agent-qa by vostride runs natural-language end-to-end tests against web, Android and iOS interfaces using Playwright or Appium. Tests, configuration, evidence and memidex knowledge are files in the user's project. Its CLI, dashboard and local MCP server support test authoring, execution, evidence review and feedback on verdicts. Node.js 24 or later is required. Version 0.2.5 CLI and MCP discovery were checked; real browser or device tests, model calls and self-improvement quality were not tested. This is a local test runner; vostride's public documentation MCP is a separate read-only service. Software use costs $0 for FSL-permitted purposes, while model inference and infrastructure cost extra. FSL-1.1-ALv2 restricts competing commercial use and grants an Apache 2.0 future license after two years. Documentation: https://vostride.com/docs/agent-qa/mcp ; source and license: https://github.com/vostride/agent-qa .
Best for agent capabilities
Useful in agent tasks
Overview
When to use agent-qa
agent-qa is listed for Browser, Code Execution workflows. agent-qa by vostride runs natural-language end-to-end tests against web, Android and iOS interfaces using Playwright or Appium. Tests, configuration, evidence and memidex knowledge are files in the user's project. Its CLI, dashboard and local MCP server support test authoring, execution, evidence review and feedback on verdicts. Node.js 24 or later is required. Version 0.2.5 CLI and MCP discovery were checked; real browser or device tests, model calls and self-improvement quality were not tested. This is a local test runner; vostride's public documentation MCP is a separate read-only service. Software use costs $0 for FSL-permitted purposes, while model inference and infrastructure cost extra. FSL-1.1-ALv2 restricts competing commercial use and grants an Apache 2.0 future license after two years. Documentation: https://vostride.com/docs/agent-qa/mcp ; source and license: https://github.com/vostride/agent-qa . Consider it when an agent needs this capability through a documented service boundary instead of custom infrastructure maintained inside the application.
In 4agent’s task model, the product maps to Browser automation, Code execution. That makes it a candidate for these tasks: Research the web, Build and deploy software.
Integration checklist
- Access: Confirm the none authentication flow, credential scope, rotation process, and whether calls can be attributed to a user or service identity.
- Client support: No SDK is recorded, so verify the HTTP API or another supported integration path.
- Automation: OpenAPI: not currently recorded; MCP: listed as available; CLI: listed as available. Confirm each requirement in the provider's current documentation.
- Operations: Test rate limits, timeouts, retry safety, error payloads, logs, data retention, and the current free-tier and paid pricing model with production-like volume.
Sources and verification
Use these primary sources to verify current behavior before making an implementation or purchasing decision. Product capabilities, limits, and prices can change after a 4agent listing is reviewed.