Agentic WeeklyGet the weekly
Microsoftv0.0.83Tested (smoke test)

Playwright MCP: what’s new in v0.0.83 and our verdict

Microsoft's MCP server that lets agents drive a browser with Playwright.

Official site

Release Ruler for Playwright MCP: marked at its Tested release date on the timeline of every AI model we track.

At a glance

Evidence
Tested (smoke test)
Released
Sep 28, 2026
Last verified
Oct 25, 2026
Pricing
Official page, dated
Best for
MCP servers

Evidence and ranking

Evidence behind this verdict

  1. Sources read1 cited source, latest fetched Oct 25, 2026. (done)
  2. Facts re-checkedLast verified Oct 25, 2026. (done)
  3. Run by usSmoke test on Oct 25, 2026 (scope below). (done)

Passed Test log result: Passed. Read the log

Where we rank it (editorial)

Listed here but not yet ranked. Ranks are editorial picks, not benchmark scores.

Pricing: Open-source server; the service it connects to may have its own costs. (checked 2026-10-25)

Our verdict

Microsoft's MCP server that lets agents drive a browser with Playwright.

Good for

  • Agents that need to test or navigate web pages

Skip if

  • You need DevTools-level performance traces (see Chrome DevTools MCP)

Tested. Tested 2026-10-25 (America/Chicago). Playwright MCP 0.0.83 exposed 25 tools and navigated a headless Chrome to a local page in 40.5 ms median (cold start 383 ms). Test environment: Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key. No language model was involved in this test, so it says nothing about any model, vendor-hosted or local. Not tested: Remote (HTTP) transport, authentication and concurrent clients: only local stdio with one client was measured; Large payloads: calls used tiny inputs, so these latencies are protocol and process overhead, not throughput; Anything about answer quality: no model was involved in the latency numbers; These are single smoke-test runs; it is not a benchmark. The machine was shared with other jobs; Clicking, typing, screenshots and snapshot-based element selection: only navigation was timed. These are smoke tests, not a benchmark. Full log: /tests/playwright-mcp.

Full test log with exact commands, versions and raw output: Playwright MCP Playwright 1.64.0-alpha-1790635538000: our test log.

Evidence
Tested (smoke test, 2026-10-25, no language model involved). A smoke test is not a benchmark.
What we ran
Playwright MCP 0.0.83 exposed 25 tools and navigated a headless Chrome to a local page in 40.5 ms median (cold start 383 ms).
Model used
None; no language model was involved
Environment
Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key
Not tested
Remote (HTTP) transport, authentication and concurrent clients: only local stdio with one client was measured; Large payloads: calls used tiny inputs, so these latencies are protocol and process overhead, not throughput; Anything about answer quality: no model was involved in the latency numbers; These are single smoke-test runs; it is not a benchmark. The machine was shared with other jobs; Clicking, typing, screenshots and snapshot-based element selection: only navigation was timed.
Date
(America/Chicago)

Best for

Key facts

Playwright MCP is Microsoft's MCP server for browser automation. It is Apache-2.0 licensed and v0.0.83 was released Sep 28, 2026.

  • License: Apache-2.0 (per GitHub)
  • Platforms: Node.js
  • Pricing model: Free and open source
  • Free tier: Free
  • Paid plans: None listed
  • GitHub: microsoft/playwright-mcp: 38,633 stars on 2026-10-25, last push 2026-10-22
  • Latest release we saw: v0.0.83, 2026-09-28
  • How to start: Add the server to your MCP client following the repository README.
  • v0.0.83 (2026-09-28): the newest release listed on the official page or repository when we read it on 2026-10-25.

How to set it up: Get started with Playwright MCP

These steps come from the vendor's own pages as read on 2026-10-25. We ran Playwright MCP on 2026-10-25; the test log lists what was and was not covered.

  1. Get access

    Add the server to your MCP client following the repository README.

  2. Check the limits and costs first

    Free. Open-source server; the service it connects to may have its own costs.

Pros and cons

Pros

  • Apache-2.0
  • Backed by the Playwright team

Cons

  • Version is still 0.0.x
  • Our test was one small task on a local 3B model; it does not show behaviour with hosted models or larger jobs

Alternatives and comparisons

  • Chrome DevTools MCP: Chrome DevTools for coding agents.
  • Browser Use: Open-source library that lets AI agents drive a browser, with a pay-as-you-go cloud browser starting at $0.02 an hour.
  • GitHub MCP Server: GitHub's official MCP server for repos, issues and pull requests.
  • Figma MCP server: Figma's own MCP server that gives coding agents access to design files.

FAQ

What is Playwright MCP?

Playwright MCP is Microsoft's MCP server for browser automation. It is Apache-2.0 licensed and v0.0.83 was released Sep 28, 2026.

Is Playwright MCP free?

Free. Open-source server; the service it connects to may have its own costs. Checked 2026-10-25; prices change, so confirm on the vendor's page.

What license is Playwright MCP under?

Its license: Apache-2.0 (per GitHub). Read from the project's own pages on 2026-10-25.

Sources

Last verified · Agentic Weekly

Guides for Playwright MCP

How to cite this page

Agentic Weekly, "Playwright MCP v0.0.83: what's new, verdict & setup", last updated 2026-10-25, https://theagenticweekly.com/tools/playwright-mcp

Keep the Reported or Tested label when you quote a verdict. Plain-text version: https://theagenticweekly.com/tools/playwright-mcp.md. More for AI assistants: /ai, /tools.json, /llms.txt.