Queay MCP Server
Queay 提供一个远程 MCP 服务器,使编码代理(如 Claude Code、Claude Desktop、GitHub Copilot、Kilo Code 等)能够列出你的测试脚本、触发运行并查看状态,而无需离开编辑器。所有执行仍运行在 Queay 自身的基础设施上;代理仅触发并读取结果,与 CI/CD 相同。
托管 MCP 服务器
npx add-mcp 'https://queay.com/api/mcp'可安装到 Claude Code、Codex、Cursor 等客户端
文档
Run Software Tests from Your Coding Agent with MCP
Queay exposes a remote MCP server so a coding agent — Claude Code, Claude Desktop, GitHub Copilot, Kilo Code, and others — can list your test scripts, trigger a run, and check its status without leaving your editor. All execution still runs on Queay's own infrastructure; the agent only triggers and reads back results, the same as CI/CD.
A coding agent using Queay MCP end to end
A real Claude Code session: list_ui_test_scripts to find a script, run_ui_test_script to start it, then get_run_status to poll it through to completion — all without leaving the editor.

Server URL & Authentication
https://queay.com/api/mcp
Authentication reuses the same access tokens as CI/CD and Scheduled Runs — no separate MCP credential. Sign up, create an Access Token from your dashboard, then pass it as an Authorization: Bearer header in your client's config.
Available Tools
list_ui_test_scripts
List all UI (browser) test scripts in the organization, with id, name, description and tags.
list_api_test_scripts
List all API test scripts in the organization, with id, name, description and test count.
run_ui_test_script
Start a run of a UI test script. Returns a runId immediately (the run happens asynchronously) — poll it with get_run_status.
run_api_test_script
Start a run of an API test script. Returns a runId immediately (the run happens asynchronously) — poll it with get_run_status.
get_run_status
Get the status and results of a run started by run_ui_test_script or run_api_test_script, including a videoUrl/screenshotUrl for completed UI runs.
get_technical_analysis
Get the Automation Analytics overview for the organization: pass/fail rate, flaky tests, execution trends and AI insights.
Full input schema for every tool, versioned, at /api/mcp/schema.
Client Setup
Claude Code
claude mcp add --transport http queay https://queay.com/api/mcp --header "Authorization: Bearer YOUR_ACCESS_TOKEN"
Claude Desktop
{
"mcpServers": {
"queay": {
"url": "https://queay.com/api/mcp",
"headers": { "Authorization": "Bearer YOUR_ACCESS_TOKEN" }
}
}
}
GitHub Copilot (VS Code mcp.json)
{
"servers": {
"queay": {
"type": "http",
"url": "https://queay.com/api/mcp",
"headers": { "Authorization": "Bearer YOUR_ACCESS_TOKEN" }
}
}
}
Replace YOUR_ACCESS_TOKEN with a token from your Access Tokens page after signing up. Exact config file names/locations vary by client version.
Let your coding agent run tests for you
Start your free trial, create an access token, and connect your agent in minutes.