AgentOps (Agent Telemetry and Monitoring) Connector for AI agents.
4 live capabilities
Track agent execution traces and monitor real-time token costs.
Waiting for input…
Why people use AgentOps (Agent Telemetry and Monitoring)
AgentOps for Real-Time AI Agent Observability
This Connector changes that by bringing the telemetry directly into your workflow. You can ask your agent to pull up a trace or a specific span, and the data appears instantly. You get a clear view of the logic flow and the exact moment a process stalled, letting you fix bugs in minutes instead of hours.
What Vinkius changes
You get instant visibility into your agent's internal logic and costs without leaving your workspace.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Debugging a failing loop
An AI Engineer notices an agent is stuck in a loop.
- Real-world use case 02
Budget auditing
A Product Manager wants to know the cost of a new feature.
- Real-world use case 03
Capability call inspection
A developer needs to see what parameters were sent to a search capability.
Complete set · 4capabilities
The complete AgentOps (Agent Telemetry and Monitoring) capability set.
These are the exact actions your AI can choose when you ask it to work with AgentOps (Agent Telemetry and Monitoring).
01—04
4 capabilities in this set.
Part of 4 available through AgentOps (Agent Telemetry and Monitoring).
- 01 Capability
Get trace metrics
Pull the specific token counts and dollar costs associated with a particular agentic trace. This provides clear data on your operational spend.
- 02 Capability
Get trace
Look up the full execution history of a specific agent run to see how it navigated a task. This helps you visualize the step by step logic flow.
- 03 Capability
Get project
Fetch the high-level details and status of your current AgentOps project. Use this to manage multiple environments and view project health.
- 04 Capability
Get span
Drill down into a single step, like a web search or a database write, to see the exact input and output. It isolates specific errors in capability calls.
Set up in minutes
One URL. Then ask AgentOps (Agent Telemetry and Monitoring) to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use AgentOps (Agent Telemetry and Monitoring) from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_OCln8CM8I7G7rNCo6QKijZPwPeMGY7W7gj6qBqEG/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it AgentOps (Agent Telemetry and Monitoring), and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable AgentOps (Agent Telemetry and Monitoring) for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_OCln8CM8I7G7rNCo6QKijZPwPeMGY7W7gj6qBqEG/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the AgentOps (Agent Telemetry and Monitoring) URL.
- Step 03
Save and start
Save the connection and enable AgentOps (Agent Telemetry and Monitoring) in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"agentops-agent-telemetry-and-monitoring": {
"url": "https://edge.vinkius.com/vk_preview_OCln8CM8I7G7rNCo6QKijZPwPeMGY7W7gj6qBqEG/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using AgentOps (Agent Telemetry and Monitoring)
Open Agent mode in chat and ask: "Using AgentOps (Agent Telemetry and Monitoring), help me...". 4 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"agentops-agent-telemetry-and-monitoring": {
"url": "https://edge.vinkius.com/vk_preview_OCln8CM8I7G7rNCo6QKijZPwPeMGY7W7gj6qBqEG/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using AgentOps (Agent Telemetry and Monitoring)
Ask Copilot: "Using AgentOps (Agent Telemetry and Monitoring), help me...". 4 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"agentops-agent-telemetry-and-monitoring": {
"url": "https://edge.vinkius.com/vk_preview_OCln8CM8I7G7rNCo6QKijZPwPeMGY7W7gj6qBqEG/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using AgentOps (Agent Telemetry and Monitoring)
Open Cascade and ask: "Using AgentOps (Agent Telemetry and Monitoring), help me...". 4 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"agentops-agent-telemetry-and-monitoring": {
"url": "https://edge.vinkius.com/vk_preview_OCln8CM8I7G7rNCo6QKijZPwPeMGY7W7gj6qBqEG/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using AgentOps (Agent Telemetry and Monitoring)
Ask Cline: "Using AgentOps (Agent Telemetry and Monitoring), help me...". 4 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add agentops-agent-telemetry-and-monitoring --transport http "https://edge.vinkius.com/vk_preview_OCln8CM8I7G7rNCo6QKijZPwPeMGY7W7gj6qBqEG/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using AgentOps (Agent Telemetry and Monitoring)
Ask Claude: "Using AgentOps (Agent Telemetry and Monitoring), show me...". 4 tools are ready
Where the request belongs
Work AgentOps can move forward.
This is for the engineers and managers who are tired of black box AI behavior and need hard data to prove their agents are actually working.
AI Engineer
Debugging a complex multi-step agent loop that keeps hanging on a specific capability call on a Tuesday afternoon.
Product Manager
Checking the actual token costs of a new feature to see if it stays within the quarterly budget.
DevOps Engineer
Monitoring the reliability and latency of production agents to ensure they don't crash under heavy load.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsLindy (Autonomous AI Employees)
Manage autonomous AI employees via Lindy. trigger task runs, monitor reasoning logs, and audit app integrations.
Langflow (Visual Multi-agent Orchestrator)
Orchestrate multi-agent AI workflows visually. execute flows, manage projects, and trigger webhooks directly from any AI agent.
AirOps
AI workflow orchestration. execute models, manage agents, and query memory via AI.
Datadog AI (LLM Observability)
Monitor LLM performance via Datadog. track token usage, audit prompts, and monitor AI model metrics directly from any AI agent.
AutoGen
Orchestrate Microsoft AutoGen multi-agent workflows. manage sessions, agent roles, workflows, and monitor execution logs from any AI agent.
LangGraph Cloud (Stateful AI Agents)
Orchestrate stateful AI agents via LangGraph Cloud. manage assistants, monitor conversation threads, and handle human-in-the-loop overrides.
Bring your own AI
Change the model, client or framework. Keep AgentOps connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about AgentOps.
The practical details behind the request, access and result.
What is AgentOps MCP for?
It's a capability that lets you see the "inner thoughts" and performance data of your AI agents. You get a clear view of how they make decisions and how much they cost to run.
How does AgentOps MCP help with costs?
It connects to your telemetry to pull specific token usage and dollar amounts for every agent run. This helps you spot expensive loops and manage your budget.
Can I use AgentOps MCP to debug my agent's logic?
Yes, it lets you pull up specific execution traces to see the exact path an agent took. You can see every capability call and step it performed.
How do I see specific capability interactions?
You can use the Connector to look at individual spans. This shows you the exact input and output for every single action your agent takes.
Is AgentOps MCP for production agents?
It's ideal for production because it provides the structured telemetry needed for reliable monitoring. You can track performance across your entire project.
Does AgentOps MCP show me my project details?
Yes, it can retrieve high-level information about your AgentOps projects, like their status and current activity.
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.
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.
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.
One connection away
Give your agent a direct line to AgentOps.
Connect AgentOps once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available