MCP server for Playwright

MCP server for Playwright is an application that provides AI assistants with browser automation and web page interaction capabilities via the standard Model Context Protocol (MCP). The server uses structured accessibility snapshots of pages and does not require vision-capable models. It is deployed on a virtual machine in Yandex Cloud.

Key Features and Benefits

• Yandex AI Studio Integration. The MCP server integrates with AI Studio MCP Servers — connect it to your AI agents in just a few clicks.
• Browser Automation. Navigate pages, click elements, type text, fill forms, and perform other actions in Chromium through an AI assistant.
• Accessibility Page Snapshots. Work with a structured representation of the page without the need for image recognition.
• Headless Mode. The browser runs without a GUI for efficient operation on servers.
• Content Extraction. Retrieve text, links, forms, and other elements of web pages.
• Screenshots and PDF. Capture screenshots and generate PDF documents from web pages.
• Bearer Token Authorization. All requests to the MCP server are protected with a Bearer token stored in Yandex Lockbox.
• Standard MCP Protocol. Uses the open Model Context Protocol for AI model interaction.
• HTTP with SSE Transport. The MCP server is accessible on port 8000 (HTTP with SSE).
• Minimal Resources. The application runs on a virtual machine with minimal configuration (2 vCPU, 2 GB RAM).
• Docker Containerization. The server runs in Docker containers (MCP + nginx auth proxy).

1. Create a secret in Yandex Lockbox to store the Bearer token for authorization. The secret must contain a bearer_token key with an arbitrary token value.
2. Create a service account with the roles compute.editor, iam.serviceAccounts.admin, lockbox.payloadViewer, vpc.admin (the admin role includes all the specified roles).
3. In the management console select the Cloud Apps service.
4. In the left panel, select Application Store.
5. Select MCP Playwright and click the Use button.
6. Specify:
   • Application name.
   • (Optional) Application description.
   • The service account created earlier.
   • The cloud subnet where the virtual machine will be deployed.
   • Lockbox secret ID containing the Bearer token for authorization.
7. Click the Install button and wait for the application to install.
8. After installation, the MCP server will be available at http://<vm-ip>:8000.
9. Configure your AI client (Claude Desktop, Cursor, etc.) to connect to the MCP server, specifying the Authorization: Bearer <your-token> header.

Connecting the MCP server to Yandex AI Studio

1. In the management console open the AI Studio service and go to the MCP Hub section.
2. Click Create MCP server and choose the External MCP server type.
3. Specify the server name and the ID of the VPC network where the MCP server virtual machine is deployed. The network ID is available on the application page in the Application data section, VPC network ID field.
4. At the MCP server connection step, fill in the parameters with the values from the Application data section:
   • MCP server type — value from the MCP server type field.
   • MCP server URL — value from the MCP server URL (internal) field.
   • In the HTTP headers block, add an Authorization header with the value Bearer <bearer_token>, where <bearer_token> is the token from the Yandex Lockbox secret specified during application installation.
5. Click Connect. After a successful connection check, select the required tools and click Connect — the MCP server will be registered in AI Studio and available for use by AI agents.

• Automating routine browser actions via an AI assistant: filling forms, navigating sites, collecting data.
• Extracting information from web pages using accessibility snapshots without image recognition.
• End-to-end testing of web applications with scenarios controlled via natural language.
• Capturing screenshots and PDF snapshots of pages for reports and archiving.
• Building AI agents capable of interacting with modern web applications.

Yandex Cloud technical support is available 24/7. The types of requests you can submit and the appropriate response time depend on your pricing plan. You can switch to the paid support plan in the management console. You can learn more about the technical support terms here.