Ornold
Accueil
Qu’est-ce que MCP
Tarifs
Partenaires
Blog
Cas d'usage
Navigateurs
Commencer
MCP Server · Open Protocol

AI Browser Operations
for Dolphin Anty

Connect MCP-compatible AI agents to browser profiles you own. Automate authorized QA, internal operations, and repeatable web workflows with visual interaction and recovery.
Get Started
Practical Examples

See how it works in practice

Authorized QA and operations workflows running across browser profiles with Ornold MCP.

Prepare authorized browser workspaces

An AI agent connects to profiles your team owns, checks session readiness, and opens the approved workspace for a repeatable operation.

Prepare authorized browser workspaces

An AI agent connects to profiles your team owns, checks session readiness, and opens the approved workspace for a repeatable operation.
Vision Mode

Interact visually when layouts change

Instead of relying on CSS selectors or XPath that break on any layout change, our Vision approach takes a screenshot and uses AI to detect every interactive element with pixel-precise coordinates.
1
ScreenshotCapture viewport from each browser in parallel
2
CLIP GroupingGroup identical pages to analyze each layout only once
3
Element DetectionDetect elements with box coordinates [x1, y1, x2, y2]
4
Coordinate ClickClick the center of the detected element using normalized coordinates
https://workspace.example/review
Review workspace
Search
Status
Open
[ {id:1, type:"input", label:"Search"}, {id:2, type:"input", label:"Status"}, {id:3, type:"button", label:"Open"} ]
Protocole ouvert

Qu’est-ce que MCP ?

Model Context Protocol (MCP) est un standard ouvert d’Anthropic qui permet aux agents IA de se connecter à des outils externes via une interface universelle unique.

Un serveur, n’importe quel agent

L’intégration s’écrit une seule fois. Claude Code, Codex, Cursor, Windsurf et tout autre agent compatible MCP peuvent l’utiliser sans modification.

Contrats d’outils typés

Chaque outil a un schéma typé — nom, description, paramètres. L’agent IA découvre les outils automatiquement et sait exactement comment les appeler.

Pourquoi nous avons choisi MCP

Au lieu de créer des plugins séparés pour chaque agent IA, MCP permet à Ornold d’exposer plus de 30 outils d’automatisation de navigateur en une seule fois — et ils fonctionnent partout.
Écosystème MCP

Combinez avec n'importe quel serveur MCP

Ornold fonctionne aux côtés d'autres serveurs MCP dans un seul agent. Automatisation du navigateur + messagerie + tableurs + bases de données — le tout dans une seule conversation.
Claude Code
Codex
Claude Desktop
Kilo Code
Roo Code
Windsurf
Cursor
Augment Code
Gemini CLI
MCP PROTOCOL
🌐
Ornold Browser MCPConnect through supported APIs or CDP and operate only profiles your organization owns or is authorized to manage.
Dolphin AntyDolphin Anty
Octo BrowserOcto Browser
Linken SphereLinken Sphere
VisionVision
➕Any CDP
🔌
Écosystème MCPConnectez plusieurs serveurs MCP à un seul agent. Chacun gère son domaine — Ornold automatise les navigateurs, d'autres s'occupent de Slack, Excel, des bases de données et plus encore. L'agent orchestre le tout.
SlackSlack
Google SheetsGoogle Sheets
TelegramTelegram
PostgreSQLPostgreSQL
GitHubGitHub
GmailGmail
NotionNotion
StripeStripe
JiraJira
🔌 Any MCP
🌐 Ornold + ... =
Hover over a service to see how it works with Ornold
Core Features

Built for reliable browser operations

Tools for authorized QA and internal workflows, from vision-based interaction to controlled parallel execution across browser profiles.

Vision-First Approach

AI sees the page through screenshots, detects UI elements via vision analysis, and clicks by normalized coordinates. No fragile selectors.

Controlled Parallel Execution

Run approved QA and operations steps across multiple connected profiles. Smart concurrency adapts to system resources.

Approval Checkpoints

Pause sensitive steps for human review, preserve workflow state, and resume after an authorized operator confirms the action.

Configurable Interaction

Use visual coordinates or structured page references with predictable timing, clear logs, and reproducible behavior.

Auto-Sync & Recovery

Continuous status tracking. Automatic recovery for disconnected or behind browsers. No manual babysitting.

Dual Interaction Mode

Vision mode (coordinates) as primary, accessibility snapshots (ref-based) as fallback. Two layers of reliability.
Approval Checkpoints

Keep sensitive steps
under operator control.

Pause a workflow for review, preserve the current browser state, and continue only after an authorized operator confirms the next action.
browser_parallel_wait_for → Waiting for approved page state → Workflow paused for operator review → Approval recorded in the audit trail → Approved sessions resumed → Final state verified
Manual approval
Pause and resume
Audit trail
Session status
Step confirmation
Structured logs
Targeted retry
Error recovery
MCP Tools

30+ tools for complete browser control

Every tool runs in parallel across all connected browsers. Target specific profiles with browserIds or tags.
browser_listList all connected browsers with status, URL, and tags
browser_statusSync status of all browsers — detect BEHIND or FAILED states
browser_parallel_navigateNavigate all browsers to the same URL in parallel
browser_parallel_vision_analyze_groupedScreenshot + CLIP grouping + vision element detection
browser_parallel_click_normalized_boxClick element by normalized box coordinates from vision analysis
browser_parallel_snapshotAccessibility tree snapshots with element refs for interaction
browser_parallel_fillFill inputs with same or per-browser values
browser_parallel_typeType text with configurable timing across approved browser sessions
browser_parallel_run_codeExecute Playwright code with per-browser template variables
browser_parallel_wait_forWait for text, element, or timeout across all browsers
browser_run_recorded_flowReplay saved macros by ID across browser profiles

Start automating in minutes

Add the MCP server to your agent config and connect browser profiles your team is authorized to operate.
1
Create an account & get your token
Sign up at mcp.ornold.com, go to API Tokens tab, and create a new token.
Create Free Account
2
Install Node.js (if not installed)
macOS (Homebrew)brew install node
Windows / Linuxnodejs.org → LTS
3
Paste this prompt into your AI agent
Open your agent (Claude Code, Cursor, Codex, Windsurf, Cline, Claude Desktop) and paste the message below. The agent reads the public install guide on GitHub, asks which supported browser and interaction mode you use, then installs the integration.
Install Ornold MCP — AI browser automation for authorized workflows. Full install guide for AI agents: https://github.com/ornold-ai/ornold-mcp/blob/main/AGENTS.md Before installing, ask me: 1. Do I have an Ornold token (orn_sk_…)? If not, send me to https://mcp.ornold.com → Tokens → Create token. 2. Which supported browser do I use? (Linken Sphere / Dolphin Anty / Vision Browser / Wade X / another CDP browser) — this decides the connection flags. 3. Mode: "vision" (for dynamic interfaces) or "dom" (for structured pages). If I want both, set up two MCP servers so the tool list stays focused. 4. Is Node.js 18+ installed? Run "node -v"; if missing, point me to https://nodejs.org. Then install Ornold MCP for the agent you're running in, using the install method and flags from AGENTS.md. Install the skill (npx mcp-ornold-browser --install-skill) where supported. Verify with browser_status. Use it only with systems, accounts, and data I own or am authorized to manage.
4
Start automating
Once the agent confirms browser_status works, ask it to navigate, inspect pages, fill authorized forms, or record reusable QA and operations flows across your browser profiles.