# AgentOps

> Use this tool when you need to debug AI agent runs and analyze performance bottlenecks through observability and tracing data. It provides access to project information, trace details, and execution traces via an authenticated API, accepting authentication credentials as input and returning detailed trace data as output. Ideal for use in complex AI workflows, AgentOps enables programmatic access to observability data for building and optimizing AI assistants.

Canonical page: https://skillsregistry.net/skills/agentops-ai-agentops  
JSON: https://api.skillsregistry.net/v1/skills/agentops-ai-agentops

## Description

This MCP server provides access to AgentOps observability and tracing data for debugging AI agent runs, enabling retrieval of project information, trace details, span metrics, and complete execution traces through authenticated API access. Built using TypeScript with the Model Context Protocol SDK and Axios for HTTP requests, it features automatic authentication via environment variables, JWT token management, comprehensive trace analysis with nested span data, and data cleaning utilities to filter empty values from API responses. The implementation supports both individual trace/span lookups and complete trace reconstruction with all child spans and metrics, making it valuable for debugging complex AI agent workflows, analyzing performance bottlenecks, understanding execution patterns, and building AI assistants that need programmatic access to observability data without manual AgentOps dashboard navigation.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/agentops-ai-agentops)
- **Repository:** <https://github.com/agentops-ai/agentops-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "agentops-ai-agentops"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/agentops-ai-agentops` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/agentops-ai-agentops/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt