How to Use the EyePop.ai MCP in Claude

Q: How do I analyze local files with EyePop.ai in Claude Desktop?

Use the analyzeimage tool inside Claude Desktop to process files on your local drive. Your agent reads the local path, sends the payload to EyePop.ai, and displays the detected labels in your chat window via this MCP integration.

Q: Can I manage my visual pipelines using EyePop.ai inside Claude Desktop?

Yes. Run createpop to build a new pipeline, or use listpops to see your existing setups. Claude Desktop manages these API calls directly through your connected account.

Q: Does the EyePop.ai integration with Claude Desktop support connection health checks?

Run checkeyepopstatus to verify that Claude Desktop has a live connection to your EyePop.ai endpoint. This tool returns the current API latency and system availability immediately.

Q: How do I list available computer vision models in EyePop.ai using Claude Desktop?

Execute the listmodels tool to get a full directory of pre-trained models. Claude Desktop parses the response so you can choose between face recognition, object detection, or classification models using an MCP configuration.

Run computer vision pipelines directly from Claude Desktop to analyze local images and videos without writing code.

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 Claude Desktop

Create your Vinkius account to connect EyePop.ai to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze local media directly in Claude Desktop

The `analyze_image` tool passes local files from your machine straight to EyePop.ai models inside Claude Desktop. Your agent inspects files on your hard drive, extracts bounding boxes, and returns labels without you writing a single line of Python. This setup runs locally via the Claude Desktop config file. You drop an image into the chat, and the desktop app uses your local system transport to trigger the visual pipeline instantly.

Configure visual pipelines inside Claude Desktop

The `create_pop` tool configures visual pipelines, or "pops," directly through the Claude Desktop chat interface. You tell your agent what objects to track, and it configures the pipeline parameters on your EyePop.ai account. Once configured, you check the status of your pipeline using `get_pop` or pull a list of active configurations with `list_pops`. Claude Desktop displays the pipeline structure in plain text so you verify the model targets before processing heavy files.

Query model metadata inside this MCP Server

The `analyze_video` tool extracts temporal object detection data from video files using the EyePop.ai MCP Server. Your agent processes frames sequentially and returns timestamps alongside detection coordinates directly in your desktop workspace. To find the right model for your video, use `list_models` or `get_model` to check parameters. You avoid wasting API credits on incorrect model architectures by verifying compatibility before running a long video analysis.

Setup guide

Set up EyePop.ai MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The EyePop.ai MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the EyePop.ai MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under eyepopai-mcp.

json

{
  "mcpServers": {
    "eyepopai-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

Use the `analyze_image` tool inside Claude Desktop to process files on your local drive. Your agent reads the local path, sends the payload to EyePop.ai, and displays the detected labels in your chat window via this MCP integration.

Yes. Run `create_pop` to build a new pipeline, or use `list_pops` to see your existing setups. Claude Desktop manages these API calls directly through your connected account.

Run `check_eyepop_status` to verify that Claude Desktop has a live connection to your EyePop.ai endpoint. This tool returns the current API latency and system availability immediately.

Execute the `list_models` tool to get a full directory of pre-trained models. Claude Desktop parses the response so you can choose between face recognition, object detection, or classification models using an MCP configuration.

Your local images and video files are sent directly to the EyePop.ai API for processing, and only the resulting detection metadata returns to Claude Desktop. The MCP protocol ensures your raw media files never persist on public intermediate servers.

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