SkillFoxx

Type a name, a task or a service

AgentOps MCP Server

AgentOps MCP server: the agent reads traces and spans of agent runs to find where they failed

MCP serverMedium risk

agentops-ai/agentops-mcpAuthor: AgentOps

Install

{
    "mcpServers": {
        "agentops-mcp": {
            "command": "npx",
            "args": ["agentops-mcp"],
            "env": {
              "AGENTOPS_API_KEY": ""
            }
        }
    }
}

Fill in your AgentOps project key.

This is third-party code. Review the repository files before installing.

What it does

The server gives the agent access to AgentOps observability data. The auth tool exchanges a project key for a token, get_trace and get_span return a single trace or span, and get_complete_trace returns a full trace with all spans and metrics. This lets the agent inspect a failed run of another agent and explain which step broke.

Who it is for. For agent developers who already send telemetry to AgentOps.

Good fit when

  • You need to inspect the trace of a failed agent run
  • You need to compare span metrics within one trace

Not a fit when

  • Agent telemetry is not collected in AgentOps
  • You need to search traces by criteria; the server works only with known IDs

Example request

Open trace 7f3a... in AgentOps and tell me at which step the agent failed

Limitations

Requires an AgentOps account, a project key and Node.js 18+. There are only four read-only tools and you need the trace ID. The repository has not changed in over a year.

How to disable. Remove the agentops-mcp block from the client's MCP config.

MCP

Transport
stdio
Authentication
API key
Environment variables
AGENTOPS_API_KEY
required, secret		AgentOps project API key

Security check

  • Calls the AgentOps API with a project key
  • Traces may contain prompts and responses with user data

README in short

The README shows an MCP config running via npx with AGENTOPS_API_KEY, a Cursor deeplink and Smithery install for Claude Desktop. It documents four tools with parameters: auth, get trace, get span and get complete trace. Local build steps are included.

FAQ

Does the server change data in AgentOps?

No, all tools only read traces and spans.

Editors’ pick

Open-source personal AI assistant on your own machine: answers in Telegram, Slack, Discord and WhatsApp, extended with skills and plugins

CLIHigh risk389.7K
Editors’ pick

A self-improving agent from Nous Research with a TUI, messaging gateway, cron jobs and skills it writes itself

CLIHigh risk245.6K
Editors’ pick

An open source coding agent for the terminal and desktop with build and plan modes

CLIHigh risk207.4K
Editors’ pick

Open prompt library with a Claude Code plugin, MCP server and CLI: search, fetch and improve prompts and skills from an agent

PluginMedium risk170.4K