AgentOps API MCP Server logo

AgentOps API MCP Server

by AgentOps-AI

The AgentOps API MCP Server allows LLM agents to interact with the AgentOps API for accessing trace data. It provides tools for agents to list recent traces and get detailed information about specific traces.

View on GitHub

Last updated: N/A

What is AgentOps API MCP Server?

This MCP server acts as a bridge between LLM agents and the AgentOps API, enabling agents to access and analyze trace data from their AgentOps projects. It handles authentication and communication, providing a secure and convenient way for agents to understand and debug their behavior.

How to use AgentOps API MCP Server?

The server can be used with Claude Coder by configuring the config.yaml file with the server's path. Alternatively, it can be run standalone using the provided run-server script or directly with Python. Agents interact with the server through tool calls, providing their AgentOps API key and any necessary parameters.

Key features of AgentOps API MCP Server

  • Secure authentication using JWT tokens

  • Provides tools for listing and retrieving trace details

  • Supports custom API URLs for non-production environments

  • Stateless design for security and scalability

Use cases of AgentOps API MCP Server

  • Debugging LLM agent behavior

  • Analyzing trace data to identify performance bottlenecks

  • Monitoring agent activity and resource usage

  • Integrating AgentOps tracing into LLM workflows

FAQ from AgentOps API MCP Server

How does the server handle authentication?

The server uses a two-step authentication process: the agent provides their API key, which the server exchanges for a JWT token from the AgentOps API. This token is then used for all subsequent requests.

What tools are available to agents?

The server provides two main tools: list_traces for listing recent traces and trace_detail for retrieving detailed information about a specific trace.

Can I use a custom API URL?

Yes, agents can override the default AgentOps API URL on a per-request basis using the AGENTOPS_API_URL parameter.

How do I use this server with Claude Coder?

You need to configure Claude Coder by adding the server's path to your config.yaml file under the mcp_servers section.

Is any user data stored on the server?

No, the server is stateless and does not store any user data between requests.