workspace/skills/snmptrap-receiver/SKILL.md
Receive and query SNMP traps from network devices via UDP.
npx skillsauth add automateyournetwork/netclaw snmptrap-receiverInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Receive and query SNMP traps from network devices via UDP.
snmptrap-receiver
This skill enables NetClaw to receive SNMP traps from network devices (routers, switches, firewalls) and query the collected data. It supports SNMPv1, SNMPv2c, and SNMPv3 trap formats.
snmptrap-mcp
| Tool | Purpose |
|------|---------|
| snmptrap_start_receiver | Start listening for SNMP traps |
| snmptrap_stop_receiver | Stop the receiver |
| snmptrap_get_status | Check receiver status and statistics |
| snmptrap_query | Search traps with filters |
| snmptrap_get_trap | Get full details of a specific trap |
| snmptrap_get_counts | Get trap counts by type and source |
1. Use snmptrap_start_receiver with port 10162
2. Configure network devices to send traps to this port
3. Use snmptrap_get_status to verify traps are being received
1. Use snmptrap_query with trap_oid_prefix "1.3.6.1.6.3.1.1.5" for standard traps
2. Filter by source_ip to focus on specific device
3. Use snmptrap_get_trap for full variable binding details
1. Use snmptrap_get_counts to see trap distribution
2. Focus on linkDown, authenticationFailure counts
3. Query high-frequency trap sources for details
The snmptrap-mcp server is configured via environment variables:
SNMPTRAP_PORT: UDP listening port (default: 162)SNMPTRAP_BIND_ADDRESS: Bind address (default: 0.0.0.0)SNMPTRAP_RETENTION_HOURS: Trap retention (default: 24)SNMPTRAP_RATE_LIMIT: Max traps/second (default: 1000)SNMPTRAP_DEDUP_WINDOW: Dedup window in seconds (default: 5)syslog-receiver - Syslog message collectionipfix-receiver - Flow data collectiongnmi-telemetry - Streaming telemetrytesting
Human-in-the-loop escalation via HumanRail — route low-confidence agent decisions, pre-destructive operation approvals, and ambiguous incident tickets to real human engineers. Human answers are verified and returned as structured output. Workers are paid via Lightning Network. Use when the agent is uncertain, when a destructive change needs explicit human sign-off beyond a ServiceNow CR, or when an ambiguous ticket requires human triage before automated handling.
testing
Manage EVE-NG node lifecycle. Use when listing nodes, checking runtime state, creating or deleting nodes, starting or stopping nodes or whole labs, verifying node details, or wiping node NVRAM back to factory defaults.
development
Manage EVE-NG labs and platform inventory. Use when listing labs, checking lab metadata, creating or deleting labs, importing or exporting lab archives, checking EVE-NG health or auth, or verifying available node images before build work.
tools
Execute live CLI commands on running EVE-NG nodes over telnet console. Use when running show commands, making live config changes, verifying protocol state, testing connectivity, checking console readiness, or interacting with IOS, Junos, VPCS, EOS, or NX-OS nodes.