BrowserStack Connector for AI agents.
10 live capabilities
Manage cross-browser testing builds and logs from your AI agent.
Waiting for input…
Why people use BrowserStack
BrowserStack for faster cross-browser testing debugging
This Connector changes that by letting you stay in your chat client. You just ask your agent for the logs of a failed build, and it pulls the data for you instantly. You get the exact reason for the failure without ever leaving your workspace.
What Vinkius changes
You stop tab-hopping between your IDE and the BrowserStack dashboard.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Debugging a flaky test
A QA engineer asks for the logs of build e4da3b.
- Real-world use case 02
Checking capacity
A DevOps lead asks how many more tests they can run.
- Real-world use case 03
Updating scripts
A developer needs to know if a specific browser version is supported.
Complete set · 10capabilities
The complete BrowserStack capability set.
These are the exact actions your AI can choose when you ask it to work with BrowserStack.
01—04
4 capabilities in this set.
Part of 10 available through BrowserStack.
- 01 Capability
List browsers
Lists all supported OS and browser combinations for configuring desired capabilities.
- 02 Capability
List builds
Lists recent builds with statuses, durations, and session counts for tracking suites.
- 03 Capability
Get build
Retrieves session details, OS/browser combos, and logs for a specific automation build.
- 04 Capability
Get session
Gets specific details for a session, including video URLs, logs, and failure reasons.
05—07
3 capabilities in this set.
Part of 10 available through BrowserStack.
- 05 Capability
Get session logs
Fetches the text execution logs for a session to help debug failed test steps.
- 06 Capability
Get plan
Shows your current plan details, including parallel session usage and queue length.
- 07 Capability
Delete session
Deletes a specific BrowserStack session by its ID.
08—10
3 capabilities in this set.
Part of 10 available through BrowserStack.
- 08 Capability
Delete build
Deletes a specific BrowserStack build using its unique ID.
- 09 Capability
List projects
Lists all projects on BrowserStack Automate with their names, IDs, and build counts.
- 10 Capability
Get project
Fetches full details for a project, including its group ID and recent builds.
Set up in minutes
One URL. Then ask BrowserStack to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use BrowserStack from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_QfMSmaBJhbb00bXFG15oIucKmIgIGaxUOK4qcRpA/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it BrowserStack, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable BrowserStack for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_QfMSmaBJhbb00bXFG15oIucKmIgIGaxUOK4qcRpA/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the BrowserStack URL.
- Step 03
Save and start
Save the connection and enable BrowserStack in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"browserstack": {
"url": "https://edge.vinkius.com/vk_preview_QfMSmaBJhbb00bXFG15oIucKmIgIGaxUOK4qcRpA/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using BrowserStack
Open Agent mode in chat and ask: "Using BrowserStack, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"browserstack": {
"url": "https://edge.vinkius.com/vk_preview_QfMSmaBJhbb00bXFG15oIucKmIgIGaxUOK4qcRpA/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using BrowserStack
Ask Copilot: "Using BrowserStack, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"browserstack": {
"url": "https://edge.vinkius.com/vk_preview_QfMSmaBJhbb00bXFG15oIucKmIgIGaxUOK4qcRpA/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using BrowserStack
Open Cascade and ask: "Using BrowserStack, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"browserstack": {
"url": "https://edge.vinkius.com/vk_preview_QfMSmaBJhbb00bXFG15oIucKmIgIGaxUOK4qcRpA/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using BrowserStack
Ask Cline: "Using BrowserStack, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add browserstack --transport http "https://edge.vinkius.com/vk_preview_QfMSmaBJhbb00bXFG15oIucKmIgIGaxUOK4qcRpA/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using BrowserStack
Ask Claude: "Using BrowserStack, show me...". 10 tools are ready
Where the request belongs
Work BrowserStack can move forward.
QA engineers and DevOps folks who are tired of manual dashboard hunting to debug failed tests or check concurrency limits.
QA Engineer
Pulls logs for failed sessions directly into the IDE to find bugs faster.
DevOps Engineer
Checks parallel session limits and clears out stuck execution sessions.
Test Automator
Verifies supported OS/browser combinations while updating test scripts.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsTestMu AI (formerly LambdaTest)
Manage cross-browser testing via TestMu AI. audit automation builds, inspect test sessions, and retrieve visual logs.
LambdaTest
Test your website and apps across thousands of real browsers and devices in the cloud with automated and manual testing capabilities.
Browserbase
Cloud browser infrastructure for AI agents. create, control, and manage headless Chromium sessions via CDP for automated web interaction.
Browserless (Playwright Cloud)
Equip your AI with a remote headless browser to scrape, interact, and run Playwright safely via cloud.
Sauce Labs
Monitor and manage UI/E2E test automation at scale via AI. stop failing jobs, inspect video logs, and check pipeline concurrency metrics.
Mabl (AI-Powered Test Automation)
Manage E2E testing via Mabl. trigger test plans, monitor execution results, and perform AI-driven failure analysis.
Bring your own AI
Change the model, client or framework. Keep BrowserStack connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about BrowserStack.
The practical details behind the request, access and result.
Can the BrowserStack MCP help me debug failed tests?
Yes, it lets you pull the text execution logs of a failed session directly into your chat. You can see the exact error messages without leaving your IDE.
How does this Connector help with my testing plan?
It gives you instant visibility into your current plan, showing you how many parallel sessions you're using and how many are left in your queue.
Can I see which browsers are supported with the BrowserStack MCP?
Yes, you can ask your agent to list all supported OS and browser combinations to make sure your test scripts are configured correctly.
Does this Connector work with Claude or Cursor?
Yes, it works with any MCP-compatible client, including Claude, Cursor, and Windsurf.
Can I manage my projects using this?
You can list all your projects and get specific details about them, like group IDs and recent build history, using natural language.
How do I find out why a test timed out?
You can ask your agent to fetch the session details for a specific build. It will pull the OS, browser, duration, and any available logs to help you find the bottleneck.
Can my AI automatically read the logs of a failed Selenium test?
Yes. When you ask it to investigate a recently failed build, the agent can use get_build to find the failed session, and then automatically call get_session_logs. It will download the raw textual execution steps directly into the chat and summarize why the UI test failed.
Is there a risk that my AI alters my testing scripts or repository code?
No, this Connector integrates exclusively with BrowserStack Automate API. It can read statuses, logs, and configurations, and can delete hung sessions or builds, but it has no connection to your actual codebase or git repository.
How can I resolve concurrent session limits preventing my pipeline from advancing?
You can ask your agent to get_plan to inspect your parallel boundaries and verify if you are queuing. Then, the agent can look up stalled items via list_builds and execute delete_session or delete_build to manually unblock stuck processes.
One connection away
Give your agent a direct line to BrowserStack.
Connect BrowserStack once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available