--- title: "The Best MCP Servers for Browser Automation (2026)" description: "Browser MCP servers do three jobs: drive your Chrome step by step, run cloud browsers, or take a goal. How to pick yours, with our pick for each." canonical: "https://browser-use.com/posts/best-mcp-servers-for-browser-automation" last_updated: "2026-10-18" --- # The Best MCP Servers for Browser Automation (2026) **Author:** Gregor Zunic **Date:** 2026-10-17 > Browser MCP servers do three jobs: drive your Chrome step by step, run cloud browsers, or take a goal. How to pick yours, with our pick for each. --- Every browser MCP server does one of three jobs: it lets your coding agent click through pages itself, it gives your agent browsers on someone else's machines, or it takes a goal and runs a whole browser agent for you. Figure out which job you have before you compare servers, because the best server for one job is usually wrong for the other two. My picks: Browser Harness for step-by-step work in your own Chrome, the Browser Harness CLI on our cloud browsers for step-by-step work in the cloud (Kernel if your client only speaks MCP, Steel if a person has to step in for logins), and the Browser Use Cloud MCP server when you want to hand off the whole task and only read the answer. Disclosure: we make Browser Use and Browser Harness, so they come first. Competitor facts come from each project's own repo, docs and pricing page, checked October 18, 2026. ## The Three Kinds A browser MCP server gives Claude Code, Cursor or Codex browser tools. The servers split on two things: who decides each click, and where the browser runs. - **Your agent drives every step, on your machine.** Clicks, typing, page reads, screenshots. Your coding agent plans each action, and every page it reads lands in its context. Most control, most tokens. All free: Browser Harness, Playwright MCP, Chrome DevTools MCP, agent-browser and Browser MCP. - **Cloud browsers.** The browser runs on a vendor's machines: many at once, proxies and CAPTCHA handling, nothing on your laptop, and none of your local logins. You pay per browser-hour. Browser Use Cloud, Browserbase, Kernel, Steel and Hyperbrowser. Their tools come in different shapes: Kernel and Steel give your agent raw steps, Browserbase takes one step at a time in plain words, and Browser Use Cloud and Hyperbrowser take whole jobs. - **Give it a goal.** You send a task in plain words, a second agent with its own model does the clicking, and your coding agent only reads the result. The Browser Use Cloud MCP server works this way. The Browser Use open-source server has a full-agent tool next to its step tools, Hyperbrowser has hosted agents, and agent-browser has an opt-in chat tool. Browser Use Cloud and Hyperbrowser sit in two kinds at once: cloud browsers, and whole tasks. ## Four Questions Before You Pick - **Which browser?** Logged-in work on your own accounts needs your Chrome. Tests want a clean, isolated profile. Parallel or unattended work wants cloud browsers. - **Low-level tools or a whole agent?** Step tools give your agent full control and make it read every page. Task tools keep raw pages out of its context, but you trust the other agent's work. - **Context cost.** Every page snapshot your agent reads costs input tokens, and on long tasks that is most of the bill. Playwright's own [README](https://github.com/microsoft/playwright-mcp) says coding agents "might benefit from using the CLI+SKILLS instead", because CLI calls "avoid loading large tool schemas and verbose accessibility trees into the model context". That's the reason Browser Harness defaults to a CLI and a skill. - **Cost and license.** Local servers are free and open source, and your model tokens are the bill. Cloud servers add browser time, proxy traffic and sometimes a monthly plan. ## My Pick for Each Kind ### Your Agent Drives, on Your Machine: Browser Harness [Browser Harness](https://browser-use.com/browser-harness) is our open-source tool for letting a coding agent use your real Chrome, logged in as you. It talks to Chrome directly over the Chrome DevTools Protocol (CDP), with no Playwright and no extension. A background daemon holds one connection to your Chrome, and the tab it controls gets a horse emoji in its title. Its skill has the agent open its own tab first, so it doesn't take over the one you're looking at. There's no snapshot tool: the agent reads the page through JavaScript, screenshots or raw CDP calls like `Accessibility.getFullAXTree`, and clicks by coordinates, which go through iframes and shadow DOM. The default setup is a CLI plus a skill. You paste one [setup prompt](https://browser-use.com/browser-harness) into your agent and it installs everything, no config to edit. If your client only speaks MCP, browser-harness-mcp exposes the same helpers as [23 tools](https://github.com/browser-use/browser-harness/blob/main/docs/MCP.md), from `browser_click` to raw `browser_cdp`: ```bash claude mcp add browser-harness -- uvx --from 'browser-harness[mcp]' browser-harness-mcp ``` MIT and free in your own Chrome, no API key. The catches. The agent sees your whole logged-in Chrome, not a sandbox. On Chrome 144+ you tick remote debugging once in `chrome://inspect` and click Allow per connection (`browser-harness mac-approve` clicks it on macOS). One daemon controls one tab, so two agents acting at once can race. There's no documented clean-profile mode for the MCP server and no Firefox or WebKit. In our eval it was slower than Playwright MCP and Chrome DevTools MCP. Two free servers beat us at specific jobs: - **[Playwright MCP](https://github.com/microsoft/playwright-mcp)** for tests. `--isolated` starts every session clean, `--browser` runs Firefox and WebKit, and it reads pages as accessibility snapshots with element refs, so it needs no vision model. It was the fastest tool in our eval, with about twice our tokens. If your team already lives in Playwright, use it. - **[Chrome DevTools MCP](https://github.com/ChromeDevTools/chrome-devtools-mcp)** for debugging your own app. It's from the Chrome DevTools team and records performance traces, runs Lighthouse audits, inspects network requests and reads console messages with source-mapped stack traces. Browser Harness can reach that data through raw CDP, but this has purpose-built tools for it. It had the highest raw score in our eval (within noise) and used about three times our tokens. ```bash claude mcp add playwright npx @playwright/mcp@latest claude mcp add chrome-devtools --scope user npx chrome-devtools-mcp@latest ``` ### Cloud Browsers: Browser Harness on Our Cloud, or Kernel Over MCP Our own cloud MCP server runs on cloud browsers, but it takes whole tasks, not clicks (next section). For step-by-step work in the cloud I use the Browser Harness CLI on our cloud browsers, \$0.02 per browser-hour. Its MCP server only covers your local Chrome, so if your client only speaks MCP, I'd pick Kernel. **[Kernel](https://github.com/kernel/kernel-mcp-server)** runs every browser as Chromium in its own unikernel VM. `execute_playwright_code` runs Playwright code inside that VM, next to the browser, and `browser_repl` is a persistent Node.js runtime there with raw CDP; the README calls it "unrestricted VM code execution, not a sandbox." You pay per second of active runtime, \$0.06 per hour headless and \$0.48 headful, and a browser stops billing 5 seconds after the last activity. The gotcha: the default inactivity timeout is 60 seconds, so an agent that pauses longer loses the browser unless it sets `timeout_seconds`. MIT, hosted with OAuth sign-in: ```bash claude mcp add --transport http kernel https://mcp.onkernel.com/mcp ``` Then run `/mcp` once in Claude Code to sign in. **[Steel](https://github.com/steel-dev/steel-mcp-server)** reads the page as an accessibility tree with `@eN` refs and acts by ref. Its standout is `steel_session_handoff`: a person takes over for a login, CAPTCHA, payment or local file, then hands the browser back. Our server has a live URL you can watch, but no handoff. It's MIT and not on npm, so `npx github:` builds it on first run. | Server | Browser-hour | Good at | Catch | | --- | --- | --- | --- | | Browser Use Cloud | \$0.02 | Whole tasks, many at once | No click tools | | Kernel | \$0.06 headless, \$0.48 headful | Playwright code and a REPL in the browser's VM | 60-second default inactivity timeout | | Steel | \$0.10 Launch, \$0.08 Scale | Handing the browser to a person | Not on npm; Launch sessions cap at 15 minutes | | Browserbase | \$0.12 Developer, \$0.10 Startup, after included hours | Plain-word steps (act, observe, extract) | API key goes in the URL | | Hyperbrowser | \$0.10 | One-call scrape, crawl and extract | No npm release since April 2025 | If you already pay Browserbase, its server is the shortest path, and your agent keeps step control without reading raw pages. Plans, proxy rates, stealth and every tool for all five are in the [cloud browser round-up](https://browser-use.com/posts/best-cloud-browser-mcp-servers). ### Give It a Goal: Browser Use Cloud MCP The [Browser Use Cloud MCP server](https://docs.browser-use.com/cloud/guides/mcp-server) is hosted, so there's no local server to run. `run_session` takes a task in plain words and runs a full Browser Use agent on one of our cloud browsers, then returns right away. Your agent polls `get_session` for status, output, a cost breakdown and a live URL. Each poll returns a status, not a page, which is the whole point: your coding agent reads the task, a few checks and the answer. `output_schema` gets you JSON back, `profile_id` starts the task already logged in, and `keep_alive` plus `send_task` handle follow-ups in the same browser. You pay \$0.02 per browser-hour, model tokens at provider cost plus 20%, and residential proxy traffic at \$5/GB, with the US proxy on by default ([pricing](https://browser-use.com/pricing)). New projects can run 10 at once, more as you spend. ```bash claude mcp add -t http browser-use https://api.browser-use.com/v3/mcp -H "Authorization: Bearer YOUR_API_KEY" ``` It runs API V3, which our docs say is faster and cheaper than V4 but less accurate. It also wasn't in the eval. Every client config is on [/mcp](https://browser-use.com/mcp). For free and local, the [Browser Use open-source server](https://docs.browser-use.com/open-source/customize/integrations/mcp-server) launches a local Chrome with step tools, plus `retry_with_browser_use_agent`, which hands the task to a full browser-use agent when direct control fails. That agent runs on your own OpenAI API key. Models, cost and how to watch a run for every goal-taking server are in the [browser agent round-up](https://browser-use.com/posts/best-browser-agent-mcp-servers). ## What We Measured We ran four step-by-step tools on 100 of the 200 tasks in [BU Bench V2.1](https://github.com/browser-use/benchmark), one run per task, with the same agent (Codex with GPT-6 Luna), the same fresh Browser Use cloud browser and the same judge. Browser Harness ran as its CLI and skill, not the MCP server. Scores: Chrome DevTools MCP 61.0, Browser Harness 60.4, Playwright MCP 60.0, agent-browser 56.3. No tool won. Paired differences, Browser Harness minus each tool: Playwright MCP +0.4 points (95% interval -5.7 to +6.6), Chrome DevTools MCP -0.6 (-6.6 to +5.6), agent-browser +4.0 (-1.8 to +10.0). Every interval includes zero. Where they differed was tokens. Median input tokens per task: Browser Harness 2.1M, agent-browser 3.3M, Playwright MCP 4.4M, Chrome DevTools MCP 6.7M. So Browser Harness had the lowest median agent cost per task, \$0.042 against \$0.066 for Playwright MCP and \$0.097 for Chrome DevTools MCP. By median time Playwright MCP was fastest at 8.3 minutes, then Chrome DevTools MCP at 8.7, Browser Harness at 9.0 and agent-browser at 11.3. Limits: one run per task, half the benchmark, one agent and one model, and a fresh cloud browser every time, not your logged-in Chrome. The data file doesn't record whether agent-browser ran as its CLI or its MCP server. Versions and every per-task score are in the [data file](https://browser-use.com/benchmarks/coding-agent-browser-tools.json), and the full table with tool calls and solve rates is in the [step-by-step round-up](https://browser-use.com/posts/best-mcp-servers-to-control-a-browser). ## All Eleven Servers | Server | Kind | Browser | License | Cost | Best for | | --- | --- | --- | --- | --- | --- | | Browser Harness | Drives every step | Your Chrome; the CLI also drives our cloud browsers | MIT | Free; CLI cloud browsers \$0.02 per hour | Coding agents in your logged-in Chrome | | Browser Use Cloud MCP | Cloud, whole tasks | Browser Use cloud browsers | Hosted | \$0.02 per hour plus tokens and proxy | Handing off tasks, many at once | | Browser Use open-source MCP | Steps plus agent fallback | A local Chrome it launches | MIT | Free; your OpenAI key | A local agent on your own key | | Playwright MCP | Drives every step | Its own Chrome, Firefox, WebKit or Edge; your Chrome via extension | Apache-2.0 | Free | Tests, clean and cross-browser sessions | | Chrome DevTools MCP | Drives every step | Its own Chrome; your Chrome via --autoConnect | Apache-2.0 | Free | Performance, network and console debugging | | agent-browser | Drives every step; opt-in chat tool | Its own headless Chrome; your Chrome via flags | Apache-2.0 | Free | A single-binary CLI with safety controls | | Browser MCP | Drives every step | Your Chrome, one connected tab | Apache-2.0 | Free | A quick try in one tab | | Kernel MCP | Cloud, raw steps | Kernel cloud browsers | MIT | \$0.06-\$0.48 per hour | Playwright code on cloud browsers | | Steel MCP | Cloud, raw steps | Steel cloud, or self-hosted steel-browser | MIT | \$0.08-\$0.10 per hour | Logins that need a person | | Browserbase MCP | Cloud, plain-word steps | Browserbase cloud browsers | Hosted; npm package Apache-2.0 | \$0.10-\$0.12 per hour after included hours | Existing Browserbase customers | | Hyperbrowser MCP | Cloud, whole jobs | Hyperbrowser cloud browsers | MIT | \$0.10 per hour | Scraping and extraction | A shorter [browser MCP server comparison](https://browser-use.com/mcp) puts five of these side by side: where each runs, how it works, what it's best for and what it costs. ## The Deep Dives - [The step-by-step round-up](https://browser-use.com/posts/best-mcp-servers-to-control-a-browser) covers the five tools of the first kind (Browser Harness, Playwright MCP, Chrome DevTools MCP, agent-browser and Browser MCP): how each works under the hood, install, license, gotchas, where each beats us, and the full eval. - [The cloud browser round-up](https://browser-use.com/posts/best-cloud-browser-mcp-servers) covers Browser Use Cloud, Browserbase, Kernel, Steel and Hyperbrowser: prices, stealth, concurrency and tools. - [The browser agent round-up](https://browser-use.com/posts/best-browser-agent-mcp-servers) covers Browser Use Cloud, the Browser Use open-source server, Hyperbrowser and agent-browser's chat tool: models, cost and how to watch a run. Cloud prices are per browser-hour as listed by each vendor on October 18, 2026, before plan fees, included hours and proxy traffic. --- BROWSER USE - Browser Use Agents: give Browser Use a task and receive completed work. API V4 is current for new integrations. - Browser Infrastructure: connect your agent or automation to managed browsers through SDK, REST, or CDP. Starts at $0.02/browser-hour. - Developer tools: Open Source, Browser Harness, SDK, and MCP support the two products above. [Developer Index](https://browser-use.com/index.md) [Product Map](https://browser-use.com/llms.txt) [Full Product Context](https://browser-use.com/llms-full.txt) [Pricing](https://browser-use.com/pricing.md) [Cloud Docs](https://docs.browser-use.com/cloud/quickstart) [Open Source Docs](https://docs.browser-use.com/open-source/introduction)