Notte MCP Server

MCP server for all Notte tools in the agentic ecosystem.

Manage your sessions. Run agents. Take control: observe, scrape, act, authenticate.

[The Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) provides a standardized protocol for connecting LLM applications with external tools and data sources. It enables seamless integration between language models and the context they need, whether you're developing an AI-powered IDE, building a chat interface, or designing custom AI workflows.

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.json file to see the installed MCP servers. note you might need to install the mcp-remote package using npx 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:

Metadata

Release files for notte-mcp 1.8.28

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for notte-mcp 1.8.28
File	Size	Uploaded	Provenance
notte_mcp-1.8.28.tar.gz	7.2 kB	Jul 13, 2026	Without provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for notte-mcp 1.8.28
File	Interpreter	ABI	Platform	Reset
notte_mcp-1.8.28-py3-none-any.whl 6.1 kB Jul 13, 2026 Without provenance	Python 3	none	any	Details

Total release size: 13.3 kB

Release files / notte_mcp-1.8.28.tar.gz

Download URL	notte_mcp-1.8.28.tar.gz
Size	7.2 kB
Tags	Source
SHA-256 checksum How to use checksums	`e40baa861246a583d1aa07e1905f47647254c9beffacf36e841147db10cce9ea`
BLAKE2b-256 checksum How to use checksums	`354a26dc642864348d4c407a76b761e2265cb3d84c824a7a41f3452988938715`
Upload date	Jul 13, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.11.14`

Release files / notte_mcp-1.8.28-py3-none-any.whl

Download URL	notte_mcp-1.8.28-py3-none-any.whl
Size	6.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`543363e1502e1b23dba9a99a713f8ccc39fc0c05aa539aff437507ade9364ce0`
BLAKE2b-256 checksum How to use checksums	`e263f4e5a223fd20e981e397c8c30f934633031d828792a9f37203d47b10c022`
Upload date	Jul 13, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.11.14`

Security for notte-mcp 1.8.28

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.