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 RunAutomation MCP Server.

How many tools does the RunAutomation MCP Server MCP server expose? +

91 tools across 4 categories: Destructive, Execute, Read, Write. 28 are read-only. 63 can modify, create, or delete data.

How do I enforce a policy on RunAutomation MCP Server? +

Register the RunAutomation MCP Server 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 RunAutomation MCP Server tool call.

Deterministic rules across all 91 RunAutomation MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RUNAUTOMATION →

Free to start. No card required.

91 RunAutomation MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.