> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.merge.dev/merge-agent-handler/observe/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.merge.dev/_mcp/server.

# Observe

> Build once. Connect to every API, tool, and LLM. Ship products and agents to production without owning the integration stack.

## Docs

- [Tool Call Logs](https://docs.merge.dev/merge-agent-handler/observe/tool-call-logs.md): What's in the Agent Handler Tool Call Logs, how to filter them, and how to debug a failure end to end from the dashboard.
- [API Request Logs](https://docs.merge.dev/merge-agent-handler/observe/api-request-logs.md): What's captured in API Request Logs, when they're useful, and how they relate to Tool Call Logs.
- [Stream logs to a SIEM](https://docs.merge.dev/merge-agent-handler/observe/stream-logs-to-a-siem.md): Set up your SIEM or observability platform to retrieve Agent Handler logs from the public log endpoints, with verified step-by-step instructions per platform.
- [Audit Trail](https://docs.merge.dev/merge-agent-handler/observe/audit-trail.md): What's in the Agent Handler Audit Trail: event catalog, retention, CSV export, and how to use it for compliance.
- [Webhooks](https://docs.merge.dev/merge-agent-handler/observe/webhooks.md): How to receive outbound webhooks from Agent Handler, verify signatures, handle failed deliveries, and the full event catalog.
- [Playground](https://docs.merge.dev/merge-agent-handler/observe/playground.md): How to use the in-app Agent Handler playground to chat with a Tool Pack as a specific Registered User, with deep-link export to your IDE.