Developer toolsPublic source

mcp-browser

Web browsing and scraping for AI agents — read pages as clean text, take screenshots, extract structured data, interact with forms, and get accessibility trees. 17 tools powered by headless Chrome via native CDP (Chrome…

Open the source Read the official guide ↗

What it gives an agent

A purpose-built capability behind one MCP connection.

The server owns its domain logic and publishes a tool contract an MCP client can discover. ADK-Rust can load that contract into an agent, normalize each schema for the chosen model provider, and keep the connection lifecycle outside the agent’s business logic.

Zero config — Chrome auto-downloads and launches on first run

Full rendering — JavaScript-heavy SPAs work out of the box

Dual mode — headless Chrome for complex pages, lightweight HTTP for simple ones

Structured extraction — CSS selectors, accessibility trees, metadata

Visual capture — screenshots and PDFs

Form interaction — click, type, wait, evaluate JS

Architecture

How mcp-browser fits into an agent system.

The model never needs the implementation details or credentials of the system behind the server. It sees reviewed tool definitions. The MCP client handles discovery and calls, while the server keeps ownership of validation, policy, and communication with its domain system.

ADK-Rust agent

Chooses a capability from the reviewed tool catalog.

→

MCP client

Discovers schemas, sends calls, and receives typed content.

→

mcp-browser

Validates the request and owns 17 documented tool contracts.

→

Domain system

Keeps the API, data, credentials, and business rules behind the server.

Connection: stdio · Server framework: ADK MCP SDK + rmcp

mcp-browser architecture diagram from its official repository

Tool catalog

What can an agent ask mcp-browser to do?

Each tool has a stable name, a human-readable purpose, and a JSON input contract discovered during MCP initialization. Risk classes come from the project’s registry manifest when one is available.

17 named tools

read_page

Fetch URL → clean readable text (strips HTML, scripts, styles)

see documentation

get_html

Full rendered HTML after JavaScript execution

see documentation

extract_links

All links with text and href (up to 100)

see documentation

extract_metadata

Title, description, OG tags, canonical URL

see documentation

query_selector

Extract text content of elements matching CSS selector

see documentation

get_accessibility_tree

Structured page representation (77% fewer tokens than HTML)

see documentation

extract_structured

Extract named fields using a selector map

see documentation

screenshot

Full-page screenshot (base64 PNG)

see documentation

screenshot_element

Screenshot a specific element by CSS selector

see documentation

save_pdf

Save page as PDF (base64)

see documentation

click

Click an element by CSS selector

see documentation

type_text

Type text into an input field

see documentation

Governance

Understand the effect of every tool.

A server connection inherits the authority of its credentials and deployment environment. The declarations below come from this project’s README and MCP registry manifest; your application still decides which tools an agent receives and where approval is required.

17 see documentation

Review the server documentation and deployment credentials before enabling it for an agent.

MCP surface

What the current documentation declares.

MCP can carry tools, resources, prompts, structured results, progress, cancellation, and long-running work. This record highlights the modern protocol features explicitly mentioned by this repository.

The current README concentrates on its tool surface. Check the source and release notes before relying on optional MCP capabilities beyond tool discovery and invocation.

ADK MCP SDKrmcp

Install and connect

Follow the project’s documented starting point.

Install the server in the environment that owns its credentials and domain access. Add it to your MCP host, verify the discovered tools, and narrow the toolset before giving it to a production agent.

Install

cargo install mcp-browser

MCP client configuration

{
  "mcpServers": {
    "browser": {
      "command": "mcp-browser"
    }
  }
}

Commands and configuration are extracted from the public README. Confirm prerequisites, environment variables, and release-specific options in the official documentation before deployment.

Official documentation

Continue with the project maintainers’ source of truth.

This page provides an approachable map of the server. The repository remains authoritative for exact schemas, prerequisites, configuration, examples, tests, releases, and security updates.

Overview ↗README.md CHANGELOG ↗CHANGELOG.md Api Reference ↗docs/api-reference.md Architecture ↗docs/assets/architecture.svg Issues and support ↗github.com issues

Keep exploring