PluginBench
MCP Server
Active
MIT

Qase Test Management MCP Server

io.qase/mcp-server

Connect AI assistants to Qase test management — manage cases, runs, defects, and results via 40 task-oriented tools.

What is the Qase Test Management MCP server?

The Qase MCP Server is the official Model Context Protocol integration for Qase Test Management Platform, enabling AI assistants like Claude and Cursor to read and write test cases, runs, results, defects, suites, milestones, and more. It provides 40 task-oriented tools consolidated from 83 v1 tools, with support for Qase Query Language (QQL) searches, composite workflows, and direct REST API access.

This server bridges AI assistants to your Qase test management workspace, letting you bootstrap project context, create or update test cases, report CI results, triage defects, and search with QQL — all through standardized MCP tools. Use the hosted version (Enterprise plan, qase.io only) or run it yourself with your API token for full flexibility across any Qase instance.

How to install Qase Test Management

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • QASE_API_TOKEN
    required
    secret

    Qase API token from app.qase.io > Settings > API Tokens

  • QASE_API_DOMAIN

    Custom API domain for enterprise (default: api.qase.io)

  • QASE_API_PROTOCOL

    Scheme used to reach the API domain: http or https. Use http only for self-hosted deployments served without TLS (default: https)

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@qase/mcp-server"
      ],
      "env": {
        "QASE_API_TOKEN": "<YOUR_QASE_API_TOKEN>",
        "QASE_API_DOMAIN": "<YOUR_QASE_API_DOMAIN>",
        "QASE_API_PROTOCOL": "<YOUR_QASE_API_PROTOCOL>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • qase_project_context — Bootstrap full project structure in one call — suites, milestones, environments, users, custom fields
  • qase_case_upsert — Create or update test cases
  • qase_ci_report — Report CI results for multiple test cases in a single call
  • qase_triage_defect — Create a defect from a failed test result
  • qql_search — Search across cases, runs, results, defects, and plans using Qase Query Language
  • qase_discover_tools — Discover and activate secondary tools on demand
  • qase_api — Direct REST API access for any endpoint not covered by other tools

Use cases

  • Bootstrap project context to see all suites, milestones, environments, and custom fields in one call
  • Create or update test cases programmatically with title, description, priority, and custom fields
  • Report CI pipeline results directly to Qase, linking test outcomes to specific cases and runs
  • Triage failed tests by creating critical defects with linked test results and run context
  • Search test cases, results, and defects across your project using Qase Query Language (QQL) with advanced filters

Qase Test Management MCP server FAQ

What is the Qase MCP Server?

It's the official MCP integration for Qase Test Management, giving AI assistants like Claude and Cursor 40 tools to manage test cases, runs, results, defects, suites, and milestones without custom code.

Is it free?

The hosted version (https://mcp.qase.io/mcp) requires an Enterprise plan on qase.io. Running it yourself with your own API token works on any Qase plan and instance.

How do I connect it in Claude?

Open Settings → Connectors, find Qase Test Management, and click Connect. For Cursor, add the hosted URL to .cursor/mcp.json, or install @qase/mcp-server locally.

Do I need an API token?

Only if you run the server yourself. The hosted version uses OAuth login with your Qase account (Enterprise plan required).

What authentication is required?

Hosted: sign in with your Qase account (Enterprise plan, qase.io workspace). Self-run: provide QASE_API_TOKEN environment variable.

Can I use this on a Qase dedicated instance?

Yes — run the server yourself with your API token. The hosted version only works on qase.io (Enterprise plan).

README (reference)

Source of truth, from the repository.

Qase MCP Server

Official Model Context Protocol (MCP) server for Qase Test Management Platform — connect AI assistants to your test cases, runs, defects, and more.

npm version License: MIT MCP Registry

Table of Contents

Overview

The Qase MCP Server lets AI assistants (Claude, Cursor, Codex, and any other MCP client) read and write Qase test cases, runs, results, defects, suites, milestones, and more — through a standardized protocol, with no custom integration code.

Features:

  • 40 task-oriented tools (41 total, including qase_discover_tools) — consolidated from 83 v1 tools for lower token usage and better LLM accuracy
  • Composite tools — multi-step workflows in a single call: CI reporting, defect triage, regression run setup
  • QQL support — Qase Query Language for advanced searches across cases, runs, results, defects, and plans
  • Project context bootstrap — one call returns full project structure (suites, milestones, environments, users, custom fields)
  • Test case review — propose new cases or changes for review, assign reviewers, and track status (approving and merging remain UI-only)
  • Tool discovery — secondary tools stay hidden until needed, keeping the default tool list small
  • Hosted or self-run — connect to https://mcp.qase.io/mcp with just your Qase login, or run the server locally with your own API token
  • Tenant-safe caching & HTTP resilience — two-tier cache (in-memory + optional Redis), connection pooling, retry with backoff
  • Escape hatch — direct REST API access for any endpoint via qase_api

Use Cases

ScenarioExample promptTool
Bootstrap project context"Show me the structure of project DEMO — suites, milestones, environments"qase_project_context
Create or update a test case"Create a high-priority smoke test case in project DEMO titled 'Login with valid credentials'"qase_case_upsert
Report CI results"Report these CI results for project DEMO: case 1 passed, case 2 failed with 'timeout error'"qase_ci_report
Triage a failed test"Create a critical defect for the login timeout failure in run #42"qase_triage_defect
Search with QQL"Find all failed test results from the last 7 days in project DEMO"qql_search

See Tools and docs/tools.md for the full reference.

Quick Start

Use the hosted Qase MCP (recommended)

No install, no API token — connect to the Qase-hosted server and sign in with your Qase account.

Note: The hosted Qase MCP requires the Enterprise plan and a workspace on Qase's main cloud (qase.io). On another plan, or on a dedicated instance, run the server yourself with your own API token — that works everywhere.

  • Claude — open Settings → Connectors, find Qase Test Management, click Connect.
  • Cursor — add {"mcpServers": {"qase": {"url": "https://mcp.qase.io/mcp"}}} to .cursor/mcp.json.
  • Codex — add the URL https://mcp.qase.io/mcp in Settings → MCPs → Add server, or configure ~/.codex/config.toml for the CLI.
  • VS Code — add {"servers": {"qase": {"type": "http", "url": "https://mcp.qase.io/mcp"}}} to .vscode/mcp.json, or run MCP: Add Server.

Full per-client steps, other clients, and the active-workspace model: docs/connect.md.

Run it yourself

Install the package and provide your own API token:

npm install -g @qase/mcp-server
export QASE_API_TOKEN=your_api_token_here

Then point your MCP client's stdio config at the @qase/mcp-server binary. Full install options, client configs (Claude Desktop, Cursor, Claude Code, Codex, OpenCode), environment variables, and transports (stdio/SSE/streamable-HTTP): docs/self-run.md.

Building on top of this server

For integration authors only — if you use the server directly, nothing here applies to you.

If your product drives this server (a plugin, an agent, a wrapper CLI), it can identify itself so its usage is attributable in Qase analytics, independently of which AI host is connected:

QASE_MCP_INTEGRATION=quality-supervisor/1.4.0   # <name>/<version>, version optional

The name must be on the allowlist in src/utils/integration-marker.ts — add yours in a PR. Anything unlisted or malformed is ignored, and the API call still succeeds. HTTP transports also accept the marker per request (X-Qase-Integration header or ?integration=). Details: docs/self-run.md.

Upgrading from v1

v2 consolidated 83 v1 tools into 29 task-oriented tools (30 total, including a discovery tool), and has since grown to 36 (37 total). Tool names and response shapes have changed. See docs/migration.md for the complete tool mapping table, response format changes, and before/after examples.

Tools

41 tools across 6 groups (40 task-oriented tools plus qase_discover_tools for on-demand activation of secondary tools). 17 are listed from the start; the rest stay hidden until qase_discover_tools activates them:

GroupCountDescription
Read2Fetch any entity by type/ID, or bootstrap full project context in one call
QQL2Search across cases, runs, results, defects, and plans with Qase Query Language
Write32Create, update, and delete cases (single or up to 100 at once), runs, results, defects, suites, milestones, plans, shared steps, environments, and attachments; link cases and runs to Jira issues; propose and manage test case reviews
Composite3Multi-step workflows in one call: CI reporting, defect triage, regression run setup
Escape hatch1Direct REST API access for any endpoint not covered by the tools above
Meta1qase_discover_tools — find and activate secondary tools on demand

Full tool-by-tool reference with parameters and the discovery model: docs/tools.md.

Documentation

Contributing

Contributions are welcome! See CONTRIBUTING.md for development setup, testing, and linting guidelines.

License

MIT License — see LICENSE for details.

Support

Links

Related MCP servers

Qt 5 and Qt 6 framework and product docs: Qt Creator, MCUs, Squish, Coco and more.

Query BigQuery, Snowflake, Redshift & Azure Synapse with natural language

View repository →

Winning numbers for 30+ world lotteries, minutes after each draw. Free, no key, CC BY 4.0.

Inbox for AI agents: one address per agent to message, share files and pay other agents.

RARate Ranger logo

Watch a hotel's price after your user booked it, and email them when it drops enough to rebook.

0
View repository →

Normalized JSON for any domain across 1,200+ TLDs, reading WHOIS where no RDAP server exists.