Cisco SD-WAN vManage read-only operations — fabric devices, WAN Edge inventory, templates, policies, alarms, events, interface stats, BFD sessions, OMP routes, control connections, running config.

Apache-2.0Auto-check: notes

Install Sdwan Ops

skills CLI
$ npx skills add automateyournetwork/netclaw --skill sdwan-ops -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install automateyournetwork/netclaw sdwan-ops --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/automateyournetwork/netclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/workspace/skills/sdwan-ops .claude/skills/sdwan-ops && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sdwan-ops
GitHub stars
676
Token cost
~1.7k tokens
SKILL.md length
563 words
Files
1
Skills in repo
120
Repo updated
First seen
Licence
Apache-2.0

At a glance

Cisco SD-WAN vManage read-only operations — fabric devices, WAN Edge inventory, templates, policies, alarms, events, interface stats, BFD sessions, OMP routes, control connections, running config.

  • Works in 7 steps: Fabric overview: get_devices — verify… → WAN Edge inventory:… → Alarms: get_alarms — identify active… → …
  • Checking SD-WAN fabric health
  • SKILL.md covers MCP Server, How to Call Tools, Available Tools (12) and Workflow: SD-WAN Fabric Health…, plus 6 more sections
  • Calls python3; needs VMANAGE_PASSWORD

What it does

Sdwan Ops is an agent skill from automateyournetwork/netclaw. Cisco SD-WAN vManage read-only operations — fabric devices, WAN Edge inventory, templates, policies, alarms, events, interface stats, BFD sessions, OMP routes, control connections, running config. Use when checking SD-WAN fabric health, viewing vManage alarms, auditing SD-WAN policies and templates, or troubleshooting BFD tunnels.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Model Context Protocol and Python. The repository describes itself as: An AI agent that claws through your network. The licence is Apache-2.0.

When your agent uses it

  • Checking SD-WAN fabric health
  • Viewing vManage alarms
  • Auditing SD-WAN policies and templates
  • Troubleshooting BFD tunnels

Example prompts

  • “/sdwan-ops”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Fabric overview: get_devices — verify all controllers and edges are reachable
  2. WAN Edge inventory: get_wan_edge_inventory — check serial numbers, versions
  3. Alarms: get_alarms — identify active issues (CRITICAL, MAJOR, MINOR)
  4. Control plane: get_control_connections for key devices — verify DTLS/TLS tunnels
  5. BFD health: get_bfd_sessions for key devices — check tunnel health
  6. Report: Fabric status summary with severity-sorted findings
  7. GAIT: Record all queries in audit trail

What it can do on your machine

Read from SKILL.md and the folder at commit aa90e7d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • VMANAGE_PASSWORD

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sdwan Ops loads about 1.7k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 563 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:126
    AME`, `VMANAGE_PASSWORD` in `~/.openclaw/.env`

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from automateyournetwork/netclaw at commit aa90e7d, republished under its Apache-2.0 licence (© automateyournetwork). 563 words, ~1,687 tokens.

Download SKILL.mdSave it as .claude/skills/sdwan-ops/SKILL.md (or your agent's skills folder).
name
sdwan-ops
description
Cisco SD-WAN vManage read-only operations — fabric devices, WAN Edge inventory, templates, policies, alarms, events, interface stats, BFD sessions, OMP routes, control connections, running config. Use when checking SD-WAN fabric health, viewing vManage alarms, auditing SD-WAN policies and templates, or troubleshooting BFD tunnels.
license
Apache-2.0
user-invocable
true

Cisco SD-WAN Operations

MCP Server

  • Source: siddhartha2303/cisco-sdwan-mcp
  • Command: python3 -u $SDWAN_MCP_SCRIPT --transport stdio (stdio transport)
  • Requires: VMANAGE_IP, VMANAGE_USERNAME, VMANAGE_PASSWORD environment variables
  • Python: 3.10+
  • Dependencies: fastmcp, requests, python-dotenv

How to Call Tools

bash
python3 $MCP_CALL "python3 -u $SDWAN_MCP_SCRIPT --transport stdio" <tool_name> '<args_json>'

Available Tools (12)

ToolParametersWhat It Does
get_devicesnoneList all fabric devices — vManage, vSmart, vBond, vEdge with status
get_wan_edge_inventorynoneWAN Edge details: serial number, chassis ID, model, version
get_device_templatesnoneAll device templates with attached device count
get_feature_templatesnoneAll feature templates (VPN, interface, routing, security)
get_centralized_policiesnoneCentralized policy definitions (traffic engineering, QoS, security)
get_alarmsnoneActive alarms across the fabric with severity
get_eventsnoneRecent audit events and operational logs
get_interface_statsdevice_ipInterface statistics for a specific device (throughput, errors, drops)
get_bfd_sessionsdevice_ipBFD session status for device-to-device connectivity health
get_omp_routesdevice_ipOMP routes — received and advertised routes per device
get_control_connectionsdevice_ipDTLS/TLS control connections between fabric nodes
get_running_configdevice_ipFull running configuration for a device

Workflow: SD-WAN Fabric Health Check

When a user asks about SD-WAN health or status:

  1. Fabric overview: get_devices — verify all controllers and edges are reachable
  2. WAN Edge inventory: get_wan_edge_inventory — check serial numbers, versions
  3. Alarms: get_alarms — identify active issues (CRITICAL, MAJOR, MINOR)
  4. Control plane: get_control_connections for key devices — verify DTLS/TLS tunnels
  5. BFD health: get_bfd_sessions for key devices — check tunnel health
  6. Report: Fabric status summary with severity-sorted findings
  7. GAIT: Record all queries in audit trail
Example: Fabric Health
bash
# List all fabric devices
python3 $MCP_CALL "python3 -u $SDWAN_MCP_SCRIPT --transport stdio" get_devices '{}'

# Check active alarms
python3 $MCP_CALL "python3 -u $SDWAN_MCP_SCRIPT --transport stdio" get_alarms '{}'

# Check BFD sessions on a WAN edge
python3 $MCP_CALL "python3 -u $SDWAN_MCP_SCRIPT --transport stdio" get_bfd_sessions '{"device_ip":"10.10.10.100"}'

# Check OMP routes on a WAN edge
python3 $MCP_CALL "python3 -u $SDWAN_MCP_SCRIPT --transport stdio" get_omp_routes '{"device_ip":"10.10.10.100"}'

Workflow: SD-WAN Policy Audit

When auditing SD-WAN templates and policies:

  1. Device templates: get_device_templates — list all templates with device counts
  2. Feature templates: get_feature_templates — inspect VPN, interface, routing, security templates
  3. Centralized policies: get_centralized_policies — review traffic engineering and security policies
  4. Config verification: get_running_config for target device — confirm template-applied config
  5. Report: Template and policy audit with recommendations
Example: Policy Audit
bash
# List device templates
python3 $MCP_CALL "python3 -u $SDWAN_MCP_SCRIPT --transport stdio" get_device_templates '{}'

# List centralized policies
python3 $MCP_CALL "python3 -u $SDWAN_MCP_SCRIPT --transport stdio" get_centralized_policies '{}'

# Get running config for a specific device
python3 $MCP_CALL "python3 -u $SDWAN_MCP_SCRIPT --transport stdio" get_running_config '{"device_ip":"10.10.10.100"}'

Workflow: SD-WAN Troubleshooting

When investigating SD-WAN connectivity or performance:

  1. Device status: get_devices — is the device reachable via vManage?
  2. Control connections: get_control_connections — DTLS/TLS tunnel state
  3. BFD sessions: get_bfd_sessions — tunnel health between sites
  4. OMP routes: get_omp_routes — are routes being exchanged?
  5. Interface stats: get_interface_stats — throughput, errors, drops
  6. Events: get_events — recent operational events for timeline correlation
  7. Running config: get_running_config — verify configuration matches intent
Show full SKILL.md (202 more words)Show less

Integration with Other Skills

SkillIntegration
pyats-networkCLI-level verification of SD-WAN edge devices via SSH
gait-session-trackingRecord all vManage queries in GAIT audit trail
markmap-vizVisualize SD-WAN fabric topology as mind map
uml-diagramGenerate SD-WAN architecture diagrams (nwdiag, sequence)
servicenow-change-workflowReference SD-WAN audit findings in CRs

Important Rules

  • All operations are read-only — no configuration changes can be made through this MCP server
  • GAIT audit mandatory — record all vManage queries in the session audit trail
  • Cross-reference with pyATS — use CLI-level verification alongside vManage API data for complete visibility
  • SSL verification — vManage API uses HTTPS; SSL certificate warnings are suppressed by the MCP server for lab/self-signed certs
  • API rate limits — vManage may rate-limit API requests; avoid rapid polling

Error Handling

  • Auth fails (401/403): Check VMANAGE_IP, VMANAGE_USERNAME, VMANAGE_PASSWORD in ~/.openclaw/.env
  • Connection timeout: Verify vManage is reachable from the NetClaw host (ping $VMANAGE_IP)
  • Device IP not found: Use get_devices to list all devices and find correct system IP
  • Empty results: Device may not be onboarded or may be unreachable from vManage

Environment Variables

  • VMANAGE_IP — vManage IP address or hostname
  • VMANAGE_USERNAME — vManage API username
  • VMANAGE_PASSWORD — vManage API password
  • SDWAN_MCP_SCRIPT — Path to the Python MCP server script (set by install.sh)
  • MCP_CALL — Path to mcp-call.py wrapper (set by install.sh)

© automateyournetwork, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in workspace/skills/sdwan-ops of automateyournetwork/netclaw.

Open the folder on GitHubat commit aa90e7d

Compare with similar skills

Sdwan Ops next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sdwan Ops compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sdwan Ops this skillautomateyournetwork/netclaw676—~1.7kAutomated safety check: NotesApache-2.0
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MemPalace Setup and OperationMemPalace/mempalace59k—~2.2kAutomated safety check: PassMIT
LangBot Plugin Developmentlangbot-app/LangBot18k—~3.9kAutomated safety check: PassApache-2.0
Vexor CLIscarletkc/vexor2443 repos~1.2kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.

    59k GitHub stars~2.2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • LangBot Plugin Development

    langbot-app/LangBot

    Guides building, debugging and testing LangBot plugins: components, SDK calls, README and locale rules, SDK pitfalls and WebSocket-based testing.

    18k GitHub stars~3.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Vexor CLI

    scarletkc/vexor

    Semantic file discovery via vexor. An agent skill from scarletkc/vexor.

    244 GitHub starsUsed in 3 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed
  • Google Antigravity SDK

    google-antigravity/antigravity-sdk-python

    Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK.

    3.7k GitHub stars~2.1k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check: notes

More from automateyournetwork/netclaw

All 120 skills in this repo
  • EVE-NG Lab Topology Design

    automateyournetwork/netclaw

    Entry point for designing EVE-NG network labs: classifies the request, gathers missing requirements, proposes options and validates the resulting topology.

    676 GitHub stars~612 tokensUpdated today
    Auto-check passed
  • ACI Policy Change Deployment

    automateyournetwork/netclaw

    Deploys Cisco ACI policy changes only behind an approved ServiceNow Change Request, capturing pre and post-change fault baselines and rolling back automatically on a fault delta.

    676 GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • Cisco ACI Fabric Health Audit

    automateyournetwork/netclaw

    Runs a phased health audit of a Cisco ACI fabric through MCP tools: node status, links, tenant and policy review, faults and endpoint learning.

    676 GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Anta Validation

    automateyournetwork/netclaw

    Validate Arista EOS network state against ANTA's pre-built 208-test catalogue, with structured pass/fail verdicts.

    676 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Arista Cvp

    automateyournetwork/netclaw

    Arista CloudVision Portal (CVP) automation via REST API — device inventory, events, connectivity monitoring, tag management (4 tools).

    676 GitHub stars~2.2k tokensUpdated today
    Auto-check: notes
  • AWS Cloud Monitoring

    automateyournetwork/netclaw

    AWS CloudWatch monitoring — metrics, alarms, log queries, VPC flow log analysis, network performance.

    676 GitHub stars~1k tokensUpdated today
    Auto-check passed

Questions about Sdwan Ops

What does Sdwan Ops do?

Cisco SD-WAN vManage read-only operations — fabric devices, WAN Edge inventory, templates, policies, alarms, events, interface stats, BFD sessions, OMP routes, control connections, running config. Sdwan Ops is an agent skill from automateyournetwork/netclaw. Cisco SD-WAN vManage read-only operations — fabric devices, WAN Edge inventory, templates, policies, alarms, events, interface stats, BFD sessions, OMP routes, control connections, running config.

When should I use Sdwan Ops?

Sdwan Ops fits situations like: checking SD-WAN fabric health; viewing vManage alarms; auditing SD-WAN policies and templates; troubleshooting BFD tunnels.

How do I install Sdwan Ops in Claude Code?

Run `npx skills add automateyournetwork/netclaw --skill sdwan-ops -a claude-code`. Or copy the skill folder (workspace/skills/sdwan-ops in automateyournetwork/netclaw) into .claude/skills/sdwan-ops in your project. Claude Code loads it when a task matches its description.

How do I install Sdwan Ops in Codex?

Run `npx skills add automateyournetwork/netclaw --skill sdwan-ops -a codex`. Or copy the skill folder (workspace/skills/sdwan-ops in automateyournetwork/netclaw) into .agents/skills/sdwan-ops in your project. Codex loads it when a task matches its description.

Can I use Sdwan Ops in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add automateyournetwork/netclaw --skill sdwan-ops -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sdwan-ops, .gemini/skills/sdwan-ops, .github/skills/sdwan-ops and .opencode/skills/sdwan-ops in your project.

What does Sdwan Ops need to run?

Going by SKILL.md and its folder, Sdwan Ops needs the command-line tools its instructions call (python3) and credentials named VMANAGE_PASSWORD. Our summary lists: Python 3.

Does Sdwan Ops access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Sdwan Ops safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Sdwan Ops use?

Sdwan Ops is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sdwan Ops use?

About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sdwan Ops?

Skills that share tags, products or a category with Sdwan Ops: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MemPalace Setup and Operation (MemPalace/mempalace, 59k stars) and LangBot Plugin Development (langbot-app/LangBot, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sdwan Ops?

automateyournetwork (a GitHub user) maintains it in automateyournetwork/netclaw, which has 676 GitHub stars. The repository holds 120 skills in this directory. The repository was last updated on October 9, 2026.

Source: automateyournetwork/netclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.