How to Use the BugBug MCP in LangChain

Run your BugBug automated browser tests and trace test executions directly inside your LangChain reasoning loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BugBug MCP to LangChain

Create your Vinkius account to connect BugBug to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup BugBug with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger BugBug tests from LangChain chains

Let your agent decide when to kick off a browser test. When your codebase changes, your LangChain agent uses `run_test` or `run_suite` to verify the deployment immediately without manual intervention. The tool output flows straight to the next step in your sequence. If `get_test_run` shows a failure, your agent can inspect the log and draft a bug report in the same run.

Inspect active test runs with this MCP Server

Use `list_suite_runs` to keep tabs on your continuous integration pipeline. Your agent fetches the latest runs, checks their status, and decides if it needs to poll for updates. If a run hangs, the agent calls `get_suite_run` to diagnose the exact step that failed. You get immediate visibility into your browser testing health without jumping between dashboards.

Inventory your entire QA suite

Stop hardcoding test IDs in your code. This MCP server lets your planning agents map out your test coverage by using `list_projects` and `list_tests` to find the exact test cases available for your web application. This makes your QA chains highly adaptable. When you ask your agent to test a specific feature, it queries `list_suites` to find the right match and executes it on the fly.

Setup guide

Set up BugBug MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes BugBug tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "bugbug-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent BugBug transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by BugBug. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect BugBug now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about BugBug MCP in LangChain

You hook up the MCP tools directly to your agent's tool list. When the agent calls `run_test`, the returned run ID is immediately available for the next chain step, where `get_test_run` monitors the status.

Yes, by using an agent loop. Your agent initiates the suite with `run_suite`, then enters a loop using `get_suite_run` to check the progress until it completes or times out.

LangSmith captures every single input and output from this server. You can see the exact parameters passed to `run_test` and trace the latency of your automated browser tests.

No. Vinkius handles the authentication behind the scenes. Your agent just talks to the single MCP endpoint, keeping your credentials safe and out of your codebase.

It only touches your test definitions, project metadata, and execution run results. Your proprietary application database and user passwords never pass through our infrastructure.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript