mcpField
A
Agentops Mcp

Agentops Mcp

Local
github.com/AgentOps-AIDeveloper Tools14Updated 67w ago
Repository

About Agentops Mcp

AgentOps MCP is a server for developers investigating AI agent runs. It provides access to AgentOps traces, spans, and trace metrics to help identify where a run succeeds or fails.

Key features

  1. 01Authenticate with an AgentOps project API key
  2. 02Retrieve traces by ID
  3. 03Retrieve spans by ID
  4. 04View traces with spans and metrics

Use cases

  1. 01Inspect a specific agent run trace
  2. 02Review an individual span during debugging
  3. 03Examine trace metrics to locate failures

MCP support

Exposes AgentOps authentication and trace-inspection tools to MCP clients. Tools retrieve traces, spans, and complete trace data with metrics.

#observability#tracing#ai#agents

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "agentops": {
      "command": "npx",
      "args": [
        "-y",
        "agentops-mcp"
      ],
      "env": {
        "AGENTOPS_API_KEY": "<AGENTOPS_API_KEY>"
      }
    }
  }
}
Run commandnpx -y agentops-mcp
Environment variables to set
AGENTOPS_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmagentops-mcp

Tools

4

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
api_keystringNoAgentOps project API key (optional if AGENTOPS_API_KEY environment variable is set)

Details

From the project README

AgentOps MCP Server

smithery badge

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.

Usage

MCP Client Configuration

Add the following to your MCP configuration file:

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

Installation

Installing via Cursor Deeplink

Install MCP Server

Installing via Smithery

To install agentops-mcp for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @AgentOps-AI/agentops-mcp --client claude
Local Development

To build the MCP server locally:

# Clone and setup
git clone https://github.com/AgentOps-AI/agentops-mcp.git
cd mcp
npm install

# Build the project
npm run build

# Run the server
npm pack

Available Tools

auth

Authorize using an AgentOps project API key and return JWT token.

Parameters:

  • api_key (string): Your AgentOps project API key
get_trace

Retrieve trace information by ID.

Parameters:

  • trace_id (string): The trace ID to retrieve
get_span

Get span information by ID.

Parameters:

  • span_id (string): The span ID to retrieve
get_complete_trace

Get comprehensive trace information including all spans and their metrics.

Parameters:

  • trace_id (string): The trace ID

Requirements

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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.