Agentops MCP Server

MCP index access to the AgentOps Public API.

Local serverstdio

What is the Agentops MCP MCP server?

MCP index access to the AgentOps Public API. Exposed over MCP by the agentops mcp mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

The AgentOps MCP server provides access to observability and tracing data for debugging complex AI agent runs. This adds crucial context about where the AI agent succeeds or fails.

Its toolset

Everything the assistant can do here goes through one of these:

  • auth — Authorize using an AgentOps project API key and return JWT token
  • get_trace — The get_trace tool exposed by this server
  • get_span — The get_span tool exposed by this server
  • get_complete_trace — Get comprehensive trace information including all spans and their metrics

Configuration

You will need one environment variable: AGENTOPS_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Node.js >= 18.0.0 - AgentOps API key (passed as parameter to tools)

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at @smithery/cli on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Agentops MCP's toolset — auth, get_trace, get_span and 1 more — is a fair guide to whether it matches your workflow. It is maintained by AgentOps-AI; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Agentops MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the agentops mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
authAuthorize using an AgentOps project API key and return JWT token.
get_traceThe get_trace tool exposed by this server.
get_spanThe get_span tool exposed by this server.
get_complete_traceGet comprehensive trace information including all spans and their metrics.

How to install the Agentops MCP MCP server

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

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Node.js >= 18.0.0 - AgentOps API key (passed as parameter to tools)
VariableDescriptionRequired
AGENTOPS_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Agentops MCP to auth.
  • Use Agentops MCP to get trace.
  • Use Agentops MCP to get span.

Frequently asked questions

It connects Agentops MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (auth, get_trace, get_span, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agentops MCP directly.