Overview
Use these guides when you need practical steps for understanding local AI agent usage on an endpoint. They focus on inventorying what is present, confirming what Beacon can observe, and investigating runtime activity once events are flowing.Which Guide Should I Use?
Inventory Local Agent Runtimes
Find installed runtimes, MCP servers, local configs, hooks, OTLP settings, and observed coverage.
Investigate Agent Runtime Activity
Inspect prompts, tools, commands, approvals, MCP activity, file changes, and forwarding readiness.
Fast Triage
Use these pages to answer:- What is installed? Use Inventory Local Agent Runtimes.
- What can the agent access? Check MCP server and config inventory.
- What happened? Use Investigate Agent Runtime Activity.
- Can I forward this? Validate the runtime log, then use Log Forwarding.
Setup
Before following these guides, install Beacon and configure endpoint telemetry:Configure endpoint telemetry
Sample output
Sample output
Sample output
Key Features Demonstrated
- Discover installed and configured local agent runtimes.
- Inspect MCP servers, hooks, OTLP settings, and runtime config files.
- Confirm whether supported runtimes have produced Beacon events.
- Move from local investigation to forwarding-ready event streams.