browser-use MCP server
This browser-use MCP server is a note storage system that allows you to:
Store notes: Add new notes with a name, description, and content using the
add-notetoolAccess notes: Retrieve stored notes via a custom
note://URI schemeSummarize notes: Generate brief or detailed summaries of all stored notes using the
summarize-notesprompt with an optionalstyleparameterManage resources: Each note is stored with structured metadata (name, description, mimetype)
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., "@browser-use MCP serveradd a note about meeting tomorrow with content 'Team sync at 2 PM to discuss Q3 goals'"
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.
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
Related MCP server: Datetime MCP Server
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 syncBuild package distributions:
uv buildThis will create source and wheel distributions in the dist/ directory.
Publish to PyPI:
uv publishNote: You'll need to set PyPI credentials via environment variables or command flags:
Token:
--tokenorUV_PUBLISH_TOKENOr 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-useUpon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
Available Tools
1 tooladd-noteD
Add a new note
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| content | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Add a new note' implies a mutation operation but fails to specify permissions needed, whether the note is persistent, if there are rate limits, or what happens on success/failure. This leaves critical behavioral traits undocumented.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at three words, with no wasted language. It's front-loaded with the core action, though this brevity comes at the cost of clarity and completeness for a tool with parameters and no annotations.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 2 parameters with 0% schema coverage, no annotations, no output schema, and no sibling context, the description is severely incomplete. It doesn't explain what the tool returns, how parameters are used, or behavioral aspects, failing to provide adequate context for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description mentions no parameters, while the input schema has 2 required parameters (name, content) with 0% schema description coverage. This creates a complete gap in understanding what 'name' and 'content' represent, their formats, or constraints, making parameter usage ambiguous.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Add a new note' restates the tool name 'add-note' with minimal elaboration, making it tautological. It specifies the verb 'add' and resource 'note' but lacks any distinguishing details about scope, format, or context that would clarify what kind of note is being added or where it's stored.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool, such as prerequisites, alternatives, or specific scenarios. With no sibling tools mentioned, it doesn't differentiate from other note-related operations, leaving the agent without context for appropriate invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
With only one tool, there is no possibility of ambiguity or confusion between tools. The tool 'add-note' has a clear and distinct purpose that cannot be misselected against other tools.
Since there is only one tool, it inherently follows a consistent naming pattern. The tool name 'add-note' uses a verb_noun format, which is clear and predictable, and there are no other tools to cause inconsistency.
A single tool is too few for a server named 'browser-use', which suggests a broader scope related to browser interactions. This minimal set feels thin and incomplete for the implied domain, limiting functionality.
The tool set is severely incomplete for a browser-use server. With only an 'add-note' tool, there are obvious gaps in core browser operations like navigation, clicking, or form filling, making it inadequate for typical browser automation tasks.
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 Connectors
Google Keep-style notes app with an MCP server for AI agents to read/write notes.
An MCP server that used to create notes
Cross-session, cross-device memory for your agent: remember and recall notes. No key to start.
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceFacilitates note storage and summarization through custom URIs, allowing users to manage, summarize, and update notes with varying detail levels in a collaborative environment.
- FlicenseCqualityDmaintenanceThis server enables users to store, manage, and summarize notes using a custom URI scheme, with functionality to add new notes and generate summaries with varying levels of detail.3
- FlicenseBqualityDmaintenanceA server for managing and summarizing notes using a custom URI scheme, with tools to add notes and create styled summaries.418
- FlicenseNot gradedqualityDmaintenanceA simple note-taking MCP server that allows storing and summarizing notes with custom URI schemes and provides functionality to add notes and generate summaries with different detail levels.5
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/adamdude828/mcp-browser-use'
If you have feedback or need assistance with the MCP directory API, please join our Discord server