How to Use the Xray (Test Management) MCP in LangChain

Q: How does LangChain use Xray (Test Management) data to guide testing?

Your agent uses tools like getindividualtestruns to gather specific test history. It can then decide if a failure in that run requires checking the overall project configuration using getxraysettings.

Q: Can I list all available tests in Xray (Test Management) using LangChain?

Yes. The listxraytests tool lists every test case in the project, providing a clean starting point for any multi-step chain or agent process.

Q: Does this MCP Server support persistent context for Xray (Test Management) with LangChain?

The client supports session management via client.session(), ensuring that the outputs from one tool call remain available as input context for later steps.

Build reasoning agents with LangChain using Xray (Test Management) data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Xray (Test Management) MCP to LangChain

Create your Vinkius account to connect Xray (Test Management) 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 Xray (Test Management) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Test Data Retrieval for LangChain

The `list_test_executions` tool lets your agent pull a full list of all test runs. You can then feed those IDs into `get_execution_details` to grab the granular results needed for decision making. This chain structure is perfect for ReAct agents; one step gathers the scope, and the next validates the outcome against specific run data.

Querying Test Structures via MCP Server

Need to know what tests exist? Use `list_xray_tests` to list every test case in the Xray project. Then, if you find a relevant ID, call `get_test_details` for all the specific metadata attached to it. It's ideal for creating complex pipelines where the agent first maps the available assets and then pulls deep specs on demand.

Managing Test Plans with LangChain

The `list_test_plans` tool lets your agent see all existing test plans. Once a plan is identified, you can use `get_test_plan_details` to pull the full setup and scope of that testing cycle. This makes it simple for multi-step workflows: the agent selects the correct plan record, then processes the detailed contents.

Setup guide

Set up Xray (Test Management) 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 Xray (Test Management) 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({
    "xray-test-management-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 Xray (Test Management) 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 Xray (Test Management). 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 Xray (Test Management) 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 Xray (Test Management) MCP in LangChain

Your agent uses tools like `get_individual_test_runs` to gather specific test history. It can then decide if a failure in that run requires checking the overall project configuration using `get_xray_settings`.

The MCP Server handles test execution records, including specific test IDs and associated run results. Your agent can use these structured outputs to build context for subsequent decisions.

Yes. The `list_xray_tests` tool lists every test case in the project, providing a clean starting point for any multi-step chain or agent process.

The client supports session management via `client.session()`, ensuring that the outputs from one tool call remain available as input context for later steps.

This server touches test execution records, including granular results, individual run instances, and project configuration settings.

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