aicoolies logo

Browserbase MCP Server

Cloud browser automation via MCP for scalable testing

Share
freemiumOpen Source
Visit Website →

Browserbase MCP Server gives MCP clients a hosted or self-hostable browser through Browserbase and Stagehand. It exposes tools for starting sessions, navigating, acting, observing, extracting, and taking screenshots, with a hosted Streamable HTTP endpoint for easiest setup and local STDIO/Docker options for teams that want to run the Apache-licensed server themselves.

We have a review for this tool

A detailed review by the aicoolies team — click to read

Browserbase MCP Server is the official Browserbase and Stagehand bridge for giving MCP clients a controllable browser. The current docs describe a hosted Streamable HTTP endpoint served by Browserbase infrastructure plus a self-hostable STDIO server with the same six core tools: start, end, navigate, act, observe, extract, and screenshot. That distinction matters for buyers comparing it with local Playwright MCP options: the value proposition is managed browser sessions, natural-language Stagehand actions, session lifecycle control, recordings/logging, and Browserbase infrastructure rather than a purely local browser driver.

The public README and docs now emphasize both setup paths. The hosted endpoint at mcp.browserbase.com/mcp is recommended for the easiest start and includes Browserbase-hosted capacity, while the open-source Apache-2.0 repository can be installed with npm, run directly, or built as a Docker image. Teams still need Browserbase API credentials, and self-hosted configurations may also need a model API key depending on the Stagehand/model settings. Claims about CAPTCHA, proxy support, geolocation, or reliability should be framed as platform capabilities and plan-dependent infrastructure features, not guaranteed bypass outcomes.

Pricing is tied to Browserbase platform usage. The current pricing page lists Free at $0/month with 3 concurrent browsers, 1 browser hour, 1,000 Search calls, 1,000 Fetch calls, 15-minute sessions, 7-day retention, and $5 in model tokens; Developer at $20/month with 25 concurrent browsers and 100 browser hours; Startup at $99/month with 100 concurrent browsers and 500 browser hours; and custom Scale plans with 250+ concurrent browsers and usage-based allowances. The GitHub repo remains active with about 3.4K stars, so the base page should present it as an open-source server attached to a commercial managed-browser platform.

Pricing

Browserbase pricing lists Free $0 with 3 concurrent browsers and 1 browser hour, Developer $20/mo, Startup $99/mo, and custom Scale plans; usage overages apply for browser hours, Search, Fetch/Extract, and proxies.

Platforms

Hosted Streamable HTTP MCP, STDIO, Docker, Browserbase cloud sessions, Stagehand, Claude/Cursor-compatible MCP clients

Categories

Tags

Use Cases

Alternatives

Playwright logo

Playwright

Reliable end-to-end testing

Cross-browser E2E testing framework by Microsoft supporting Chromium, Firefox, and WebKit with one API. Features auto-waiting, tracing with timeline/screenshots/DOM snapshots, codegen for recording tests, and parallel execution. Component testing for React, Vue, Svelte. Built-in API testing, network mocking, and mobile emulation. Known for reliability and speed vs Selenium/Cypress. 70K+ GitHub stars, rapidly becoming the E2E standard.

open-sourceOpen Source
Browser Use logo

Browser Use

AI agent framework for web browser automation

Browser Use is an open-source AI agent framework with 99K+ GitHub stars enabling LLMs to control web browsers via natural language. Y Combinator-backed, it lets agents navigate sites, fill forms, extract data, and complete multi-step tasks autonomously. Built on Playwright with vision-based element detection, multi-tab management, cookie persistence, and self-correcting actions. Supports OpenAI, Anthropic, and local models with a simple Python API for building custom browser agents.

open-sourceOpen Source

BrowserMCP

Automate local Chrome browser via MCP

BrowserMCP is an MCP server that enables AI agents to automate a local Chrome browser — navigating pages, clicking elements, filling forms, extracting content, and taking screenshots. It gives coding agents the ability to interact with web applications the way a human would, directly from Claude Desktop, Cursor, or any MCP client.

open-sourceOpen Source
Tabstack logo

Tabstack

Mozilla-backed browser infrastructure for AI agents

Tabstack is Mozilla's browser infrastructure service for AI agents, providing clean markdown extraction, structured JSON data, and automated browser actions through a fast API. With two-tier fetch escalation that achieves sub-600ms latency for static pages, robots.txt compliance, and ephemeral data handling, it offers an ethical alternative to aggressive web scraping tools — complete with an MCP server for Claude and Cursor integration.

freemiumOpen Source

Related Tools

Hermes Agent logo

Hermes Agent

Top Pick

Open-source AI agent framework with persistent memory, reusable skills, tools, and messaging gateways

Hermes Agent is an open-source AI agent framework with persistent memory, reusable skills, 40+ tools, cron jobs, and messaging gateways.

open-sourceOpen Source

Safari MCP Server

Apple's Safari-native MCP server for web debugging agents

Safari MCP Server is Apple's safaridriver-based MCP server in Safari Technology Preview, giving compatible coding agents local access to Safari page content, console logs, network requests, screenshots, JavaScript evaluation, interactions, viewport controls, and accessibility/performance checks.

freeTelemetry

Headroom

Context compression for LLM apps and coding agents

Headroom is an Apache-2.0 context compression layer for LLM apps and coding agents. It compresses tool output, logs, files, RAG chunks, and agent history through a local library, proxy, wrapper, or MCP server, with retrieval hooks for bringing originals back when needed. Treat its savings numbers as Headroom-reported benchmarks, not independent aicoolies measurements.

open-sourceOpen SourceTelemetry

Codebase Memory MCP

Codebase knowledge graph MCP server for AI coding agents

Codebase Memory MCP is an MIT-licensed MCP server that turns a repository into a persistent code knowledge graph for AI coding agents. It gives Claude Code, Cursor, Codex-style agents, and other MCP clients structural queries for functions, classes, call chains, routes, and architecture, helping them explore large projects without repeatedly rereading files or relying only on broad search.

open-sourceOpen SourceTelemetry
BeeAI Framework logo

BeeAI Framework

Python and TypeScript framework for production multi-agent systems

BeeAI Framework is an Apache-2.0 toolkit for building production-ready AI agents and multi-agent systems in Python and TypeScript. Its docs cover agents, tools, RAG, memory, workflows, backend providers, serving, and A2A/MCP integration surfaces, making it a vendor-neutral option for teams comparing LangGraph, CrewAI, Mastra, and related agent runtimes.

open-sourceOpen SourceTelemetry

Supabase MCP

MCP server for connecting AI assistants to Supabase projects

Supabase MCP is Supabase's Apache-2.0 server for connecting AI assistants to Supabase projects. It can expose database, configuration, and project-management workflows to MCP clients such as Cursor, Claude, and Windsurf, while the official docs emphasize permission and security review before production use, SQL changes, or high-privilege database access.

open-sourceOpen SourceTelemetry

Comparisons