Server data from the Official MCP Registry
Official MCP server for Qase — manage test cases, runs, suites, defects via AI tools.
Official MCP server for Qase — manage test cases, runs, suites, defects via AI tools.
Valid MCP server (2 strong, 2 medium validity signals). 6 known CVEs in dependencies Package registry verified. Imported from the Official MCP Registry.
5 files analyzed · 7 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Set these up before or after installing:
Environment variable: QASE_API_TOKEN
Environment variable: QASE_API_DOMAIN
Add this to your MCP configuration file:
{
"mcpServers": {
"io-qase-mcp-server": {
"env": {
"QASE_API_TOKEN": "your-qase-api-token-here",
"QASE_API_DOMAIN": "your-qase-api-domain-here"
},
"args": [
"-y",
"@qase/mcp-server"
],
"command": "npx"
}
}
}From the project's GitHub README.
Official Model Context Protocol (MCP) server for Qase Test Management Platform.
The Qase MCP Server provides seamless integration between AI assistants (Claude, Cursor, etc.) and the Qase Test Management Platform. It enables AI assistants to interact with your test cases, test runs, defects, and other Qase entities through a standardized protocol.
The server provides tools for managing:
npm install -g @qase/mcp-server
# Clone the repository
git clone https://github.com/qase-tms/qase-mcp-server.git
cd qase-mcp-server
# Install dependencies
npm install
# Build the server
npm run build
Create a .env file or set environment variables:
# Required: Your Qase API token
QASE_API_TOKEN=your_api_token_here
# Optional: Custom API domain for enterprise customers
QASE_API_DOMAIN=api.qase.io
Get your API token from: https://app.qase.io/user/api/token
If you're using Qase Enterprise with a custom domain:
QASE_API_DOMAIN=api.yourcompany.qase.io
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"qase": {
"command": "npx",
"args": ["-y", "@qase/mcp-server"],
"env": {
"QASE_API_TOKEN": "your_api_token_here"
}
}
}
}
Or, if installed from source:
{
"mcpServers": {
"qase": {
"command": "node",
"args": ["/absolute/path/to/qase-mcp-server/build/index.js"],
"env": {
"QASE_API_TOKEN": "your_api_token_here"
}
}
}
}
{
"mcpServers": {
"qase": {
"command": "npx",
"args": ["-y", "@qase/mcp-server"],
"env": {
"QASE_API_TOKEN": "your_api_token_here"
}
}
}
}
You can add the Qase MCP server to Claude Code using the CLI command:
claude mcp add qase -- npx -y @qase/mcp-server
Set the required environment variable:
export QASE_API_TOKEN=your_api_token_here
Alternatively, add a .mcp.json file to your project root for automatic project-scoped configuration:
{
"mcpServers": {
"qase": {
"command": "npx",
"args": ["-y", "@qase/mcp-server"],
"env": {
"QASE_API_TOKEN": "your_api_token_here"
}
}
}
}
You can also use the --scope flag to choose where the configuration is stored:
# Project-scoped (saved in .mcp.json)
claude mcp add --scope project qase -- npx -y @qase/mcp-server
# User-scoped (available in all projects)
claude mcp add --scope user qase -- npx -y @qase/mcp-server
Add a .codex/config.json file to your project root:
{
"mcpServers": {
"qase": {
"command": "npx",
"args": ["-y", "@qase/mcp-server"],
"env": {
"QASE_API_TOKEN": "your_api_token_here"
}
}
}
}
Set the required environment variable before running Codex:
export QASE_API_TOKEN=your_api_token_here
Add an opencode.json file to your project root (or ~/.config/opencode/opencode.json for global configuration):
{
"mcp": {
"qase": {
"type": "local",
"command": ["npx", "-y", "@qase/mcp-server"],
"environment": {
"QASE_API_TOKEN": "your_api_token_here"
}
}
}
}
Note: OpenCode uses a different format from other MCP clients — the command and args are combined into a single
commandarray, env vars go underenvironment, and servers are nested undermcp(notmcpServers).
Can you list all my Qase projects?
Create a test case in project DEMO titled "Login with valid credentials" with steps for entering username, password, and clicking login
Find all failed test results from the last 7 days in project DEMO
Search for all flaky test cases in project DEMO that are not automated
The server will execute:
entity = "case" and project = "DEMO" and isFlaky = true and automation = "Not automated"
Show me all open blocker defects in project DEMO
Find all test cases created by john@example.com in the last month
Create a test run in project DEMO called "Sprint 24 Regression" including all test cases from the "Authentication" suite, then add a passed result for case ID 123
list_projects - Get all projectsget_project - Get project detailscreate_project - Create new projectdelete_project - Delete projectgrant_project_access - Grant user/group accessrevoke_project_access - Revoke accesslist_cases - List all test casesget_case - Get test case detailscreate_case - Create new test caseupdate_case - Update test casedelete_case - Delete test casebulk_create_cases - Create multiple casesattach_external_issue - Link external issue (Jira, etc.)detach_external_issue - Unlink external issuecreate_case, bulk_create_cases, and update_case automatically normalize friendly labels to whatever numeric IDs your workspace currently configures for the built-in system fields (priority, severity, type, behavior, status, layer). The server fetches /v1/system_field and caches the available options so you can keep using the titles or slugs you see in Qase while still satisfying the API’s numeric requirements.
The normalization does not touch automation/is_flaky, so pass those values as the API expects (strings or booleans).
The server keeps any existing label in place when it does not match a known enum so invalid values still bubble up as errors from Qase.
list_runs - List test runsget_run - Get run detailscreate_run - Create new rundelete_run - Delete runcomplete_run - Mark run as completeget_run_public_link - Get public linkdelete_run_public_link - Remove public linklist_results - List test resultsget_result - Get result detailscreate_result - Create test resultcreate_results_bulk - Create multiple resultsupdate_result - Update resultdelete_result - Delete resultlist_plans - List test plansget_plan - Get plan detailscreate_plan - Create test planupdate_plan - Update test plandelete_plan - Delete test planlist_suites - List suitesget_suite - Get suite detailscreate_suite - Create suiteupdate_suite - Update suitedelete_suite - Delete suitelist_defects - List defectsget_defect - Get defect detailscreate_defect - Create defectupdate_defect - Update defectdelete_defect - Delete defectresolve_defect - Mark as resolvedupdate_defect_status - Update statuslist_milestones - List milestonesget_milestone - Get milestone detailscreate_milestone - Create milestoneupdate_milestone - Update milestonedelete_milestone - Delete milestonelist_environments - List environmentsget_environment - Get environment detailscreate_environment - Create environmentupdate_environment - Update environmentdelete_environment - Delete environmentlist_shared_steps - List shared stepsget_shared_step - Get shared step detailscreate_shared_step - Create shared stepupdate_shared_step - Update shared stepdelete_shared_step - Delete shared steplist_shared_parameters - List parametersget_shared_parameter - Get parameter detailscreate_shared_parameter - Create parameterupdate_shared_parameter - Update parameterdelete_shared_parameter - Delete parameterqql_search - Execute QQL queryqql_help - Get QQL syntax helpTotal: 83 tools available
npm run build
# Run all tests
npm test
# Run with coverage
npm run test:coverage
# Watch mode
npm run test:watch
# Check for issues
npm run lint
# Auto-fix issues
npm run lint -- --fix
Use the MCP Inspector for interactive debugging:
npm run inspector
Set your API token when prompted, then interact with tools in the inspector UI.
The server supports multiple transport types for different use cases:
Used by MCP clients like Claude Desktop and Cursor:
npm start
# or
npm run start:stdio
Server-Sent Events for web-based clients:
npm run start:sse
# Server runs on http://localhost:3000/sse
# Health check: http://localhost:3000/health
Full HTTP-based transport with session management:
npm run start:http
# Server runs on http://localhost:3000/mcp
# Health check: http://localhost:3000/health
# Custom port and host
node build/index.js --transport streamable-http --port 8080 --host 0.0.0.0
# Available options:
# --transport: stdio | sse | streamable-http (default: stdio)
# --port: Port number (default: 3000)
# --host: Host address (default: 0.0.0.0)
Error: Authentication failed: Please check your QASE_API_TOKEN
Solution:
Error: Network error or ECONNREFUSED
Solution:
Error: unable to get local issuer certificate
This error typically occurs in corporate environments with:
Solution: Add the NODE_EXTRA_CA_CERTS environment variable pointing to your CA certificate file:
{
"mcpServers": {
"qase": {
"command": "npx",
"args": ["-y", "@qase/mcp-server"],
"env": {
"QASE_API_TOKEN": "your_api_token_here",
"NODE_EXTRA_CA_CERTS": "/path/to/your/certificate.pem"
}
}
}
}
To find your certificate:
/etc/ssl/certs/ or /etc/pki/tls/certs/Error: Invalid domain or connection errors with custom domain
Solution:
QASE_API_DOMAIN is set to just the domain (e.g., api.company.qase.io)https:// or /v1 in the domainError: MCP client shows "no tools, prompts or resources" or 0 tools available
Solution:
QASE_API_TOKEN is set in the env sectionnpm run buildError: Unknown tool: tool_name
Solution:
npm update -g @qase/mcp-serverContributions are welcome! Please see CONTRIBUTING.md for details.
npm testnpm run lintMIT License - see LICENSE file for details
Made with ❤️ by Qase
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.