An AI QA engineer that executes natural language user journeys on web, Android, and iOS platforms while maintaining a memory of procedures.
Also known as vostride/agent-qa, @vostride/agent-qa-mcp
- Stars
- 857
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 14, 2026
- License
- —
What is agent-qa MCP?
agent-qa is an AI QA engineer that executes natural language user journeys on web, Android, and iOS platforms while maintaining a memory of procedures.
Summary generated from the project's README
About agent-qa MCP server
Automating software testing across web, Android, and iOS platforms is what agent-qa enables for developers and QA engineers. By describing user journeys in plain English, users can trigger automated tests that execute complex workflows on multiple operating systems. The system functions through a command line interface, a dedicated dashboard, or by connecting to a coding agent via MCP.
This tool distinguishes itself through a memory system called memidex, which stores facts and working procedures as reviewable files directly in your repository. It features a self-improvement mechanism that validates lessons from previous runs, retires outdated knowledge, and uses human feedback to correct errors. This approach allows the agent to maintain a continuous understanding of application behavior over time. To get started, you need Node.js 24+ and can initialize the environment using the npm package.
What you can do with it
- 1Execute cross-platform user journeysAsk an AI client to test a specific user flow on web, Android, or iOS using natural language.
- 2Maintain persistent testing knowledgeStore and review testing procedures and facts within your own repository using memidex.
- 3Debug failed test assertionsIdentify exactly where a test failed by reviewing screenshots and failed steps side by side.
- 4Refine agent accuracy through feedbackImprove the testing agent by providing feedback to correct mistakes and validate new lessons.
Written from the project's README. Every use case is checked against a quote from it.
How to install agent-qa MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall agent-qa MCP in Claude Code
$ claude mcp add agent-qa -- npx -y @vostride/agent-qa-mcpInstall agent-qa MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agent-qa": {
"command": "npx",
"args": [
"-y",
"@vostride/agent-qa-mcp"
]
}
}
}Install agent-qa MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agent-qa": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@vostride/agent-qa-mcp"
]
}
}
}Install agent-qa MCP in VS Code CLI
$ code --add-mcp '{"name":"agent-qa","type":"stdio","command":"npx","args":["-y","@vostride/agent-qa-mcp"]}'Install agent-qa MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"agent-qa": {
"command": "npx",
"args": [
"-y",
"@vostride/agent-qa-mcp"
]
}
}
}Install agent-qa MCP in Codex
$ codex mcp add agent-qa -- npx -y @vostride/agent-qa-mcpInstall agent-qa MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agent-qa] command = "npx" args = ["-y", "@vostride/agent-qa-mcp"]
Install agent-qa MCP in Gemini CLI
$ gemini mcp add -s user agent-qa npx -- -y @vostride/agent-qa-mcpInstall agent-qa MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agent-qa": {
"command": "npx",
"args": [
"-y",
"@vostride/agent-qa-mcp"
]
}
}
}Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachablePass
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubYour AI QA engineer, with memory. Describe a user journey in plain language. agent-qa tests it on web, Android or iOS and keeps the evidence. Use the CLI, the dashboard, or your coding agent through MCP and skills.
- memidex: remembers facts and working procedures as reviewable files in your repository.
- Self-improvement: validates lessons from runs, retires stale knowledge, and uses your feedback to correct mistakes.
| Benchmark | Rank | Published result |
|---|---|---|
| AndroidWorld | #1 | 100% pass@1 (116/116 tasks) |
| AppControlBench | #1 | 99.6% completion (114.5/115 points) |
Read the full benchmark reports, with run evidence and methodology, on our blog. Both used gpt-6-sol with memory and self-improvement off; AppControlBench gives half credit for partial completion.
See it in action
Inspect a failure. The demo catches a cart showing $29 instead of $53, with the failed step and its screenshot side by side.
See what memory contributed. Inspect the knowledge supplied to a run and trace it back to the steps that used it.
Run from your terminal. Real output from the demo suite: checkout passes; the deliberate cart-total bug fails.
Get started
Requires Node.js 24+.
npm install -D agent-qa
npx agent-qa init
Follow the quickstart to connect a model and run the demo, or set up with your coding agent.
[!NOTE] Early stage. Expect bugs. Report an issue when something breaks.
License
agent-qa MCP questions
How do I add agent-qa MCP to Claude Code?
Run claude mcp add agent-qa -- npx -y @vostride/agent-qa-mcp in your terminal. Add --scope user to make it available in every project.
How do I add agent-qa MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What platforms can agent-qa test?
The agent can test user journeys on web, Android, or iOS platforms.
How does the agent handle knowledge and memory?
It uses memidex to remember facts and working procedures as reviewable files within your repository.
What are the system requirements to get started?
You need Node.js version 24 or higher installed.