smartbear/smartbear-mcp

A Model Context Protocol (MCP) server which provides AI assistants with seamless access to SmartBear’s suite of testing and monitoring tools, including BearQ, BugSnag, Reflect, Swagger, PactFlow, Pact Broker, QMetry, QTM4J, Zephyr and Collaborator.

What is MCP?

The Model Context Protocol (MCP) is an open standard that enables AI assistants to securely connect to external data sources and tools. This server exposes SmartBear’s APIs through natural language interfaces, allowing you to query your testing data, analyze performance metrics, and manage test automation directly from your AI workflow.

Supported Tools

See individual guides for suggested prompts and supported tools and resources:

• BearQ - AI-powered QA test management and execution capabilities
• BugSnag - Comprehensive error monitoring and debugging capabilities
• Reflect - Test management and execution capabilities
• Swagger
  • Portal - Portal and product management capabilities
  • Studio - API and Domain management capabilities, including AI-powered API generation from prompts and automatic standardization
  • Contract Testing (PactFlow) - Contract testing capabilities
  • Functional Testing - API test discovery capabilities
• QMetry - QMetry Test Management capabilities
• Zephyr - Zephyr Test Management capabilities
• Collaborator - Review and Remote System Configuration management capabilities
• QTM4J - QTM4J Test Management for Jira capabilities

Remote MCP Servers

For BugSnag, Swagger, and Zephyr, SmartBear hosts Remote MCP Servers that you can connect to directly from your MCP client via a URL — no installation, Node.js, or API tokens required. Authentication is handled through an OAuth browser flow.

See the Remote MCP Servers guide for per-client setup instructions. You can connect to multiple remote servers at the same time.

Need BearQ, Reflect, QMetry, QTM4J, PactFlow, Collaborator, or Functional Testing? These products are only available via the local npm package below, which bundles all products into a single MCP server.

Prerequisites

• Node.js 22+ and npm
• Access to SmartBear products (BugSnag, Reflect, Swagger, QMetry, QTM4J or Zephyr)
• Valid API tokens for the products you want to integrate

Local MCP Server Installation (npm)

For all products — or if you prefer running the server locally — the MCP server is distributed as an npm package @smartbear/mcp, making it easy to integrate into your development workflow.

The server is started with the API key or auth token that you use with your SmartBear product(s). They are optional and can be removed from your configuration if you aren’t using the product. For BugSnag, if you provide a project API key it will narrow down all searches to a single project in your BugSnag dashboard. Leave this field blank if you wish to interact across multiple projects at a time.

VS Code with Copilot

For the quickest setup, use the “MCP: Add server…” command in the Command Palette to add the @smartbear/mcp npm package.

Claude Desktop

Add the following configuration to your claude_desktop_config.json to launch the MCP server via npx:

{
  "mcpServers": {
    "smartbear": {
      "command": "npx",
      "args": [
        "-y",
        "@smartbear/mcp@latest"
      ],
      "env": {
        "BEARQ_API_TOKEN": "your_bearq_api_token",
        "BUGSNAG_AUTH_TOKEN": "your_personal_auth_token",
        "BUGSNAG_PROJECT_API_KEY": "your_project_api_key",
        "REFLECT_API_TOKEN": "your_reflect_token",
        "SWAGGER_API_KEY": "your_swagger_key",
        "SWAGGER_PORTAL_BASE_PATH": "https://api.portal.swaggerhub.com/v1",
        "SWAGGER_REGISTRY_BASE_PATH": "https://api.swaggerhub.com",
        "SWAGGER_UI_BASE_PATH": "https://app.swaggerhub.com",
        "PACT_BROKER_BASE_URL": "your_pactflow_or_pactbroker_base_url",
        "PACT_BROKER_TOKEN": "your_pactflow_token",
        "PACT_BROKER_USERNAME": "your_pact_broker_username",
        "PACT_BROKER_PASSWORD": "your_pact_broker_password",
        "QMETRY_API_KEY": "your_qmetry_api_key",
        "QMETRY_BASE_URL": "https://testmanagement.qmetry.com",
        "ZEPHYR_API_TOKEN": "your_zephyr_api_token",
        "ZEPHYR_BASE_URL": "https://api.zephyrscale.smartbear.com/v2",
        "COLLABORATOR_BASE_URL": "your collab base url",
        "COLLABORATOR_USERNAME": "your collab user name",
        "COLLABORATOR_LOGIN_TICKET": "your collab login ticket",
        "QTM4J_API_KEY": "your_qtm4j_key",
        "QTM4J_BASE_URL": "https://qtmcloud.qmetry.com",
        "QTM4J_AUTOMATION_API_KEY": "your_qtm4j_automation_api_key",
        "SWAGGER_FUNCTIONAL_TESTING_API_TOKEN": "your_swagger_functional_testing_api_token",
        "SWAGGER_FUNCTIONAL_TESTING_BASE_PATH": "https://api.reflect.run/v1"
      }
    }
  }
}

Loading only the products you use

Set MCP_CLIENTS to a comma-separated, case-insensitive list of product names (for example "MCP_CLIENTS": "QMetry") to load only those products. This reduces startup time, which helps on clients with a short initialize timeout. Valid names are BearQ, BugSnag, Collaborator, Contract Testing, QMetry, QTM4J, Reflect, Swagger and Zephyr. When unset, all products are loaded.

Server Configuration (HTTP mode)

Documentation

For detailed introduction, examples, and advanced configuration visit our 📖 Full Documentation

Local Development

For developers who want to contribute to the SmartBear MCP server, please see the CONTRIBUTING.md guide.

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

Support

• Search open and closed issues for similar problems
• Report a bug or request a feature

---

SmartBear MCP Server - Bringing the power of SmartBear’s testing and monitoring ecosystem to your AI-powered development workflow.