Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Aporia with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Monitor AI models and validate LLM interactions with guardrails directly from your AI agent to ensure safety and observability.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 7 capabilities

The complete Aporia capability set.

These are the exact actions your AI can choose when you ask it to work with Aporia.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Aporia.

  1. 01

    List models

    List Aporia monitored machine learning and LLM models

  2. 02

    List monitors

    List configured Aporia monitors for a specific model

  3. 03

    Validate guardrails

    G. toxicity, PII, off-topic). Pass an array of messages. Validate LLM interactions against Aporia guardrails

  4. 04

    Get metrics

    Get performance and drift metrics for an Aporia monitored model

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Aporia.

  1. 05

    Get model

    Get specific details for a monitored Aporia model

  2. 06

    List dashboards

    List custom dashboards configured in the Aporia workspace

  3. 07

    Trigger monitor

    Trigger an immediate run of a specific Aporia monitor

Observed, not estimated

863ms average. Fast in production.

Aporia is checked daily against the live service.

Daily averagePeak 1073ms
Aug 20Today
Fastest day
708ms
Slowest day
1073ms
14-day trend
Slowing+44%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Aporia, so you can see the experience inside your AI.

It does not authenticate your account with Aporia. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Aporia Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_xK4X7s8PmKOy9iRpjDUr4oudy86jlYzJmpsm9w0q/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Aporia capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "aporia-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_xK4X7s8PmKOy9iRpjDUr4oudy86jlYzJmpsm9w0q/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions Aporia owners ask.

  • 01

    Can my AI agent check for PII vulnerabilities in my conversation logs?

    Yes. Provide a message context and prompt the agent to validate guardrails for a specific Aporia project. It will query the Aporia rules engine and return actionable insights immediately. ensuring that your outputs remain safe and compliant before deployment.

  • 02

    How quickly can I review data drift alerts triggered over the weekend?

    In seconds. During your Monday stand-up, ask your AI agent to fetch metrics for your primary model and list its monitors. The agent will pull up statistical variations and active alerts directly into your chat, saving you from navigating complex visual dashboards when you need a quick situational report.

  • 03

    If a monitor seems stuck, can the agent force its execution?

    Absolutely. If you suspect an anomaly, ask the agent to manually trigger the specific monitor ID. Instead of scheduling a redundant pipeline, the agent hits the Aporia backend to force a run, ensuring your MLOps workflow isn't blocked by cadence limitations.

Explore

More in Fort Knox

Suggestions