How to Use the Cypress Cloud MCP in LlamaIndex

Q: How do I index Cypress Cloud test results into a LlamaIndex vector store?

You connect the MCP Server using BasicMCPClient and convert the tools using McpToolSpec. Your LlamaIndex agent then runs the tools to fetch run data and loads the outputs into your document index.

Q: Can LlamaIndex query real-time Cypress Cloud data?

Yes, by using the FunctionAgent with the Cypress Cloud MCP tools, the agent can call getruns or getinstance on the fly to answer queries with live data instead of relying on stale vector embeddings.

Q: How does LlamaIndex handle flaky test reports from Cypress Cloud?

The agent calls reportflaky to retrieve flake rates and last flake dates. It then indexes these metrics, allowing you to run semantic queries to find the most unstable specs in your suite.

Q: How do I configure the Cypress Cloud MCP tool spec in Python?

Install llama-index-tools-mcp via pip. Initialize the client with your Vinkius HTTP URL, call totoollistasync(), and pass the resulting tools to your FunctionAgent.

Index Cypress Cloud test runs and spec histories directly into your LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cypress Cloud MCP to LlamaIndex

Create your Vinkius account to connect Cypress Cloud to LlamaIndex 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 Cypress Cloud with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Cypress Cloud Run History using LlamaIndex

The `get_runs` tool fetches historical Cypress Cloud run data so your LlamaIndex pipeline can index it for semantic search. Your RAG setup retrieves run IDs, commit messages, and durations, converting them into searchable document nodes. This enables you to query your testing history using natural language to find when a specific spec started failing. The MCP Server acts as a live data connector, ensuring your vector store stays updated without manual exports.

Search Spec Failures Semantically

The `get_instance` tool extracts spec-level errors, screenshot links, and video URLs directly into your LlamaIndex query engine. When an agent queries why a build failed, the engine calls this tool alongside `get_tests` to pull the exact failure trace. By indexing these live error logs, your agent can match new failures against historical fixes in your vector database. You get immediate context on whether a failing spec is a known issue or a new bug.

Profile Slow Tests with Index-Grounded Agents

The `report_slow` tool identifies your slowest Cypress Cloud tests so LlamaIndex agents can analyze performance trends over time. The tool returns average and p95 durations, which your agent parses and indexes alongside your codebase architecture documents. This allows your LlamaIndex agent to ground its optimization suggestions in real Cypress execution metrics. Instead of guessing which files are bloated, the agent queries the indexed slow-test reports to pinpoint the exact specs needing refactoring.

Setup guide

Set up Cypress Cloud MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Cypress Cloud MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Cypress Cloud tools.",
)
response = await agent.run("List recent Cypress Cloud data")

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 Cypress. 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 Cypress Cloud 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 Cypress Cloud MCP in LlamaIndex

You connect the MCP Server using `BasicMCPClient` and convert the tools using `McpToolSpec`. Your LlamaIndex agent then runs the tools to fetch run data and loads the outputs into your document index.

Yes, by using the `FunctionAgent` with the Cypress Cloud MCP tools, the agent can call `get_runs` or `get_instance` on the fly to answer queries with live data instead of relying on stale vector embeddings.

The agent calls `report_flaky` to retrieve flake rates and last flake dates. It then indexes these metrics, allowing you to run semantic queries to find the most unstable specs in your suite.

Install `llama-index-tools-mcp` via pip. Initialize the client with your Vinkius HTTP URL, call `to_tool_list_async()`, and pass the resulting tools to your `FunctionAgent`.

Absolutely, all spec run details, error logs, and project IDs are pulled through this MCP Server's ephemeral V8 sandbox. Vinkius does not store your Cypress API tokens or test payloads, passing them securely to your local index.

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