Notte
Leverage Notte Web AI agents & cloud browser sessions for scalable browser automation & scraping workflows
⚡️ we outperform other web agents in speed, costs and reliability 👉🏼 read more on open-operator-evals
Notte MCP Server
Notte MCP Server
MCP server for all Notte tools in the agentic ecosystem.
Manage your sessions. Run agents. Take control: observe, scrape, act, authenticate.
Available Tools
Session Management
| Tool | Description |
|---|---|
notte_start_session | Start a new cloud browser session |
notte_list_sessions | List all active browser sessions |
notte_stop_session | Stop the current session |
Page Interaction & Scraping
| Tool | Description |
|---|---|
notte_observe | Observe elements and available actions on the current page |
notte_screenshot | Take a screenshot of the current page |
notte_scrape | Extract structured data from the current page |
notte_step | Execute an action on the current page |
Agent Operations
| Tool | Description |
|---|---|
notte_operator | Run a Notte agent to complete a task on any website |
Getting Started
- Install the required dependencies:
pip install notte-mcp
- Set up your environment variables:
export NOTTE_API_KEY="your-api-key"
- Start the MCP server:
python -m notte_mcp.server
note: you can also start the dev server locally using
uv run mcp dev packages/notte-mcp/src/notte_mcp/server.py --with-editable .
To use the MCP in cursor or claude computer use, you can use the following json:
check out the
$HOME/Library/Application Support/Claude/claude_desktop_config.jsonfile to see the installed MCP servers. note you might need to install the mcp-remote package usingnpx mcp-remote
{
"notte-mcp": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8001/sse"
],
"env": {
"NOTTE_API_KEY": "<your-notte-api-key>"
}
}
}
Claude Desktop examples:
> Can you look for the price of airforce 1 on the nike website (men's section) ? Please show me the browser visualizer so that I can track the progress live
> Can ou check out if I have any notte session active at the moment ?
Cursor examples:
Servidores relacionados
Bright Data
patrocinadorDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Scraper.is MCP
A powerful web scraping tool for AI assistants, powered by the Scraper.is API.
Open Crawler MCP Server
A web crawler and content extractor that supports multiple output formats like text, markdown, and JSON.
AgentQL
Enable AI agents to get structured data from unstructured web with AgentQL.
Markdown Downloader
Download webpages as markdown files using the r.jina.ai service, with configurable directories and persistent settings.
Open Crawler MCP Server
A web crawler and text extractor with robots.txt compliance, rate limiting, and page size protection.
Parallel Task MCP
Perform Deep Research and Batch Tasks
Fetch
Web content fetching and conversion for efficient LLM usage
MCP YouTube Transcript Server
Retrieves transcripts from YouTube videos for content analysis and processing.
YouTube Translate MCP
Access YouTube video transcripts and translations using the YouTube Translate API.
Playwright MCP
Browser automation using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots.