Browser Use
A simple note storage system with tools to add and summarize notes using a custom URI scheme.
browser-use MCP server
A MCP server project
Components
Resources
The server implements a simple note storage system with:
- Custom note:// URI scheme for accessing individual notes
- Each note resource has a name, description and text/plain mimetype
Prompts
The server provides a single prompt:
- summarize-notes: Creates summaries of all stored notes
- Optional "style" argument to control detail level (brief/detailed)
- Generates prompt combining all current notes with style preference
Tools
The server implements one tool:
- add-note: Adds a new note to the server
- Takes "name" and "content" as required string arguments
- Updates server state and notifies clients of resource changes
Configuration
[TODO: Add configuration details specific to your implementation]
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development
Building and Publishing
To prepare the package for distribution:
- Sync dependencies and update lockfile:
uv sync
- Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
- Publish to PyPI:
uv publish
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token:
--tokenorUV_PUBLISH_TOKEN - Or username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory /Users/adamholsinger/mcp-servers/browser-use run browser-use
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
Related Servers
memory-mcp-1file
🏠 🍎 🪟 🐧 - A self-contained Memory server with single-binary architecture (embedded DB & models, no dependencies). Provides persistent semantic and graph-based memory for AI agents.
MCP Orchestro
Trello for Claude Code: AI-powered task management with 60 MCP tools, visual Kanban board, and intelligent orchestration for product teams and developers
itemit-mcp
An MCP server for asset tracking that connects to the itemit asset management API.
Confluence
Provides secure access to Atlassian Confluence content and spaces using its REST API.
Agentify
A multi-client AI agent monitoring and control system with automatic task completion detection.
TRIGGERcmd
Runs commands on your computers remotely.
OneNote
Access your entire OneNote knowledge base through AI using the Microsoft Graph API.
Ableton Live MCP
Control Ableton Live using OSC (Open Sound Control) commands.
Claude Desktop
Integrates Amoga Studio with Claude Desktop for enhanced productivity and communication.
WxO Agent MCP
Simple MCP (Model Context Protocol) server that invokes a single Watson Orchestrate agent remotely. The agent is defined once via environment variables or MCP config. Use this when you want a lightweight MCP that only chats with one agent—no tool management, no agent listing, no flows. Just invoke_agent(message) and get_agent().