Qa Use
@desplega-ai
About Qa Use
An MCP (Model Context Protocol) server that provides comprehensive browser automation and QA testing capabilities. This server integrates with desplega.ai to offer automated testing, session monitoring, batch test execution, and intelligent test guidance using AAA (Arrange-Act-As
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"desplega-qa": {
"command": "npx",
"args": [
"-y",
"@desplega.ai/qa-use-mcp@latest"
],
"env": {
"QA_USE_API_KEY": "your-desplega-ai-api-key"
}
}
}
}Tools
13Ensure API key is set, validate authentication, and install Playwright browsers. Does not start browsers (lazy initialization on session start).
Register a new user and get API key
Search and list all sessions (automated tests and development sessions) with pagination and filtering
Start an automated E2E test session for QA flows and automated testing. Returns sessionId (data.agent_id) for monitoring. URL is optional - uses app config base_url if not provided.
Start an interactive development session for debugging and exploration. Session will not auto-pilot and allows manual browser interaction.
Monitor a session status. Keep calling until status is "closed". Will alert if session needs user input, is idle, or pending.
Interact with a session - respond to questions, pause, or close the session
Search for automated tests by ID or query. If testId provided, returns detailed info for that test. Otherwise searches with optional query/pagination.
Execute multiple automated tests simultaneously. Uses the global browser WebSocket URL from init_qa_server.
Search automated test runs with optional filtering by test ID or run ID
Update application configuration settings including base URL, login credentials, and viewport type
Get the current application configuration details including base URL, login settings, and viewport
Reset and cleanup all active browser sessions. This will kill all browsers and tunnels. Use this when you hit the maximum session limit or need to free up resources.
Overview
What is Qa Use?
Qa Use is an MCP (Model Context Protocol) server that provides browser automation and QA testing capabilities. It integrates with desplega.ai to offer automated testing, session monitoring, batch test execution, and test guidance using AAA (Arrange-Act-Assert) framework templates.
How to use Qa Use?
Run with npx @desplega.ai/qa-use-mcp for stdio transport, or add --http --port 3000 for HTTP/SSE mode. Configure the server in your MCP client settings, setting the QA_USE_API_KEY environment variable with a desplega.ai API key. First-time setup requires either running init_qa_server with interactive=true or providing the API key.
Key features of Qa Use
- Launch and control Playwright browser instances (headless/headed)
- Create public tunnels for browser WebSocket endpoints
- Create, monitor, and control multiple QA testing sessions
- Real‑time progress notifications with MCP timeout protection
- Run multiple automated tests simultaneously with dependency management
- Search and list automated tests with pagination and filtering
- View test execution history with performance metrics and flakiness scores
- Pre‑built AAA framework templates for common test scenarios
Use cases of Qa Use
- Automate browser testing for web applications
- Run batch test suites with dependency ordering
- Discover and analyze test run history and flakiness
- Use intelligent templates to structure login, form, and e‑commerce tests
- Remotely monitor and interact with live test sessions
FAQ from Qa Use
What dependencies and runtime requirements does Qa Use have?
Qa Use requires Node.js to run via npx, a desplega.ai API key (obtainable through the register_user tool or at desplega.ai), and an MCP client that supports stdio or StreamableHTTP transport.
How do I authenticate with Qa Use?
For stdio mode, set the QA_USE_API_KEY environment variable. For HTTP mode, include a Bearer token with your API key in the Authorization header on each request.
What are the session limits and timeouts?
Up to 10 concurrent browser sessions are supported. Sessions have a default 30‑minute TTL, automatically refreshed on interaction. Each MCP tool call has a 25‑second maximum timeout.
What transport modes does Qa Use support?
Qa Use supports stdio (default for local MCP clients) and HTTP/SSE (StreamableHTTP, for web apps and remote access). The HTTP mode implements the MCP Streamable HTTP specification.
Where are browser sessions and test data managed?
Browser instances and tunnels are launched locally by the server. Test sessions and run data are managed through the desplega.ai API, and sessions are automatically cleaned up after expiry.
Frequently asked questions
What dependencies and runtime requirements does Qa Use have?
Qa Use requires Node.js to run via npx, a desplega.ai API key (obtainable through the `register_user` tool or at desplega.ai), and an MCP client that supports stdio or StreamableHTTP transport.
How do I authenticate with Qa Use?
For stdio mode, set the `QA_USE_API_KEY` environment variable. For HTTP mode, include a Bearer token with your API key in the `Authorization` header on each request.
What are the session limits and timeouts?
Up to 10 concurrent browser sessions are supported. Sessions have a default 30‑minute TTL, automatically refreshed on interaction. Each MCP tool call has a 25‑second maximum timeout.
What transport modes does Qa Use support?
Qa Use supports stdio (default for local MCP clients) and HTTP/SSE (StreamableHTTP, for web apps and remote access). The HTTP mode implements the MCP Streamable HTTP specification.
Where are browser sessions and test data managed?
Browser instances and tunnels are launched locally by the server. Test sessions and run data are managed through the desplega.ai API, and sessions are automatically cleaned up after expiry.
Basic information
More Developer Tools MCP servers
Repo Test Architect
RepoAssayLocal-first, read-only MCP server for evidence-backed repository test architecture audits and test planning.
OrangePro
Aamir SiddiquiOrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
Routebase
RoutebaseRoutebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.
Agent Conductor
icohangar-opsAgent conductor — AGENTS.md contract parser, SKILL.md registry, CHP decision engine over MCP
Skilder.ai
skilder.aiRun skills and MCP tools like production software: versioned, composed into roles, distributed to every agent from one governed library.
Comments