DrissionPage MCP Server
The DrissionPage MCP Server lets you automate a local Chrome/Chromium browser from LLM clients (Claude, Codex, Cursor, etc.) using 46 structured, deterministic tools instead of screenshots. Here's what you can do:
Navigation & Tabs
Navigate to URLs, go back/forward, refresh, and get the current URL
List, switch, and close browser tabs with stable MCP tab IDs
Element Interaction
Find single or multiple elements by CSS selector or XPath
Click, type text, hover, scroll into view, upload files, select options, check/uncheck controls
Read element text, attributes, DOM properties, and HTML
Page Understanding
Take viewport or full-page screenshots (inline or saved to disk)
page_snapshot— get a bounded outline of headings, links, buttons, inputs, and forms with recommended selectorspage_observe— get a compact page fingerprint: URL, title, element counts, text samples, active element, and console summary
Form Automation
form_inspect— get a full inventory of forms and controls (labels, selectors, requirements, options) for safe filling and submission
JavaScript & Page Control
Execute custom JavaScript and return JSON-safe results
Click by coordinates, scroll in any direction, resize the browser window
Read browser console logs with level filtering and pagination
Frames & Shadow DOM
List iframes, inspect them with outline data, and find elements inside iframes or open shadow roots
Storage & Cookies
Get, set, and clear cookies, localStorage, and sessionStorage
Waiting & Synchronization
Wait for elements to appear, be clickable, or stable; wait for URL changes; or wait a fixed time
Observability
Enable
observe=trueon navigate, click, and type actions to get before/after change summaries (URL, title, appeared/removed text, console errors)
MCP Resources & Prompts
Access session summaries, history, state, and tool catalogs via MCP resource URIs
Use built-in prompts for common tasks: navigating & summarizing, extracting structured data, filling forms safely, and debugging page issues
All tools return structured JSON (ok, message, data, typed error) with bounded outputs to prevent oversized responses.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DrissionPage MCP ServerGo to news.ycombinator.com and extract the top 10 headlines"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
DrissionPage MCP Server
Professional browser automation for Codex, Claude Code, and MCP clients, powered by DrissionPage.
DrissionPage is a Python web automation library built around direct Chromium/CDP control with requests-style HTTP session support. This server exposes its browser-facing capabilities as typed, atomic MCP tools.

Open the interactive Browser Lab to replay bounded natural pointer motion, drag controls, and verify observable state.
Official Repositories: GitHub | GitCode
🖱️ Atomic Browser Control with Natural Pointer Motion
DrissionPage MCP 0.8.0 exposes 69 typed browser capabilities. The MCP server provides accurate low-level observation and interaction; the client or an optional Skill composes those capabilities for a site, component library, or business workflow.
The model decides what to do; the MCP executes the requested browser operation exactly.
Screenshot / page observation
↓
Multimodal model identifies viewport coordinates
↓
page_click_xy(x=442, y=369, profile="natural")
↓
24-step eased cubic path → exact target → press → release
↓
Observe and verify the resulting page stateCore interaction guarantees
Two bounded profiles:
directemits one exact move;naturalemits a deterministic 24-step eased cubic path with reproducible 8-14ms intervals and exact final arrival.No hidden randomness: the same start, target, and profile produce the same path; there is no jitter, overshoot, or anti-detection logic. Pointer position is stateful, so a repeated call can begin from the previous endpoint.
Explicit sequences: click is the selected move profile, optional caller-specified delay, press, release; drag keeps one press across the selected path and ordered waypoints.
Failure-safe input: a pressed pointer button is released if execution fails after the press.
Fresh browser evidence: selector geometry is resolved immediately before selector-backed drag operations.
Typed results: outputs report the executed coordinates, button, step count, and explicit delay metadata.
Use structured DOM targets when reliable selectors exist. Use coordinates, natural motion, and explicit drag waypoints for canvas controls, editors, maps, charts, and other visual-only surfaces. Component-specific target discovery, challenge observation, multi-click sequencing, login procedures, and other business policy belong in the client or an optional Skill.
{
"x": 442,
"y": 369,
"profile": "natural",
"button": "left",
"element": "visually identified control"
}Designed for authorized browser automation, testing, accessibility workflows, and technical research. The core does not provide challenge-specific or site-specific workflows.
Related MCP server: WaveXisMCP
🧭 Client Setup Navigation
🚀 What is DrissionPage MCP?
DrissionPage MCP Server is a local Model Context Protocol (MCP) server that brings DrissionPage browser automation tools to Codex CLI/IDE, Claude Code, Claude Desktop, and other MCP clients.
The standalone server exposes 69 typed tools, zero MCP prompts, and one static optional-Skills catalog resource. Version 0.8.0 stabilizes that registry with opt-in Web Storage values, redacted keyboard results, selector/coordinate/keyboard download correlation, fail-closed timeout cleanup, and clearer browser-start/runtime errors. Every tool loads by default; there is no capability profile or opt-in full mode. Models compose these atomic capabilities, while reusable procedures live outside the distribution as optional Skills. Browser execution is powered by DrissionPage.
🌟 Why Choose DrissionPage MCP?
Structured-First, Vision-Ready: Uses DOM structure when available and multimodal coordinates when visual interaction is the better tool
Deterministic: Reliable element selection with CSS/XPath normalization for LLM-friendly selectors
Natural Pointer Motion: Offers exact direct movement and a bounded deterministic 24-step eased trajectory from the same atomic tools
Fast & Lightweight: Built on DrissionPage's efficient engine with minimal overhead
Type-Safe: Full type hints and Pydantic validation for all tools
Open-source Friendly: Includes compatibility notes, troubleshooting, and CI checks for maintainable contributions
Easy Integration: Simple
pip install+ Codex TOML or MCP JSON configuration
✅ Quality and Real-World Validation
DrissionPage MCP is backed by a strict regression suite and browser-backed scenario checks:
Strict automated tests: unit, protocol, schema snapshot, response-contract, resource, release-metadata, security-policy, browser-integration, and coverage checks run in CI.
95% coverage floor: CI enforces the current 95% coverage threshold and uploads coverage reports.
Real browser verification: Chrome/Chromium-backed integration tests exercise the same MCP tools exposed to clients.
Document-boundary verification: focused browser tests prove cross-origin OOPIF reads and DrissionPage-exposed closed Shadow DOM lookup without JavaScript piercing fallbacks.
Scenario validation: the playground MCP Lab covers realistic forms, commerce pages, social feeds, timelines, dynamic waits, iframe cases, and recovery paths without depending on public demo websites.
⚡ First Success Path
# Install from PyPI
python -m pip install -U "drissionpage-mcp>=0.8.0"
# Verify package and environment
drissionpage-mcp --version
drissionpage-mcp doctorThen add the Codex or MCP client configuration below and restart your client.
📦 Setup in Codex CLI/IDE (30 seconds)
Codex supports local stdio MCP servers through config.toml; the CLI and IDE extension share the same MCP configuration.
Edit Codex configuration:
User-level:
~/.codex/config.tomlProject-level:
.codex/config.tomlinside a trusted project
Add this configuration:
[mcp_servers.drissionpage] command = "drissionpage-mcp" startup_timeout_sec = 20 tool_timeout_sec = 60Restart Codex. In the TUI, run
/mcp; from a shell, runcodex mcp list.
For Claude Code, Claude Desktop, and other JSON-based MCP clients, see Integration Examples.
🎯 Quick Examples
Navigate and Screenshot
"Visit https://example.com and take a screenshot for me"Search and Extract
"Go to Wikipedia, search for Python, and get the first paragraph"Form Automation
"Fill out the form at https://httpbin.org/forms/post and submit it"Data Scraping
"Get the top 10 news headlines from news.ycombinator.com"🛠️ 69 Typed Browser Tools
🌐 Navigation (5 tools)
page_navigate- Navigate to any URL; optionally open it in a new tab withnew_tabor return anobservechange summarypage_navigate_with_http_auth- Navigate through a scoped HTTP auth challenge in a dedicated disposable Chromium context without returning credentialspage_go_back- Navigate backward in browser historypage_go_forward- Navigate forward in browser historypage_refresh- Reload current page
🗂️ Tab Operations (3 tools)
tab_list- List open browser tabs with stable MCP tab IDstab_switch- Switch to a tab returned bytab_listtab_close- Close one tab without closing the whole browser
🎯 Element Interaction & Extraction (16 tools)
element_find- Find one element by CSS selector or XPath; bare selectors likeh1are treated as CSSelement_find_all- Extract bounded repeated elements with text, attributes, and recommended selectorselement_click- Click any element with additive left/right/middle and single/double-click semanticselement_click_and_download- Correlate one selector, coordinate, or keyboard trigger with one integrity-checked artifact underDP_MCP_DOWNLOAD_ROOTelement_type- Input text into elementselement_upload_file- Useelement_upload_file(paths=[...])to upload files fromDP_MCP_UPLOAD_ROOTtoinput[type=file]element_click_and_upload- Arm Chromium's file chooser, click its trigger, inject approved files, and clean interception without an operating-system pickerelement_scroll_into_view- Bring an element into the viewport before actingelement_hover- Hover an element to trigger menu/tooltip stateselement_select- Select an option by value, text, or indexelement_check- Check or uncheck checkbox/radio controlselement_get_text- Get element or page textelement_get_attribute- Get an HTML attributeelement_get_property- Get a live DOM property such as an input valueelement_get_html- Get element or page HTMLelement_state_get- Read live DrissionPage state flags and document/viewport geometry for one element
📸 Page Operations (18 tools)
page_screenshot- Capture an inline full-page or viewport screenshotpage_screenshot_save- Save a screenshot underDP_MCP_SCREENSHOT_ROOTpage_export_artifact- Generate a managed PDF or MHTML artifact underDP_MCP_ARTIFACT_ROOTwith SHA-256 and receipt evidencepage_snapshot- Return a bounded page outline with headings, links, buttons, inputs, forms, and selector recommendationspage_accessibility_snapshot- Return a bounded Chromium accessibility tree for the page or a scoped element, with field values redacted unless explicitly requestedpage_observe- Return a compact page fingerprint with URL, title, counts, visible text samples, active element, and recent console summarypage_evaluate- Run bounded JavaScript in the current page and return a JSON-safe resultpage_scroll- Usepage_scroll(pixels=...)for relative scrolling, or passx/yfor an absolute positionkeyboard_press- Send keys to the active element/page without echoing the input in resultspage_resize- Adjust browser windowpage_pointer_move- Move to exact viewport CSS coordinates withdirector bounded deterministicnaturalmotionpage_pointer_drag- Perform one failure-safe coordinate drag through up to six optional ordered waypoints with the selected profilepage_pointer_drag_element- Resolve source and destination geometry immediately before dragging; supports CSS/XPath in the top document or one same-origin iframe, plus CSS paths through nested open Shadow DOM hostspage_click_xy- Move withdirectornaturalmotion, optionally wait for an explicit delay, then press and release at the exact targetpage_close- Close browserpage_get_url- Get current URLpage_dialog_observe- Wait for and inspect a pending native alert, confirm, or prompt without handling itpage_dialog_respond- Usepage_dialog_respond(action="accept")(or"dismiss") for one pending alert, confirm, or prompt
🧱 Frame / Shadow DOM (5 tools)
frame_list- List iframe/frame contexts without changing global frame stateframe_snapshot- Useframe_snapshot(frame_selector="...")orframe_indexto inspect one iframe with bounded outline dataframe_find- Find an element inside a selected iframeshadow_find- Find one element inside a shadow root exposed by the current supported DrissionPage runtime, including tested closed rootsshadow_find_all- Extract repeated elements from a DrissionPage-exposed shadow root
🌍 Browser Environment (6 tools)
browser_headers_set- Replace extra request headers and echo the accepted values; an empty object clears thembrowser_user_agent_set- Override the user agent and optional platform, returning both the accepted and previous user agentsbrowser_cache_clear- Clear HTTP cache while preserving Cookies, localStorage, and sessionStoragebrowser_permission_get- Query one browser permission for the current document origin without opening an OS promptbrowser_permission_set- Usebrowser_permission_set(setting="granted")(or"denied"/"prompt") for an exact origin/current Chromium contextbrowser_permissions_reset- Reset permission overrides for the current Chromium context
🍪 Cookies & Storage (7 tools)
browser_cookies_get- Read normalized cookies with values redacted by defaultbrowser_cookies_set- Set up to 100 cookies in one call and echo values in the successful result by defaultbrowser_cookies_delete- Delete one named cookie with optional URL/domain/path scopebrowser_cookies_clear- Clear all browser cookiesstorage_get- Read localStorage/sessionStorage by key or as a map, with values redacted unlessinclude_values=truestorage_set- Set one localStorage/sessionStorage item without echoing the valuestorage_clear- Clear one storage key or an entire storage area
🧪 Debug / Observability (1 tool)
page_console_logs- Read bounded browser console messages with level filtering, cursor pagination, and limits
⏱️ Wait Operations (4 tools)
wait_for_element- Wait for element to appear (with timeout)wait_for_url- Usewait_for_url(url_pattern="...")until the current URL contains the supplied textwait_until- Usewait_until(condition="text_contains", value="...")or another documented condition/value pairwait_time- Delay execution
🌐 Network Control & Observation (4 tools)
network_listen_start- Start bounded HTTP/XHR/Fetch observation through DrissionPagenetwork_listen_wait- Wait for bounded packet metadata with optional redacted headers or body excerptsnetwork_listen_stop- Stop observation and optionally clear queued packetsnetwork_blocked_urls_set- Usenetwork_blocked_urls_set(urls=[...])to replace blocked URL patterns; an empty list clears them
🧩 Optional Skills Discovery
Resource:
drissionpage://skills/catalogPrompts: none
Repository convention:
skills/<skill-name>/SKILL.md, for exampleskills/drissionpage-visual-workflows/SKILL.mdSkills are optional and separately published; the MCP server remains fully usable without them.
📚 Documentation
Guide | Description |
Installation, tools, and architecture | |
Supported Python, DrissionPage, MCP, and browser versions | |
Public MCP tool names, inputs, annotations, and response shape | |
Doctor command, browser startup, and client setup fixes | |
Release notes |
🏗️ Architecture
Built with clean, modular design:
DrissionMCP/
├── drissionpage_mcp/
│ ├── cli.py # Process entry point
│ ├── server.py # MCP transport and request routing
│ ├── context.py # Browser and tab lifecycle facade
│ ├── runtime.py # Operation keys, receipts, artifacts, and capability state
│ ├── tool_outputs.py # Typed public result contracts
│ ├── browser/ # Focused DrissionPage capabilities and page scripts
│ └── tools/ # 69 typed MCP tool definitions and thin adapters
├── tests/ # Unit tests
└── playground/ # MCP Lab business-scenario playgroundKey Principles:
✅ Type-safe Pydantic models for all tools
✅ Async/await throughout
✅ Clean separation of concerns
✅ Comprehensive error handling
✅ Unit and protocol test coverage for core tool registration/response behavior
🔧 Configuration
Codex CLI / IDE (Recommended)
[mcp_servers.drissionpage]
command = "drissionpage-mcp"
startup_timeout_sec = 20
tool_timeout_sec = 60
# Optional browser/runtime environment variables:
# [mcp_servers.drissionpage.env]
# CHROME_PATH = "/custom/path/to/chrome"
# DP_HEADLESS = "1"You can also add it with the Codex CLI:
codex mcp add drissionpage -- drissionpage-mcpIf Codex/Cursor/Claude Desktop is launched from a GUI and cannot see your shell
PATH or virtualenv, use the absolute Python executable instead:
[mcp_servers.drissionpage]
command = "/absolute/path/to/python"
args = ["-m", "drissionpage_mcp.cli"]
startup_timeout_sec = 20
tool_timeout_sec = 60JSON MCP Clients
{
"mcpServers": {
"drissionpage": {
"command": "drissionpage-mcp"
}
}
}Advanced JSON Setup
{
"mcpServers": {
"drissionpage": {
"command": "drissionpage-mcp",
"args": ["--log-level", "DEBUG"],
"env": {
"CHROME_PATH": "/custom/path/to/chrome"
}
}
}
}Absolute-Python fallback for GUI clients:
{
"mcpServers": {
"drissionpage": {
"command": "/absolute/path/to/python",
"args": ["-m", "drissionpage_mcp.cli"],
"env": {
"CHROME_PATH": "/custom/path/to/chrome",
"DP_HEADLESS": "1"
}
}
}
}📋 Requirements
Python 3.10+ (3.11+ recommended)
Chrome or Chromium browser
Any MCP-compatible client: Codex CLI/IDE, Claude Code, Claude Desktop, Cursor, VS Code, etc.
🧪 Testing
Verify Installation
# Environment diagnostics; add --launch-browser for a browser startup check
drissionpage-mcp doctor
drissionpage-mcp doctor --launch-browser
# Source checkout tests
python -m pip install -e ".[dev]"
python -m pytest tests/
# Coverage report (CI enforces the current 95% floor and uploads coverage.xml)
python -m pytest tests/ --cov=drissionpage_mcp --cov-report=term-missing --cov-report=xml
# Browser-backed MCP Lab scenario checks
DP_HEADLESS=1 python playground/run_mcp_lab.py --all --jsonGitHub Actions runs lint, unit, protocol, package, browser integration, and
coverage jobs. Codecov is configured through codecov.yml and the CI workflow.
Try It Out
# No-browser MCP registry check
python playground/run_mcp_lab.py --case registry
# Local deterministic site check
python playground/run_mcp_lab.py --case site
# Browser-backed form inspection scenario
DP_HEADLESS=1 python playground/run_mcp_lab.py --case form-inspect🚀 Use Cases
✅ Automated Testing - Test web applications ✅ Data Scraping - Extract structured data from websites ✅ Form Automation - Fill and submit forms ✅ Monitoring - Check for updates or changes ✅ Screenshot Verification - Capture and verify page state ✅ Content Analysis - Analyze web content programmatically
🐛 Troubleshooting
Tools Not Loading?
drissionpage-mcp --versionShould output the installed package version, for example drissionpage-mcp 0.8.0.
drissionpage-mcp doctor must also report both mcp_supported and
mcp_server_wiring as ok; package-version output alone does not prove that an
MCP client can initialize the server.
Browser Issues?
# Check browser installation
which google-chrome # Linux
which chromium # macOSCodex / MCP Client Not Finding Server?
Codex: run
codex mcp list; in the TUI, run/mcpJSON clients: verify config file path and JSON syntax
Restart Codex or your MCP client after changes
Check logs:
drissionpage-mcp --log-level DEBUG
See docs/troubleshooting.md for the complete troubleshooting guide.
📊 Project Status
Component | Status |
Core Features | ✅ Complete |
Testing | ✅ Strict unit/protocol/schema checks plus browser-backed scenarios |
Documentation | ✅ Setup, compatibility, troubleshooting, and public tool contracts |
Package | ✅ PyPI metadata and build checks |
Status | 🟡 Beta; real browser behavior depends on local Chrome/Chromium and target sites |
Version: 0.8.0 | License: Apache 2.0 | Maintained: ✅ Active
🗺️ Roadmap
Current (v0.8.0)
69 atomic navigation, tab/frame/shadow, accessibility, observation, interaction, browser-environment, network, Cookie/storage, wait, and console tools, all loaded by default
stdio MCP server integration
Doctor diagnostics for local setup
Stable JSON mirror,
structuredContent, and typed per-tool MCPoutputSchemaStructured recovery hints in
error.details.hintsfor common failuresSanitized browser failures with
DIALOG_PENDING/DIALOG_NOT_FOUNDrecovery and strict standards-compliant JSON for non-finite JavaScript valuesBalanced
page_snapshotoutput so link-heavy pages still expose controls and formsAtomic type, select, check, click, keyboard, upload, wait, and state-read tools cover native controls and framework-driven widgets without library-specific branches
Tab management with
tab_list,tab_switch,tab_close, andpage_navigate(new_tab=true)Observable actions with
page_observe,page_evaluate,wait_until, and optionalobserve=truechanges on navigation, click, and typeConsole observability with
page_console_logs, console summary inpage_observe, and console change fields inobserve=trueForm, component-library, challenge, and convenience workflows remain outside the MCP core
Optional Skills are discoverable through one static resource and excluded from wheel and sdist packages
Capability-probed
page_dialog_respond, additive double/context click behavior, and selector/coordinate/keyboard download correlation with safeArtifactRefmetadataSecret-bearing Web Storage values require
include_values=true; keyboard and keyboard-download results expose redacted metadata onlyPer-tab download trigger locking, shared deadlines, cleanup/replay guarantees, and a 250ms fail-closed late-mission guard
Reproducible W01-W08 public-tool benchmark with ten isolated runs per workload, machine-readable evidence, and zero duplicate side effects
Network listener beta with
network_listen_start,network_listen_wait, andnetwork_listen_stopfor HTTP/XHR/Fetch observationBrowser-only request environment control with echoed header, user-agent, and blocked-URL writes plus cache-only clearing that preserves Cookies and Web Storage
directand deterministic boundednaturalprofiles forpage_pointer_move,page_pointer_drag, andpage_click_xy, with exact endpoints and failure-safe releaseOptional bounded
page_pointer_drag.waypointsfor one held multi-segment canvas, map, box-selection, or visual-editor gestureFile upload, scrolling, hover, select/check, keyboard, iframe, shadow DOM, cookie, and storage tools for DrissionPage 4.x
Pure browser Cookie set/get/delete/clear flow, including bounded batch writes whose successful results echo values for MCP callbacks
Ten-cycle controlled and validation input replacement through native DrissionPage input on the supported browser matrix
Cross-origin OOPIF reads through
frame_*and closed Shadow DOM lookup through DrissionPage-backedshadow_*, with narrower pointer targeting documented separatelyBackward-compatible string or structured selector/accessibility targets across element reads, actions, waits, uploads, and click-download correlation, resolving ordered frames first and then ordered Shadow DOM hosts
Bounded accessibility snapshots, non-handling native dialog observation, and live element state/geometry for autonomous locate-act-verify loops
Browser permission observation/set/reset, managed PDF/MHTML artifacts, automatic file chooser interception, and credential-redacted HTTP auth isolated by disposable Chromium context
Chrome sandbox remains enabled by default;
DP_NO_SANDBOX=1is reserved for restricted container/root environmentsNo retained action history, generated code snippets, or absolute screenshot paths in public results
Opt-in local safety policy for navigation and screenshot paths
One optional-Skills catalog resource, zero prompts, plus eval, compatibility, and troubleshooting documentation
PyPI distribution
📖 Integration Examples
Codex CLI / IDE
[mcp_servers.drissionpage]
command = "drissionpage-mcp"
startup_timeout_sec = 20
tool_timeout_sec = 60Verify with:
codex mcp listClaude Code
{
"mcpServers": {
"drissionpage": {
"command": "drissionpage-mcp"
}
}
}Config file: ~/.config/claude-code/mcp_settings.json (macOS/Linux) or
%APPDATA%\claude-code\mcp_settings.json (Windows).
Cursor
{
"mcpServers": {
"drissionpage": {
"command": "drissionpage-mcp"
}
}
}Config file: ~/.cursor/mcp.json (global) or .cursor/mcp.json (project). You
can also add it from Cursor Settings → Tools & MCPs → New MCP Server.
Claude Desktop
{
"mcpServers": {
"drissionpage": {
"command": "drissionpage-mcp"
}
}
}Once connected, the tools load automatically:
🤝 Contributing
Contributions are welcome!
Fork the repository
Create a feature branch
Make focused changes
Run the relevant checks
Submit a pull request
See CONTRIBUTING.md for setup, validation, and compatibility expectations.
🔒 Security
Runs locally in your environment
Uses a local browser that may have access to authenticated sessions, cookies, downloads, and page content
Can open and interact with any site reachable from the local machine
Does not require external API credentials
Best Practices:
Use a dedicated browser profile for sensitive workflows
Review MCP client prompts before allowing actions on authenticated or production systems
Respect website terms of service, robots.txt, and rate limits
See SECURITY.md for reporting and safe-usage guidance
📄 License
Licensed under Apache License 2.0 - see LICENSE
📈 Statistics
🌟 Show Your Support
If you find this project useful, please consider:
⭐ Starring on GitHub
📤 Sharing with your network
💬 Leaving feedback or suggestions
🐛 Reporting issues to help improve
Made with ❤️ by Wukunyun
Ready to automate your workflows? Install now: python -m pip install -U drissionpage-mcp
🆕 Latest Version: v0.8.0
Released on 2026-07-31. This release stabilizes the 69-tool contract without adding public tool names or bundling Skills, component adapters, or business workflows:
Makes localStorage/sessionStorage values opt-in through
include_values=true, and returns redacted metadata fromkeyboard_pressand keyboard-triggered downloads.Extends
element_click_and_downloadwith strict coordinate and keyboard triggers while preserving selector/accessibility calls, operation-key replay, and one-trigger/one-mission correlation.Serializes generic download triggers per tab under one shared deadline, restores prior state on all terminal paths, and cancels late missions during a 250ms fail-closed guard.
Classifies browser-start and dialog failures before generic runtime fallback while redacting localized DrissionPage, CDP, private destination, and rejected-path details.
Enforces Ruff and mypy in GitHub CI, then runs multi-version unit/protocol tests, browser boundaries, full browser coverage, W01-W08, clean-wheel stdio, and package privacy gates.
Keeps advanced held-key, IME/composition, touch/pinch, and clipboard capabilities deferred until their lifetime, cleanup, policy, and browser support can be verified.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityDmaintenanceAn MCP server providing robust browser automation tools for AI assistants, including page navigation, element interaction, and screenshot capabilities. It leverages the DrissionPage library to enable standardized DOM analysis, network monitoring, and complex web task automation.17MIT
- AlicenseAqualityAmaintenanceA comprehensive browser automation MCP server providing 149 tools across 13 capability tiers, enabling LLMs to control Chrome/Edge via CDP or BiDi protocols with features like navigation, screenshots, network interception, and more.2721MIT
- Alicense-qualityCmaintenanceA browser automation MCP server with stealth mode, profile management, and multi-browser support, enabling LLMs to control browsers for tasks like navigation, data extraction, and form filling.231MIT
- Alicense-qualityBmaintenanceMCP server that bridges Model Context Protocol with browser automation, offering 37 tools across three modes (Playwright, CDP, Chrome Extension) and an autonomous agent for web tasks.MIT
Related MCP Connectors
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
A paid remote MCP for AI agent browser DevTools MCP, built to return verdicts, receipts, usage logs,
Zenrows MCP server — Fetch, Extract, Batch, and Browser Sessions for AI coding assistants
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jumodada/Drissionpage-MCP-Server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server