AnalysisNov 3, 20265 min read8 sources

Browser automation for agents: Browserbase, Stagehand, Playwright MCP

In one minute

Browser automation for AI agents splits into two layers: where the browser runs and how the model drives it. Browserbase is a hosted platform that gives agents fleets of headless cloud browsers plus Fetch, Search, Identity (stealth, CAPTCHA solving, proxies, authentication) and session observability

, billed per browser hour. Stagehand is Browserbase's open-source MIT SDK that mixes natural-language act/extract/observe/agent calls with deterministic Playwright-style code and can run on a local browser or on Browserbase. Playwright MCP is Microsoft's MCP server that lets any MCP client (Claude Code, Codex, Cursor, VS Code and others) control a local browser through accessibility snapshots rather than screenshots. It is for engineers building agents that log in, fill forms or extract data from sites without APIs.

*Field guide compiled 2026-10-23 from the official documentation, pricing pages and changelogs linked below; every line links to the page that states it.*

What it does

  • Act. Execute browser actions from a natural-language instruction; Stagehand says act() self-heals when a site redesigns its form. How: await stagehand.act("click the login button") source
  • Extract. Pull schema-validated structured data from a page. How: await stagehand.extract("extract the price", z.number()) source
  • Observe. Discover available actions on a page and return real selectors, so code can fill credentials without passing them to the model. How: await stagehand.observe("find submit buttons") source
  • Agent. Automate whole multi-step workflows autonomously, including computer-use (CUA) mode with a chosen model. How: stagehand.agent({ mode: "cua", model: "..." }).execute("apply for this job") source
  • Caching Actions. Two caching strategies, Browserbase Cache (managed, server-side) and Local Cache, to reduce LLM cost and speed up repeated automations. How: See Stagehand Best Practices Caching Actions source
  • Playwright MCP. MCP server that drives a browser via Playwright's accessibility tree, so no vision model is needed and tool application is deterministic. How: Add {"command": "npx", "args": "@playwright/mcp@latest"} to the MCP client config; e.g. claude mcp add playwright npx @playwright/mcp@latest or codex mcp add playwright npx "@playwright/mcp@latest" source
  • --caps. Opt-in extra Playwright MCP capabilities such as vision (coordinate-based), pdf, devtools, network, storage and testing tools. How: npx @playwright/mcp@latest --caps=vision,pdf (env PLAYWRIGHTMCPCAPS) source
  • --extension. Connect Playwright MCP to a running Edge/Chrome instance and reuse your logged-in tabs and browser state. How: Install the Playwright Extension, then run with --extension source

Modes

  • Persistent profile. Playwright MCP default: logged-in state is stored in a per-workspace profile under ms-playwright/mcp-{channel}-{workspace-hash}; override with --user-data-dir. source
  • Isolated. Playwright MCP --isolated: each session uses a throwaway profile; seed login state with --storage-state. source
  • Browser Extension. Playwright MCP attaches to your existing Chrome/Edge tabs and sessions. source
  • Playwright CLI. Microsoft recommends CLI + SKILLs over MCP for coding agents because it avoids loading large tool schemas and accessibility trees into context. source
  • cua. Stagehand agent mode that runs a computer-use model to drive the browser. source
  • localBrowser. Stagehand on a local browser with userDataDir so cookies persist between runs, instead of a hosted Browserbase session. source

Pricing and limits

  • Browserbase Free Plan: $0/mo. 3 concurrent browsers, 1 browser hour, 3 Agent runs, 1,000 Search and 1,000 Fetch calls, 15 minutes/session, $5 in model tokens, no CAPTCHA solving, 7-day retention source
  • Browserbase Developer Plan: $20/mo. 25 concurrent browsers, 100 browser hours then $0.12/browser hr, 15 Agent runs, 1 GB proxies then $12/GB, auto CAPTCHA solving, basic stealth source
  • Browserbase Startup Plan: $99/mo. 100 concurrent browsers, 500 browser hours then $0.10/browser hr, 50 Agent runs, 10,000 Fetch calls then $0.5/1k, 5 GB proxies then $10/GB source
  • Steel Launch: $0 per month + usage. $30 one-time credits, 10 concurrent sessions, sessions up to 15 minutes; browser hours $0.10, CAPTCHA solves $3/1k, proxy $10/GB source
  • Steel Scale: $250 per month + usage. $100 credits/month, 100 concurrent sessions, sessions up to 1 hour; browser hours $0.08, CAPTCHA solves $1/1k, proxy $6/GB source
  • Browser Use cloud browsers: $0.02 / hour. Pay as you go, plus $5 / GB residential proxy; browser agents billed at model + 20% source

Recent changes

  • 2026-08-28: Stagehand server v3.7.6 and related Stagehand releases published on GitHub. source

Alternatives

  • Steel. Hosted browser infra priced as plan plus usage: $0.10 browser hour on Launch and $0.08 on Scale ($250/month), with CAPTCHA solves billed per 1k; stealth browser only on Enterprise. source
  • Browser Use. Pay-as-you-go cloud browsers at $0.02/hour with no subscription, and hosted browser agents billed at model cost + 20%. source
  • Playwright CLI. Same Playwright engine exposed as CLI commands and skills, more token-efficient than the MCP server for coding agents. source

Traps

  • A Playwright MCP persistent profile can be used by only one browser instance at a time, so concurrent MCP clients in the same workspace conflict; use --isolated or a distinct --user-data-dir per client. source
  • In Playwright MCP isolated mode, closing the browser discards all storage state for the session, so logins are lost unless you pass --storage-state. source
  • Browserbase Free caps sessions at 15 minutes, includes 1 browser hour and has no CAPTCHA solving; CAPTCHA solving starts on Developer. source
  • MCP browser tools load large tool schemas and verbose accessibility trees into the model context, which Microsoft flags as a token cost for coding agents. source

Evidence / sources

  1. 1docs.stagehand.dev/v3/first-steps/introduction
  2. 2docs.stagehand.dev/v3/best-practices/caching
  3. 3github.com/microsoft/playwright-mcp
  4. 4browserbase.com/pricing
  5. 5steel.dev/pricing
  6. 6browser-use.com/pricing
  7. 7github.com/browserbase/stagehand
  8. 8github.com/browserbase/stagehand/releases
All Analysis

Next reads

Read next

Open the graph
  1. 01topicToolsExplore the tools topic hub.
  2. 02topicDeveloper ToolsExplore the developer_tools topic hub.
  3. 03archiveAnalysisOpen the latest authorial analysis.
  4. 04sourcesSourcesSee the original sources this archive cites.
Who read this page?Machine requests, hidden until opened

Loading the privacy-safe route aggregate...

Open the JSON contract