Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ChistokhinSV/gns3-mcp --skill gns3-lab-automationgit clone --depth 1 https://github.com/ChistokhinSV/gns3-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chistokhinsv/gns3-mcp/gns3-lab-automation)<a href="https://agentmods.dev/skills/chistokhinsv/gns3-mcp/gns3-lab-automation"><img src="https://agentmods.dev/badge/skills/chistokhinsv/gns3-mcp/gns3-lab-automation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chistokhinsv/gns3-mcp/gns3-lab-automation"><img src="https://agentmods.dev/badge/skills/chistokhinsv/gns3-mcp/gns3-lab-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00098 | $0.02846 |
| Opus 5.5 | $0.00039 | $0.01138 |
| Sonnet 5.5 | $0.00020 | $0.00569 |
| Haiku 4.5 | $0.00010 | $0.00285 |
Grade A, and why
gns3-lab-automation scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The `gns3` MCP server drives a GNS3 v3 server. Every call goes through its tools; never call the GNS3 REST API with curl - the server handles JWT auth. How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GNS3 Lab Automation
The gns3 MCP server drives a GNS3 v3 server. Every call goes through its tools; never call the GNS3 REST API with curl - the server handles JWT auth.
Tools at a glance
| Tool | Use it for |
|---|---|
project |
list, open (by name), create (auto-opens), close |
node |
list, create from a template, delete, set (properties and start/stop/suspend/reload/restart; wildcards) |
link |
list, batch connect/disconnect (validated before anything changes) |
console |
batch of send, send_and_wait, read, keystroke on telnet consoles |
ssh |
batch of configure, command, read, disconnect through the SSH proxy (Netmiko) |
node_file |
Docker nodes: read, write, configure_network |
project_docs |
get / update the project README (IPs, credentials, notes) |
drawing |
list, create, update, delete, batch (rectangles, ellipses, lines, text) |
export_topology_diagram |
SVG/PNG of the canvas |
notification |
live GNS3 events: subscribe, read, unsubscribe, status |
query_resource |
read any resource URI (see below) |
gns3_connection |
check, retry, reconnect (after a GNS3 restart) |
tftp, http_client |
lab services on the SSH proxy |
search_tools |
find a tool by category or capability |
Ground rules
- Know the current project. Node, link, console and drawing tools act on the server's current project. After a server restart it picks the first opened project - with several open, call
project(action="open", name=...)first. - Read before you write.
project_docs(action="get")holds IP plans and credentials.query_resource("projects://<id>/topology_report")gives nodes, links and status in one call. - Nodes boot slowly.
node(action="set", state_action="start")waits up to ~60 s forstarted; consoles and SSH need the OS to finish booting after that. - Console first-access rule. The first batch for a node that was never accessed may only contain
readops; other ops are skipped. Read once, then send. - Trust the reports. A
noderesult withunapplied_propertiesorWarning: not applied by GNS3means GNS3 ignored those keys - fix the key name for that node type instead of retrying. Errordetailscarry GNS3's reason (missing image, connected switch, node must be stopped). - Record what you build (IPs, logins, purpose) with
project_docs(action="update").
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 177 lines · 98 tokens per session scan A 1b3a4579904b
gns3-lab-automation is a skill published in the GitHub repository ChistokhinSV/gns3-mcp (16 stars, last pushed 3d ago), licensed MIT. It adds 98 tokens to every session and 2,846 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-03.
gns3-lab-automation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gns3-lab-automationChistokhinSV/gns3-mcp | Skill | 16 | 3d ago | MIT | A | 98 | Claude Code |
| opik-diagnosecomet-ml/opik-mcp | Skill | 225 | 9d ago | Apache-2.0 | A | 187 | Claude Code |
| ue-mcp-epic-routingdb-lyon/ue-mcp | Skill | 476 | yesterday | MIT | A | 81 | Claude Code, Codex |
| qa-knowledgegriddynamics/rosetta | Skill | 370 | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| apitapn1byn1kt/apitap | Skill | 131 | 17d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| frontmcp-setupagentfront/frontmcp | Skill | 148 | yesterday | Apache-2.0 | A | 176 | Claude Code, Codex |
| x-use-reviewihuzaifashoukat/x-use | Skill | 181 | 4d ago | MIT | A | 56 | Claude Code |