workspace/skills/multivendor-fleet-ops/SKILL.md
# Multivendor Fleet Ops Ask one question of many devices at once — across mixed vendors — and get per-device answers. **MCP server:** `multivendor-cli-mcp` · **Tools:** `run_fleet`, `get_facts` ## `run_fleet` `target` is a group name, a comma-separated device list, or `all`. Supply exactly one of: - `command` — raw CLI, only for platforms this server owns - `getters` — NAPALM normalized facts, permitted read-only on any platform ``` run_fleet(target="edge", getters=["get_facts","get_interf
npx skillsauth add automateyournetwork/netclaw workspace/skills/multivendor-fleet-opsInstall 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.
Ask one question of many devices at once — across mixed vendors — and get per-device answers.
MCP server: multivendor-cli-mcp · Tools: run_fleet, get_facts
run_fleettarget is a group name, a comma-separated device list, or all. Supply exactly one of:
command — raw CLI, only for platforms this server ownsgetters — NAPALM normalized facts, permitted read-only on any platformrun_fleet(target="edge", getters=["get_facts","get_interfaces"])
run_fleet(target="srl1,srl2", command="show version")
requested always equals returned. Every targeted device appears, including failures. A
silently absent device would read as success, which is the most dangerous possible output for a fleet
query — you'd scan the list and see no problem where there is one.
summary counts by status. One device failing never aborts the others.
Defaults: 10 concurrent workers, 30s per-device timeout, both overridable. Ten rather than Nornir's own 20 because each worker holds an SSH session and devices commonly cap concurrent management sessions at 5–15.
get_facts returns one shape across vendors, which no other NetClaw server can do. pyATS and
junos-mcp each answer well for their own platform, but their shapes differ, so a question spanning
vendors otherwise needs reconciling by hand.
Where a platform has no NAPALM driver — SR Linux, FRR, VyOS, MikroTik — you get a row with
available: false and a gap_reason, not a missing row. That distinction is deliberate: "this
platform cannot tell us" and "there are none" are different answers, and conflating them produces a
wrong one. provenance is never faked as napalm for scraped output.
Verified live: get_facts across IOS-XE and SR Linux returns rows with identical keys — one is data,
one is a reported gap.
netmiko also drives Fortinet, Palo Alto PAN-OS and Check Point, so this server gives CLI-level reach to them today. That is not equivalent to their dedicated API integrations:
| Vendor | What CLI gives you | What it does NOT give you | |---|---|---| | Fortinet | FortiOS CLI reads | FortiManager policy packages, ADOM model, install preview | | Palo Alto | PAN-OS CLI reads | Panorama device groups, templates, commit validation | | Check Point | GAiA CLI reads | Management API policy layers, threat intel |
Roadmap items R3 (Fortinet) and R4 (Palo Alto) are still needed. Do not treat CLI reach as completing them.
tools
Zoom meeting intelligence — correlates a live or referenced Zoom meeting discussion against NetClaw's historical meeting record (via the official Zoom Meetings MCP) and today's actual network state. Use when someone in a Zoom meeting references a past discussion or incident ('didn't we have this issue before?'), or asks to search prior meetings for a topic. Does not itself recognize live in-meeting questions — that happens automatically inside zoom-rtms-mcp's own extractor (spec 118) before this skill is ever invoked.
tools
Manage Lantronix out-of-band (OOB) infrastructure via Percepxion central management platform: device inventory, serial port inspection via SLC CLI, firmware compliance, config management, security auditing, and closed-loop incident remediation. Use during outages, maintenance windows, compliance cycles, and AI-assisted automation workflows.
tools
Federate your NetClaw with other NetClaw operators over the BGP mesh — exchange capability inventories and ask your claw what a peer can do. (US1; remote invocation and chat land in later phases.)
tools
Track token consumption, enforce session budgets, and display cost for every NetClaw interaction.