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

Use AgentOps with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Pinpoint bottlenecks and track costs in real time.

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 · 4 capabilities

The complete AgentOps capability set.

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

Capability set01 / 01

01-04

4 capabilities in this set.

Part of 4 available through AgentOps.

  1. 01

    Get trace metrics

    Get metrics for a specific trace

  2. 02

    Get trace

    Get details for a specific trace

  3. 03

    Get project

    Get AgentOps project details

  4. 04

    Get span

    Get details for a specific span

Observed, not estimated

867ms average. Fast in production.

AgentOps is checked daily against the live service.

Daily averagePeak 1184ms
Aug 20Today
Fastest day
679ms
Slowest day
1184ms
14-day trend
Slowing+30%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 4 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 AgentOps, so you can see the experience inside your AI.

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

AgentOps Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_OCln8CM8I7G7rNCo6QKijZPwPeMGY7W7gj6qBqEG/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 — AgentOps capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "agentops-agent-telemetry-and-monitoring-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_OCln8CM8I7G7rNCo6QKijZPwPeMGY7W7gj6qBqEG/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

Who it's for

Built for the work AgentOps owners hand off.

If you build AI agents, you need to know exactly how they run. This MCP is built for engineers who debug complex agentic loops, product managers who track usage costs, and DevOps teams who need reliable, structured telemetry data for production systems.

  • 01

    AI Engineers

    Debugging complex agentic loops and finding exactly where a process failed or slowed down.

  • 02

    Product Managers

    Monitoring token costs and usage patterns across agent deployments to manage budget and ROI.

  • 03

    DevOps Teams

    Ensuring the reliability and observability of production AI agents with structured telemetry data.

FAQ

Questions AgentOps owners ask.

  • 01

    What kind of data does this MCP provide?

    It provides structured telemetry data, including execution traces, individual spans, token usage counts, and associated costs. You get a complete picture of the agent's performance, not just a simple pass/fail status.

  • 02

    Can I track costs with this MCP?

    Yes. You use the get_trace_metrics capability to get detailed metrics for a specific trace. This includes the total token count and the estimated dollar cost for that run.

  • 03

    Is this for all AI agents?

    This MCP is designed for any agentic workflow that generates standard telemetry data. It lets you observe how your agents perform, regardless of the underlying model or framework.

  • 04

    How do I debug a specific capability call?

    You use the get_span capability. This allows you to drill down into the details of a single span, giving you the exact input parameters and timing for that specific capability interaction.

Explore

More in Developer Tools

Suggestions