AI tools for testing and QA

For testing with AI agents, the Playwright MCP server is the key piece: it gives the agent structured, accessibility-tree-based browser control to author and run end-to-end tests against real pages. Pair it with a coding agent that runs your test suite as its verification step, so it writes the test, runs it, and fixes failures in one loop.

Playwright MCP for browser & E2E; any coding agent to run the suite.

Curated by Joaquin FuentesLast updated: June 14, 2026

Recommended resources

Playwright MCP Server

Drive a real browser — navigate, click, assert — from chat.

Microsoft's Playwright MCP gives agents structured, accessibility-tree-based browser control. Ideal for end-to-end test authoring and verifying deployed pages without brittle pixel clicking.

Any toolFreeOfficialIntermediate

mcpbrowsertestinge2e

When to use & gotchas

When to use Reach for it when you want the agent to verify a deployed page for real — it reads the accessibility tree, so its checks are more robust than pixel clicks.

Gotcha It needs a publicly reachable URL. A sandboxed agent usually can't hit a local dev server, so point it at a deployed preview instead.

View server Repo

Frequently asked questions

Can an AI agent write end-to-end tests?

Yes — with the Playwright MCP server an agent can drive a real browser, read the accessibility tree, author robust E2E tests, and run them to confirm they pass.

Why accessibility-tree-based control?

It's far more robust than pixel or coordinate clicking — tests built on the accessibility tree survive layout and styling changes that would break brittle selectors.

← Back to all resources