agentmods.dev

gns3-mcp: Instructions file for Claude Code

CLAUDE.md

gns3-mcp CLAUDE.md is an instructions file for Claude Code from ChistokhinSV/gns3-mcp. It costs 7,814 tokens per session, scanned A, original, MIT.

A repository guide for the GNS3 MCP server, which lets AI agents work with GNS3 network-simulation labs. It covers lab control, device consoles, authentication, an SSH proxy and real-time notifications.

In plain words
What is it for?
Use it when changing GNS3 lab operations, device interaction, API access, notification streams or the SSH proxy.
Why use it?
It explains the project’s moving parts and current behavior so agents can make compatible changes to the server and its supporting services.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions Claude Code.

This is ChistokhinSV/gns3-mcp's own configuration. It tells Claude Code how to work on gns3-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gns3-mcp configures →

not rated 16repo +1 changed 3d ago A scan 7,814 tokens original MIT
View source ↗ ChistokhinSV/gns3-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to ChistokhinSV/gns3-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ChistokhinSV/gns3-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ChistokhinSV/gns3-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for gns3-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chistokhinsv/gns3-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/chistokhinsv/gns3-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chistokhinsv/gns3-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chistokhinsv/gns3-mcp/claude-md/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.

agentmods 80×15 button for gns3-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chistokhinsv/gns3-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chistokhinsv/gns3-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,814 This file is loaded in full into every session.
When invoked 7,814 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.07814 $0.07814
Opus 5.5 $0.03126 $0.03126
Sonnet 5.5 $0.01563 $0.01563
Haiku 4.5 $0.00781 $0.00781

Measured 3d ago against content hash 1740305942a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gns3-mcp CLAUDE.md 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 3d 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.

2. Test with curl:
CLAUDE.md · 788 lines

How it starts

The opening of the file, as written. The whole thing — 788 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GNS3 MCP Server - Project Instructions

Project-specific instructions for working with the GNS3 MCP server codebase.

Project Overview

MCP server providing programmatic access to GNS3 network simulation labs. Includes:

  • Desktop extension (.mcpb) for Claude Desktop
  • Agent skill with GNS3 procedural knowledge
  • Console management for device interaction
  • GNS3 v3 API client with JWT authentication

Current Version: v0.56.5 (MCP Server) / v0.3.0 (SSH Proxy)

Latest Release: v0.56.5 - project_docs update confirms what was stored SSH Proxy: v0.3.0 - Multi-Service Architecture (TFTP server, HTTP reverse proxy, HTTP client)

Recent Changes (v0.26.0 - v0.56.5)

v0.56.5 - project_docs update returns previous_length + stored_length (read back after write) and a warning on mismatch (GM-96)

v0.56.4 - icon (gecko climbing a network graph, feet are nodes): source plugin/assets/icon.svg, python scripts/render_icon.py writes plugin/assets/icon.png (1024) and mcp-server/icon.png (512); both committed

v0.56.3 - instructions.md now in the PyPI wheel ([tool.setuptools.package-data], GM-94); non-.py runtime files must be listed there (test + CI wheel check)

v0.56.2 - Client texts use current tools (GM-93): instructions.md rewritten (128 lines), prompts and error hints fixed; tests/unit/test_client_texts.py fails on any call to a removed tool name in client-facing text

v0.56.1 - published 0.56.0 + Dockerfile/smoke-test release fixes

v0.56.0 - Claude plugin + MCPB uv runtime (GM-91, GM-92)

  • plugin/ = Claude plugin gns3-lab (Claude Code + Cowork): uvx gns3-mcp@<ver> + new gns3-lab-automation skill; repo is a marketplace (.claude-plugin/marketplace.json)
  • Old skill/ removed (pre-v0.47 tool names); skill now at plugin/skills/gns3-lab-automation/
  • MCPB manifest 0.4 uv type: no uv.exe/bootstrap, deps from generated mcp-server/pyproject.toml; CLI 2.1.2; password via env; platforms darwin/win32
  • Config chain: process env > --env-file/./.env > ~/.gns3-mcp/.env (GNS3_MCP_ENV_FILE); empty values = unset
  • GNS3_USER now beats OS USER (macOS/Linux)

Read the full file on GitHub · 788 lines

Changes

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.

  1. 3d ago Changed · +1 lines · +54 tokens per session 1740305942a2
  2. 4d ago Changed · +29 lines · +1,020 tokens per session 8769e3c5e6c9
  3. 2mo ago First seen · 758 lines · 6,740 tokens per session scan A b1dd6b77dac7

Subscribe to this mod's changes

gns3-mcp CLAUDE.md is an instructions file published in the GitHub repository ChistokhinSV/gns3-mcp (16 stars, last pushed 3d ago), licensed MIT. It adds 7,814 tokens to every session, about $0.0313 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 2026-08-30.

gns3gns3-apigns3-appliancemcpmcp-server
Related

gns3-mcp CLAUDE.md compared with instructions from other repositories

gns3-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gns3-mcp CLAUDE.mdChistokhinSV/gns3-mcpInstructions file163d agoMITA7,814Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode