beginner⏱️ 12-22 minutes📅 Updated August 2026

Step-by-step guide to integrate AgentOps MCP server with oterm. Includes auth and get_trace.

AgentOps + oterm: Complete MCP Integration

AgentOps is a MCP server that Provide observability and tracing for debugging AI agents with AgentOps API..

When integrated with oterm, you can:

  • Authorize with AgentOps API key
  • Retrieve trace information by ID
  • Get span information by ID

This guide provides step-by-step instructions to set up AgentOps in oterm, including configuration, examples, and troubleshooting.

What You'll Achieve

After completing this setup:

  • AgentOps will be fully integrated and operational
  • You can use AgentOps tools directly in oterm
  • All AgentOps capabilities will be available for your workflows
  • Access to 4 different tools

Prerequisites

Before starting, ensure you have:

  • API key from AgentOps dashboard
  • oterm installed and configured
  • Compatible operating system (CLI (Terminal))

Installation

Step 1: Install AgentOps

Configuration

Step 2: Configure oterm

  1. Open oterm settings
  2. Navigate to MCP server configuration
  3. Add AgentOps server with appropriate settings
  4. Save and restart if needed

Examples

Once configured, you can use AgentOps in oterm:

Agent Performance Debugging

undefined

Ask oterm: "Show me traces for agent runs that failed today"

Expected Result: undefined

Cost Analysis

undefined

Ask oterm: "Get cost breakdown for trace abc123"

Expected Result: undefined

Performance Optimization

undefined

Ask oterm: "Show slowest spans in recent traces"

Expected Result: undefined

Testing Your Setup

  1. Launch oterm
  2. Verify AgentOps is available in the tools list
  3. Test basic AgentOps functionality

Troubleshooting

Common Issues

Connection Refused

Symptoms: Failed to connect to Ollama

Cause: Ollama service is not running

Solution:

  • Start Ollama with ollama serve
  • Check if Ollama is running on the default port (11434)

Tool Not Found

Symptoms: Model does not use the tool, Tool execution failed

Cause: MCP server not configured correctly or crashed

Solution:

  • Check the config.json for syntax errors
  • Verify the MCP server command works independently in the terminal
  • Ensure the model supports tool calling (e.g., llama3.1)

AgentOps not appearing in oterm

Symptoms: Server not listed, Tools not available

Cause: Configuration or installation issue

Solution:

  • Verify configuration syntax
  • Check AgentOps installation
  • Restart oterm
  • Check logs for error messages

Next Steps

Now that AgentOps is integrated with oterm:

  • Explore all AgentOps capabilities through oterm
  • Check out other MCP servers that work with oterm
  • Join the MCP community for tips and support
  • Consider contributing to AgentOps development

Need Help?

Related Resources

More Integrations

Explore other MCP servers that work with oterm

Need Help?

Join the MCP community for support and discussions

AgentOps + oterm: MCP Setup Guide (2026)