MCP For Claude Marketplace
AgentOps (Agent Telemetry and Monitoring)

AgentOps (Agent Telemetry and Monitoring) MCP Connector for Claude

A+

Monitor and observe your AI agents with AgentOps — track traces, spans, and project metrics directly from your agent.

4 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect AgentOps to your AI agent for comprehensive telemetry and observability of your agentic workflows. Gain deep insights into how your agents perform, identify bottlenecks, and track costs in real-time.

What you can do

  • Project Insights — Retrieve high-level details about your current AgentOps project associated with your API key using get_project.
  • Trace Analysis — Inspect specific execution traces with get_trace to understand agent behavior, decision-making, and flow.
  • Cost & Token Monitoring — Use get_trace_metrics to get detailed metrics for specific traces, including token usage counts and associated costs.
  • Granular Span Inspection — Drill down into individual spans within a trace using get_span for deep debugging of specific tool calls or LLM interactions.

How it works

  1. Subscribe to this server
  2. Enter your AgentOps API Key
  3. Start monitoring your agent's performance from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI Engineers — Debug complex agentic loops and identify exactly where a process failed or slowed down.
  • Product Managers — Monitor token costs and usage patterns across agent deployments to optimize ROI.
  • DevOps Teams — Ensure the reliability and observability of production AI agents with structured telemetry data.
telemetryobservabilityai-agentstracingmonitoring

4 tools expose this connector's capabilities to your AI agent.

get_trace_metrics

Get metrics for a specific trace

get_trace

Get details for a specific trace

get_project

Get AgentOps project details

get_span

Get details for a specific span

See how to talk to your AI agent using AgentOps (Agent Telemetry and Monitoring).

Get the details for my current AgentOps project.

I've retrieved your project details. Your current project is 'Production-Agent-v2' (ID: ao_proj_882). It is currently active and receiving telemetry data.

Show me the metrics and token costs for trace ID trace_abc123.

For trace trace_abc123, the total token count was 1,450 (800 prompt, 650 completion) with an estimated cost of $0.028. The execution took 4.2 seconds across 5 spans.

Inspect the details of span ID span_998877.

Span span_998877 was a 'tool_call' to 'web_search'. It started at 10:05:02 and finished at 10:05:04. Input parameters included 'query: agent observability' and it returned 3 search results.

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

Related Connectors

Execution Trace Recorder and Validator

Execution Trace Recorder and Validator MCP

3 tools Official

Records and validates agent execution traces to ensure integrity, determinism, and performance.

A+ View details →
Octoboard

Octoboard MCP

12 tools Official

Build client-facing marketing reports automatically by pulling data from Google, Facebook, HubSpot, and 50 other integrations.

A+ View details →
Digital Turbine

Digital Turbine MCP

10 tools Official

Equip your AI agent to manage mobile growth campaigns, track app monetization, and monitor performance via the Digital Turbine API.

A+ View details →
Execution Trace Tamper-Evident Logger

Execution Trace Tamper-Evident Logger MCP

3 tools Official

Creates immutable, cryptographic audit trails for agent execution steps using Merkle trees.

A+ View details →