SmartBear MCP server
OfficialThe SmartBear MCP server lets AI assistants interact with SmartBear's testing, monitoring, and API management tools through natural language. Key capabilities include:
BearQ (AI-Powered QA)
Run regression test suites or specific test cases (by ID or functional area)
Refine draft test cases individually, by functional area, or all at once
Expand the application model by exploring the live app
Chat with the QA Lead agent for general-purpose QA tasks
Manage tasks: get status, wait for completion, or stop running tasks
Reflect (Test Management & Execution)
List, run, and get details of tests and suites; execute and cancel suite runs
Connect to live recording sessions to add natural language steps, capture screenshots, delete steps, and insert reusable segments
BugSnag (Error Monitoring & Performance)
List, filter, and update errors (open, fix, ignore, snooze, link/unlink issues)
Get detailed event info, releases, and builds
Monitor performance via span groups, traces, and network endpoint grouping rules
Swagger / SwaggerHub (API Management)
Manage portals, products, documentation pages (Markdown/HTML), and table of contents entries
Search, retrieve, create, and update API definitions in the registry
Scan APIs for governance/standardization issues; generate and standardize APIs from natural language using AI
PactFlow / Contract Testing
Generate and review Pact tests using AI (from request/response pairs, code, or OpenAPI docs)
Check deployment safety with "Can I Deploy" and view the contract verification matrix
Manage pacticipants, branches, versions, and environments; record deployments and releases
Publish consumer and provider contracts; retrieve pacts for verification and BDCT results
Get workspace/team metrics and check PactFlow AI entitlements
Provides tools for error monitoring and debugging, enabling querying of errors, performance metrics, and project management.
Provides tools for managing APIs, portals, and domains, including AI-powered API generation, contract testing, and portal administration.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@SmartBear MCP server show me recent critical errors from BugSnag"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Related MCP server: Autotest AI MCP Server
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.
Product | Server URL |
Swagger |
|
BugSnag |
|
Zephyr |
|
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.
Alternatively, you can use npx (or globally install) the @smartbear/mcp package to run the server and add the following to your .vscode/mcp.json file:
{
"servers": {
"smartbear": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@smartbear/mcp@latest"
],
"env": {
"BEARQ_API_TOKEN": "${input:bearq_api_token}",
"BEARQ_API_BASE_URL": "${input:bearq_api_base_url}",
"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}",
"SWAGGER_PORTAL_BASE_PATH": "${input:swagger_portal_base_path}",
"SWAGGER_REGISTRY_BASE_PATH": "${input:swagger_registry_base_path}",
"SWAGGER_UI_BASE_PATH": "${input:swagger_ui_base_path}",
"PACT_BROKER_BASE_URL": "${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": "${input:zephyr_base_url}",
"COLLABORATOR_BASE_URL": "${input:collab_base_url}",
"COLLABORATOR_USERNAME": "${input:collab_username}",
"COLLABORATOR_LOGIN_TICKET": "${input:collab_login_ticket}",
"QTM4J_API_KEY": "${input:qtm4j_api_key}",
"QTM4J_BASE_URL": "${input:qtm4j_base_url}",
"QTM4J_AUTOMATION_API_KEY": "${input:qtm4j_automation_api_key}",
"SWAGGER_FUNCTIONAL_TESTING_API_TOKEN": "${input:swagger_functional_testing_api_token}",
"SWAGGER_FUNCTIONAL_TESTING_BASE_PATH": "${input:swagger_functional_testing_base_path}"
}
}
},
"inputs": [
{
"id": "bearq_api_token",
"type": "promptString",
"description": "BearQ workspace API token - leave blank to disable BearQ tools",
"password": true
},
{
"id": "bearq_api_base_url",
"type": "promptString",
"description": "BearQ API base URL - leave blank to use the default (https://api.bearq.smartbear.com)",
"password": false
},
{
"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": "swagger_portal_base_path",
"type": "promptString",
"description": "Swagger Portal API base path - only needed for on-premise installations (leave blank for cloud)",
"password": false
},
{
"id": "swagger_registry_base_path",
"type": "promptString",
"description": "Swagger Registry API base path - only needed for on-premise installations (leave blank for cloud)",
"password": false
},
{
"id": "swagger_ui_base_path",
"type": "promptString",
"description": "Swagger UI base path - only needed for on-premise installations (leave blank for cloud)",
"password": false
},
{
"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
},
{
"id": "qtm4j_api_key",
"type": "promptString",
"description": "QTM4J API Key",
"password": true
},
{
"id": "qtm4j_base_url",
"type": "promptString",
"description": "US region (default): https://qtmcloud.qmetry.com. Australia region: https://syd-qtmcloud.qmetry.com.",
"password": false
},
{
"id": "qtm4j_automation_api_key",
"type": "promptString",
"description": "QTM4J Automation API Key - required for automation tools, leave blank to disable them",
"password": true
},
{
"id": "swagger_functional_testing_api_token",
"type": "promptString",
"description": "Swagger Functional Testing API Token - leave blank to disable Functional Testing tools",
"password": true
},
{
"id": "swagger_functional_testing_base_path",
"type": "promptString",
"description": "Swagger Functional Testing API Base URL - leave blank to use the default (https://api.reflect.run/v1)",
"password": false
}
]
}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)
Variable | Default | Purpose |
| (derived from request) | The server's own public URL, e.g. |
|
| Set to |
| (unset — analytics off) | API key for the shared SmartBear Amplitude project. When set, the server reports |
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
SmartBear MCP Server - Bringing the power of SmartBear's testing and monitoring ecosystem to your AI-powered development workflow.
Available Tools
1 toolsmartbear_list_integrationsSmartBear: List IntegrationsARead-onlyIdempotentInspect
Lists every SmartBear product this server supports, whether it is configured for this connection, and for unconfigured products the environment variable or HTTP header each setting needs. Only products allowed by the server's MCP_CLIENTS setting are listed. Products that accept per-request OAuth tokens (BearQ, Reflect, QMetry) always show as configured. Takes no parameters.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only a single tool in the set, there is no possibility of confusing it with another tool; its purpose (listing supported SmartBear products and their configuration requirements) is unambiguous.
The lone tool name, smartbear_list_integrations, follows a clear snake_case verb_noun convention with a product prefix, which would be a predictable pattern if extended to other tools.
A server that claims to front the entire SmartBear product suite (BearQ, Reflect, QMetry, and others) exposes only a single discovery tool, so the surface is far too thin for the apparent scope and cannot support any actual product operations.
The only capability is listing integrations; there are no tools to actually interact with any SmartBear product (no create/read/update operations on tests, bugs, or APIs), leaving agents at a dead end after discovery.
Maintenance
Related MCP Connectors
AI-callable tools for API mocking, testing, monitoring, security, and automation.
Lets AI agents analyze API metrics, request logs, and traces, and manage apps and alerts.
Let AI agents list, read and resolve Bugsly error-tracking issues and check monitors.
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
Related MCP Servers
AlicenseBqualityBmaintenanceEnables AI assistants to interact with Sauce Labs testing platform through natural language, providing access to device cloud management, test job analysis, build monitoring, and testing infrastructure insights. Supports both Virtual Device Cloud (VDC) and Real Device Cloud (RDC) with comprehensive test analytics and team collaboration features.3410Apache 2.0- AlicenseAqualityDmaintenanceEnables AI agents to manage Autotest AI projects, screens, test cases, and test runs through natural language commands.10MIT
- AlicenseNot gradedqualityDmaintenanceProvides AI assistants with seamless access to SmartBear's suite of testing and monitoring tools, enabling querying testing data, analyzing performance metrics, and managing test automation through natural language.MIT
- AlicenseBqualityCmaintenanceLets AI assistants inspect test run results, AI QA reports, and findings with their full evidence, and, when asked, start runs, re-run only failed tests, import API specs, or scan a website. Read-only tools are free, while work-starting tools consume the workspace's allowance and report usage limits.1922 npmMIT