Resources
4 min read

Playwright MCP vs a Testing MCP Server: Which One Do You Need?

Playwright MCP drives a browser session. A testing MCP server maintains a suite. Here is how the two differ, and the setup commands for each client.

Wei-Wei Wu
CEO, Momentic
Sep 1, 2026

Playwright MCP and a testing MCP server connect an agent to an application, but they leave different artifacts behind.

The short answer

Playwright MCP gives an agent a browser for the session it is in. It can navigate, click, take snapshots, and generate Playwright code at the end. A testing MCP server gives an agent a test suite it can add to. It can author a test, run it, read the failure, and leave the test in your repository. If you want an agent to interact with a page today, use Playwright MCP. If you want the check to still run next month in CI, use a testing MCP server.

What each server actually exposes

Playwright MCP is Microsoft's open-source server. Its browser tools return a structured page snapshot on every call. The snapshot includes the rendered DOM, accessibility tree, and console.

Momentic's MCP server is local. You start it with npx momentic mcp. Its tools preview a candidate step against the live page, return a compressed screenshot and a short status, commit the step on success, run the saved test, and hand back the failure.

Comparison table

Playwright MCPMomentic MCP
What the agent producesPlaywright code, materialized locators and string literals at generation timeact, assert and extract steps that describe user intent, saved as YAML
Where the artifact livesyour repo, as a spec fileyour repo, as a YAML test file
Authoring loopinteract from memory, then generate code at the endpreview each step against the live page, commit it on success
Editing a test laterfull browser and session reset, the agent replays from memorysplice individual steps, the browser session persists across edits
Context the agent carriesa full page snapshot per tool call, accumulating across the sessiona screenshot and a short status per call, with locator resolution done server-side
Replaya changed selector or a changed string is a test failurea step replays from a multi-modal cache in milliseconds with no model call, and re-resolves in place when the page changes
Waitinghard-coded waitForTimeout in the generated specbuilt-in waits for navigation, load, screenshots, DOM mutations and same-origin requests
Running the suite in CIwhatever you build around playwright testnpx momentic run, with labels, sharding, JUnit output and a non-zero exit code on failure
Mobileweb onlythe same YAML and the same CLI for iOS and Android
Best forad hoc browser work and teams who want standard Playwright codea regression suite an agent maintains with you

Set it up

The server needs MOMENTIC_API_KEY in its environment. Follow the client-specific setup in the MCP server documentation .

Claude Code

Run this command from the project that should use the server. Verify the connection with claude mcp list, then use /mcp inside Claude Code.

claude mcp add --transport stdio momentic -- npx momentic mcp --config /absolute/path/to/momentic.config.yaml

Codex

Run this command to save the server configuration to ~/.codex/config.toml. Restart Codex before you run /mcp.

codex mcp add momentic -- npx momentic mcp --config /absolute/path/to/momentic.config.yaml

Cursor

Open the command palette, select View: Open MCP Settings, click Add a new Custom MCP server, paste this entry, and restart Cursor.

{
  "mcpServers": {
    "momentic": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "momentic",
        "mcp",
        "--config",
        "/absolute/path/to/momentic.config.yaml"
      ],
      "env": { "MOMENTIC_API_KEY": "your-api-key" }
    }
  }
}

Restart the client, start a new chat, and ask the agent which MCP tools it has. You should see momentic_* tools such as momentic_get_artifacts.

The momentic-test, momentic-spec, and momentic-maintain skills install alongside the server. See the MCP server documentation .

The documentation also covers VS Code Copilot, OpenCode, Devin, and other clients.

What the agent can do once it is connected

Your agent authors a test step by step and captures a screenshot after each step. It runs the test it just wrote, then reads back the failing step, the DOM, and the console. After a UI change it updates the test in your repository, so the change arrives in a pull request.

Playwright MCP is the right call if

  • You already have a Playwright suite and want authoring help inside it.
  • You want the artifact to be Playwright code your team already reviews.
  • You need a browser in an agent session and have no suite yet.

Momentic's MCP server is the right call if

  • You want tests to survive the next UI change without a code review.
  • You want one suite across web, iOS, and Android.
  • You want a merge gate rather than a session transcript.

How to try both

Read the deep technical comparison for the detail behind the table. Then follow the MCP setup guide to connect a client. Use the CLI when you are ready to run the saved suite in CI. Talk to us if you want help choosing a starting point.

Playwright MCP and testing MCP servers, answered.

What is the difference between Playwright MCP and a hosted testing MCP server?

Playwright MCP gives an agent a browser for its current session and can generate Playwright code at the end. A testing MCP server gives an agent a suite it can author, run, and leave in your repository.

How do I connect a testing MCP server to Claude Code or Cursor?

Use claude mcp add with the Momentic command for Claude Code. For Cursor, open the command palette, select View: Open MCP Settings, click Add a new Custom MCP server, and paste the stdio entry. The server needs MOMENTIC_API_KEY in its environment.

Which MCP server lets an agent run a whole test suite and read the results?

Momentic's MCP server lets an agent author a test, run the saved test, and read the failing step, DOM, and console back. The saved YAML test stays in your repository.

Do I need Playwright MCP if I use Momentic's MCP server?

No. You can run both, because they do different jobs. Playwright MCP gives an agent a browser for its session, while Momentic's MCP server gives it a test suite that can run in CI.

Where do the tests an agent writes actually live?

The tests live in your repository as YAML files under your version control and code review. Momentic's MCP server leaves the saved test there, and Playwright MCP leaves Playwright code in your repository.

Still have additional questions?

Contact us

Close the feedback loop.