AgentOps
This MCP server provides access to AgentOps observability and tracing data for debugging AI agent runs, enabling retrieval of project information, trace details, span metrics, and complete execution traces through authenticated API access. Built using TypeScript with the Model Context Protocol SDK and Axios for HTTP requests, it features automatic authentication via environment variables, JWT token management, comprehensive trace analysis with nested span data, and data cleaning utilities to filter empty values from API responses. The implementation supports both individual trace/span lookups and complete trace reconstruction with all child spans and metrics, making it valuable for debugging complex AI agent workflows, analyzing performance bottlenecks, understanding execution patterns, and building AI assistants that need programmatic access to observability data without manual AgentOps dashboard navigation.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/agentops-ai/agentops-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve AgentOps from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.