MODEL CONTEXT PROTOCOL

The MCP Server for
 AI Test Management

No context switching. Qase MCP Server meets you where you already work.
Terminal

npm install -g @qase/mcp-server
Start 14 Day Trial
No credit card required
Get a demo
ISO/IEC 27001
SOC2
GDPR
Enterprise SLA
INTEGRATIONS

Works with your tools

Claude Desktop
Native MCP Support
Cursor
AI-first IDE
Claude Code
CLI integration
OpenAI Codex
Codex CLI
OpenCode
Local & global config

AI writes tests. Nobody manages them. Until now.

THE PROBLEM
No traceability or coverage.
AI agents generate tests but don't manage them — no traceability, no coverage reporting, no team coordination.
No governance or compliance
Enterprises need audit trails, governance, and compliance. AI agents alone don't provide any of this.
No human oversight
AI-generated tests need human review and organizational visibility to be trusted at scale.
THE SOLUTION
Full traceability, built in
Every AI-generated test is stored in Qase with suites, runs, results, and coverage tracked via 83 API tools.
Enterprise governance by default
All operations flow through Qase's platform: role-based access, audit trails, milestones, and approval workflows.
Human review at every step
AI-created test cases are visible in Qase's UI — filter, search, and audit by author, status, or any field using QQL.
CAPABILITIES

Everything you need, nothing you don't

Item

Test Cases & Runs

Create, update, and execute test cases and runs from your AI assistant. 83 tools at your fingertips.

Item

Query Your TMS

Use Qase Query Language to filter test cases, defects, and results by any field — flaky status, automation type, author, severity, and more.

Item

Defect Tracking

Create, resolve, and manage defects without leaving your coding environment.

Item

Full API Coverage

Projects, suites, plans, milestones, environments, shared steps, custom fields — everything is accessible.

Item

Bulk Operations

Create multiple test cases or results in one go. Optimized for real-world workflows.

Item

Enterprise Ready

Custom domain support, type-safe TypeScript implementation, and comprehensive validation.

SETUP

Three minutes to connect

Add to your MCP client config, set your API token, and start talking to Qase from your AI assistant.
Check the documentation
1
Get your API token from app.qase.io
2
Add this to your MCP client configuration:
Claude Desktop
Cursor
Claude Code
Open AI Codex
Open Code
claude_desktop_config.json

{
  "mcpServers": {
    "qase": {
      "command": "npx",
      "args": ["-y", "@qase/mcp-server"],
      "env": {
        "QASE_API_TOKEN": "your_api_token_here"
      }
    }
  }
}
mcp.json

{
  "mcpServers": {
    "qase": {
      "command": "npx",
      "args": ["-y", "@qase/mcp-server"],
      "env": {
        "QASE_API_TOKEN": "your_api_token_here"
      }
    }
  }
}
.mcp.json

{
  "mcpServers": {
    "qase": {
      "command": "npx",
      "args": ["-y", "@qase/mcp-server"],
      "env": {
        "QASE_API_TOKEN": "your_api_token_here"
      }
    }
  }
}
.codex/config.json

{
  "mcpServers": {
    "qase": {
      "command": "npx",
      "args": ["-y", "@qase/mcp-server"],
      "env": {
        "QASE_API_TOKEN": "your_api_token_here"
      }
    }
  }
}
opencode.json

{
  "mcp": {
    "qase": {
      "type": "local",
      "command": ["npx", "-y", "@qase/mcp-server"],
      "environment": {
        "QASE_API_TOKEN": "your_api_token_here"
      }
    }
  }
}
3
Ask your AI: "List all my Qase projects"