Playwright MCP Cursor
Demonstrates using Playwright with the Model Context Protocol (MCP) to enable large language models to automate browser interactions, with an example of cursor-based pagination against the GitHub GraphQL API.
README
Playwright MCP Cursor
This repository demonstrates how to use Playwright with the Model Context Protocol (MCP). MCP is a standard that exposes browser automation capabilities as structured tool calls so that large‑language models can interact with websites and APIs. The included example shows how to perform cursor‑based pagination against the GitHub GraphQL API, but you can adapt the test to any site with pagination (for example, Amazon product listings).
Project structure
- package.json – defines the npm dependencies and test scripts.
- playwright.config.ts – Playwright configuration (baseURL, test directory, reporter, etc.).
- tsconfig.json – TypeScript configuration for the project.
- tests/mcp-cursor.spec.ts – automated test demonstrating how to page through API results using cursors.
Prerequisites
- Node.js (version 16 or higher).
- npm or yarn.
- A GitHub personal access token set as the environment variable
GITHUB_TOKEN(only required when running the GraphQL API test).
Installation
Clone this repository and install dependencies:
npm install
Running the tests
Execute the tests locally:
npx playwright test
Playwright will run in headless mode by default and produce an HTML report. To open the report after the run:
npx playwright show-report
Running with MCP
To expose this project to an MCP client, you'll need to start an MCP server. For instructions on installing and running the MCP server, refer to the official Playwright MCP documentation. Once the server is running, point your client to the configured endpoint to send tool calls and drive Playwright under the hood.
Customizing the pagination example
The test in tests/mcp-cursor.spec.ts fetches repositories from the GitHub GraphQL API and paginates over the results using the endCursor and hasNextPage properties. If you prefer to test pagination on a web page such as Amazon, you can modify the test to navigate a search results page, click the "Next" button and assert that the correct items are loaded. Playwright's rich locator and browser APIs make it straightforward to adapt the pattern to any paginated data source.
Continuous integration
A GitHub Actions workflow is included in .github/workflows/playwright.yml to run the tests automatically on each push or pull request. The workflow installs dependencies, downloads the necessary browsers, and executes npm test on Ubuntu. It also passes through the GITHUB_TOKEN secret so the GraphQL test can authenticate against the GitHub API.
Feel free to fork this repository and experiment with other targets and protocols to expand your test coverage.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.