SmartBear MCP Server

How to use

You use the MCP server by starting it in your development environment and then connecting your MCP client. Provide your authentication tokens for the SmartBear products you want to access; you can leave tokens blank to disable specific tools. Once running, you can query BugSnag errors, review test management data from Test Hub, work with Swagger portals, Studio projects, and contract testing via PactFlow/Pact Broker, as well as leverage QMetry, Zephyr, and Collaborator capabilities. Use natural language prompts to fetch data, run tests, or configure settings across the connected tools.

How to install

Prerequisites you need before installing the MCP Server are straightforward. Ensure you have Node.js 20 or newer and npm installed on your machine. You also need access to the SmartBear products you plan to integrate (BugSnag, Reflect, Swagger, QMetry, Zephyr, etc.) and valid API tokens for those products.

Step 1. Install the MCP server in your environment using the recommended runtime. The MCP server can be run with a lightweight setup using npx so you don’t have to install a global package.

{
  "mcpServers": {
    "smartbear": {
      "command": "npx",
      "args": [
        "-y",
        "@smartbear/mcp@latest"
      ],
      "env": {
        "BUGSNAG_AUTH_TOKEN": "${input:bugsnag_auth_token}",
        "BUGSNAG_PROJECT_API_KEY": "${input:bugsnag_project_api_key}",
        "REFLECT_API_TOKEN": "${input:reflect_api_token}",
        "SWAGGER_API_KEY": "${input:swagger_api_key}",
        "PACT_BROKER_BASE_URL": "${input:pact_broker_base_url}",
        "PACT_BROKER_TOKEN": "${input:pact_broker_token}",
        "PACT_BROKER_USERNAME": "${input:pact_broker_username}",
        "PACT_BROKER_PASSWORD": "${input:pact_broker_password}",
        "QMETRY_API_KEY": "${input:qmetry_api_key}",
        "QMETRY_BASE_URL": "${input:qmetry_base_url}",
        "ZEPHYR_API_TOKEN": "${input:zephyr_api_token}",
        "ZEPHYR_BASE_URL": "${input:zephyr_base_url}",
        "COLLAB_BASE_URL": "${input:collab_base_url}",
        "COLLAB_USERNAME": "${input:collab_username}",
        "COLLAB_LOGIN_TICKET": "${input:collab_login_ticket}"
      }
    }
  },
  "inputs": [
      {
         "id": "bugsnag_auth_token",
         "type": "promptString",
         "description": "BugSnag Auth Token - leave blank to disable BugSnag tools",
         "password": true
      },
      {
         "id": "bugsnag_project_api_key",
         "type": "promptString",
         "description": "BugSnag Project API Key - for single project interactions",
         "password": false
      },
      {
         "id": "reflect_api_token",
         "type": "promptString",
         "description": "Reflect API Token - leave blank to disable Reflect tools",
         "password": true
      },
      {
         "id": "swagger_api_key",
         "type": "promptString",
         "description": "Swagger API Key - leave blank to disable Swagger tools",
         "password": true
      },
      {
         "id": "pact_broker_base_url",
         "type": "promptString",
         "description": "PactFlow or Pact Broker base url - leave blank to disable the tools",
         "password": true
      },
      {
         "id": "pact_broker_token",
         "type": "promptString",
         "description": "PactFlow Authentication Token",
         "password": true
      },
      {
         "id": "pact_broker_username",
         "type": "promptString",
         "description": "Pact Broker Username",
         "password": true
      },
      {
         "id": "pact_broker_password",
         "type": "promptString",
         "description": "Pact Broker Password",
         "password": true
      },
      {
          "id": "qmetry_api_key",
          "type": "promptString",
          "description": "QMetry Open API Key",
          "password": true
      },
      {
          "id": "qmetry_base_url",
          "type": "promptString",
          "description": "By default, connects to https://testmanagement.qmetry.com. Change to a custom QMetry server URL or a region-specific endpoint if needed.",
          "password": false
      },
      {
          "id": "zephyr_api_token",
          "type": "promptString",
          "description": "Zephyr API token - leave blank to disable Zephyr tools",
          "password": true
      },
      {
          "id": "zephyr_base_url",
          "type": "promptString",
          "description": "Zephyr API base URL. By default, connects to https://api.zephyrscale.smartbear.com/v2. Change to region-specific endpoint if needed.",
          "password": false
      },
      {
          "id": "collab_base_url",
          "type": "promptString",
          "description": "Collab base url",
          "password": true
      },
      {
          "id": "collab_username",
          "type": "promptString",
          "description": "Collab username",
          "password": true
      },
      {
          "id": "collab_login_ticket",
          "type": "promptString",
          "description": "Collab login ticket",
          "password": true
      }
  ]
}

Additional configuration and usage notes

You can also configure the MCP server for Claude Desktop to launch via npx by including a setup block that mirrors the command and environment variables used for the MCP startup. This makes it easy to run the server from your preferred local tools and keeps token handling centralized in your project configuration.

Security and tokens

Control access to individual tools by supplying tokens or leaving tokens blank to disable particular integrations. Tokens are passed as environment variables when you start the MCP server, so keep them secure and do not share configuration files containing credentials.

Troubleshooting and tips

If tools appear disabled, verify you provided valid tokens or left them blank intentionally. Check that your environment variables are accessible to the process running the MCP server. For issues starting the server, ensure you are using Node.js 20+ and that you are running the exact command shown in the installation snippet.

DataAccess

Exposes connected tools through natural language prompts, enabling data retrieval, analysis, and actions across BugSnag, Reflect, Swagger, PactFlow, QMetry, Zephyr, and Collaborator within your AI workflow.