How to Use the EyePop.ai MCP in LlamaIndex

Q: Can I query my LlamaIndex vector store for specific EyePop.ai detections?

Yes, your agent indexes the outputs from listdetections directly into your vector store. You can then run semantic queries to find files containing specific labels.

Q: How does LlamaIndex handle metadata from EyePop.ai video analysis?

The agent parses the temporal results from analyzevideo into structured nodes. Each node contains timestamps and bounding boxes, making your video timeline searchable.

Q: Does LlamaIndex store my visual pipeline configurations permanently?

No, pipeline details retrieved via getpop are processed in memory during indexing. Vinkius uses secure V8 isolates to ensure your pipeline configurations never leak or persist in unauthorized logs.

Index real-time computer vision data directly into your LlamaIndex vector store for instant semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EyePop.ai MCP to LlamaIndex

Create your Vinkius account to connect EyePop.ai 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 EyePop.ai with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn visual detections into searchable index nodes with this MCP Server

The `list_detections` tool retrieves raw detection logs from your visual pipelines, which LlamaIndex then parses into searchable document nodes. Instead of letting visual data sit idle, your agent indexes these coordinates and labels directly into your vector database. When you query your LlamaIndex knowledge base, the search matches against actual detected objects. You can find specific moments in your media without manually tagging files or writing custom database schemas.

Run automated queries through custom visual pipelines

The `analyze_image` tool processes static media files to extract labels and coordinates for your LlamaIndex query engine. The LlamaIndex query engine uses this live visual context to resolve user queries, matching detected labels against your indexed documents. For dynamic media, your agent triggers `analyze_video` to index temporal movements and changes over time. This lets you build RAG applications that can search across both static images and long-form video files.

Manage pipeline configurations directly from your index queries

The `get_pop` tool pulls the configuration of your active visual pipeline to verify its settings before indexing new media using this MCP tool. If the pipeline setup doesn't match your index schema, your LlamaIndex agent calls `create_pop` to adjust the pipeline on the fly. This automated alignment ensures your vector store always receives data format-compatible with your existing index structure. You avoid schema mismatch errors and keep your data ingestion pipeline running smoothly.

Setup guide

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

Install the LlamaIndex MCP tool spec and initialize the client with your Vinkius URL. Pass the tools list to your FunctionAgent to start indexing visual data.

Yes, your agent indexes the outputs from `list_detections` directly into your vector store. You can then run semantic queries to find files containing specific labels.

The agent parses the temporal results from `analyze_video` into structured nodes. Each node contains timestamps and bounding boxes, making your video timeline searchable.

No, the models run on EyePop.ai's cloud infrastructure. Your LlamaIndex agent simply calls the remote tools through Vinkius to get the visual data.

No, pipeline details retrieved via `get_pop` are processed in memory during indexing. Vinkius uses secure V8 isolates to ensure your pipeline configurations never leak or persist in unauthorized logs.

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