An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Agentops Agent Telemetry And Monitoring to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Pinpoint bottlenecks and track costs in real time.

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

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 4 capabilities

We ship only the actions that matter.

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

Real work

What teams actually run

01

Debugging a failed agent run

An agent fails mid-task. You use this MCP to retrieve the full trace and inspect the last few spans to see if the failure was due to a bad capability input or an LLM hallucination.

02

Cost optimization review

You need to prove the value of an agent. You use this MCP to pull metrics and token costs for a week's worth of runs, optimizing your budget.

03

Performance bottleneck analysis

The agent is slow. You use this MCP to compare the timing of different spans, determining if the delay is in the external capability call or the LLM processing time.

04

Project setup verification

Before deployment, you use this MCP to confirm the correct project details are linked to your API key, ensuring all telemetry data goes to the right place.

Automate a task

Put AgentOps to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

AgentOps works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put AgentOps to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

864ms average. Fast in production.

AgentOps is checked daily against the live service.

Daily averagePeak 1044ms
Oct 3Today
Fastest day
655ms
Slowest day
1044ms
14-day trend
Slowing+8%

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

Guided setup for Claude? Set up AgentOps in Claude and other AIs

See all the AI clients this connector works with ↑

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.

  • 05

    How can I check the token usage and cost for a specific agent execution?

    You can use the get_trace_metrics capability by providing the specific Trace ID. It will return detailed data on token counts and the calculated financial cost for that execution.

  • 06

    Can I see the details of a single step within a larger trace?

    Yes! Use the get_span capability with the specific Span ID. This allows you to isolate and inspect individual operations, such as a single capability call or a specific LLM completion.

  • 07

    How do I verify which AgentOps project is currently active?

    Simply run the get_project capability. It retrieves the metadata and configuration details of the project associated with your current API key.

Explore

More in Developer Tools

Suggestions

Connect AgentOps to Claude, Cursor, ChatGPT & more