AMAgentOps MCP Server
Last updated December 15, 2024
About AgentOps MCP Server
An MCP server that lets AI assistants query AgentOps traces and spans for debugging and observability.
AgentOps MCP Server is an open-source Model Context Protocol implementation that exposes AgentOps observability data to AI assistants and IDEs. It enables natural language access to trace and span information, helping developers debug AI agents with contextual insights during conversations. The server provides tools for authentication, retrieving trace details, inspecting spans, and fetching complete trace data. It integrates with Claude Desktop, Cursor, and other MCP-compatible environments, allowing developers to monitor and analyze AI agent behavior seamlessly. Authentication is handled via project API keys, and configuration is supported with npx, Cursor deeplinks, or Smithery for one-click installs.
Key features
- Authenticate with AgentOps API key
- Retrieve trace details by trace ID
- Inspect span attributes and metrics
- Fetch complete trace information with associated spans
- Compatible with Claude Desktop, Cursor, and Smithery installs
- Environment-based configuration
- Secure, project-specific access
- Mirrors AgentOps Public API as MCP tools
Related tools
MCP server for Sentry integration, enabling AI assistants to access error tracking, issue management, and debugging workflows.
A browser monitoring and interaction MCP server that enables AI tools to capture, analyze, and interact with browser activity.
An MCP server that connects AI assistants with SigNoz observability data for metrics, alerts, dashboards, and service monitoring.
An MCP server that autonomously evaluates web applications through browser automation, console logs, and UX reports.
An MCP server that connects AI assistants with Axiom datasets via Axiom Processing Language (APL).
