How to Use the Percy MCP in LlamaIndex

Q: How does LlamaIndex store metadata from Percy builds?

The framework calls listbuilds and stores the resulting JSON metadata as document nodes. LlamaIndex then indexes these nodes, allowing you to search past visual test runs semantically.

Q: Can I use LlamaIndex to find specific visual diffs in Percy?

Yes, your agent uses listsnapshots to retrieve diff percentages. It then matches these metrics against your query to locate the exact snapshots that exceeded your visual thresholds.

Q: How do I set up the Percy MCP tool spec in LlamaIndex?

You initialize the BasicMCPClient with the server URL and pass it to McpToolSpec. Calling totoollistasync() exposes the visual testing tools to your LlamaIndex agent.

Index visual regression metadata into LlamaIndex to query your Percy test history semantically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Percy MCP to LlamaIndex

Create your Vinkius account to connect Percy to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Percy with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index visual test history in LlamaIndex

This Percy MCP Server feeds visual execution data directly into your LlamaIndex vector store. Your LlamaIndex indexer uses `list_builds` and `get_build_details` to ingest historical Percy test records, transforming raw API responses into searchable documents. Users query the LlamaIndex to find which commits caused the most visual churn in Percy over time. By combining live Percy API data with historical runs, your LlamaIndex RAG application answers complex visual regression questions without querying the web dashboard.

Ground RAG agents with live visual metrics

The MCP Server provides direct access to Percy visual diff data using `list_snapshots` and `get_snapshot_details`. Your LlamaIndex agent retrieves real-time Percy regression metrics to ground its responses in actual pixel-level facts rather than training data. When a user asks LlamaIndex about UI stability, the agent calls `list_comparisons` to check exact Percy browser differences. It compares current Percy snapshot states against historical baselines stored in your LlamaIndex document index to produce precise, hallucination-free summaries.

Map project configurations with LlamaIndex

Using `McpToolSpec`, your LlamaIndex pipelines map Percy project environments by querying `list_projects` and `get_project_details`. The LlamaIndex framework converts these Percy tool outputs into structured node metadata for semantic search. The LlamaIndex agent inspects `list_browsers` to verify cross-browser coverage across different Percy projects. This lets your QA team query their Percy visual testing footprint using LlamaIndex natural language, finding gaps in browser targets instantly.

Setup guide

Set up Percy 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 Percy 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 Percy tools.",
)
response = await agent.run("List recent Percy 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 Percy. 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 Percy 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 Percy MCP in LlamaIndex

The framework calls `list_builds` and stores the resulting JSON metadata as document nodes. LlamaIndex then indexes these nodes, allowing you to search past visual test runs semantically.

Yes, your agent uses `list_snapshots` to retrieve diff percentages. It then matches these metrics against your query to locate the exact snapshots that exceeded your visual thresholds.

You initialize the `BasicMCPClient` with the server URL and pass it to `McpToolSpec`. Calling `to_tool_list_async()` exposes the visual testing tools to your LlamaIndex agent.

The agent queries the index to check if similar diffs were approved historically. If the patterns match, it executes `approve_build` or `approve_snapshot` to update the baseline.

The integration only processes visual snapshots, project configurations, and build metadata. This data is handled in an ephemeral sandbox, ensuring your visual assets are never stored or exposed to external models.

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