Agentops MCP

🚀 AgentOps MCP Server

The AgentOps MCP server offers access to observability and tracing data, which is invaluable for debugging complex AI agent runs. It provides crucial context regarding the success or failure points of the AI agent.

🚀 Quick Start

✨ Features

The AgentOps MCP server enables users to access observability and tracing data, helping them understand where AI agents succeed or fail during complex runs.

📦 Installation

Installing via Cursor Deeplink

You can install the MCP server by clicking the following link:

Installing via Smithery

To automatically install agentops - mcp for Claude Desktop via Smithery, use the following command:

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

Local Development

To build the MCP server locally, follow these steps:

# 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

💻 Usage Examples

Basic Usage

First, you need to configure the MCP client. Add the following to your MCP configuration file:

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

📚 Documentation

Available Tools

auth

Authorize using an AgentOps project API key and return a 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

🔧 Technical Details

Requirements

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