Borrowing it
Nothing to install: this file belongs to marduk191/qwen3_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.
curl -O https://raw.githubusercontent.com/marduk191/qwen3_mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/marduk191/qwen3_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/instructions/marduk191/qwen3_mcp/claude-md)<a href="https://agentmods.dev/instructions/marduk191/qwen3_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marduk191/qwen3_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.
<a href="https://agentmods.dev/instructions/marduk191/qwen3_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marduk191/qwen3_mcp/claude-md.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 | $0.05679 | $0.05679 |
| Opus 5 | $0.02840 | $0.02840 |
| Sonnet 5 | $0.01136 | $0.01136 |
| Haiku 4.5 | $0.00568 | $0.00568 |
Grade A, and why
qwen3_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 10d 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. Verify server is running: `curl http://localhost:3847/skills` How it starts
The opening of the file, as written. The whole thing — 640 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qwen3 MCP Server
A Model Context Protocol (MCP) server that gives LM Studio's Qwen3 (or any local LLM) full coding agent capabilities including 80+ tools for file operations, command execution, git, web search, memory, planning, and a full skills system.
Two Server Modes
HTTP Mode (Browser Chat)
start-chat.bat
# Open http://localhost:3847/chat.html
MCP Mode (LM Studio Direct)
Add to ~/.lmstudio/mcp-servers.json:
{
"mcpServers": {
"qwen3-mcp": {
"command": "node",
"args": ["<YOUR_PATH>/src/index.js"],
"cwd": "<YOUR_PATH>"
}
}
}
Replace <YOUR_PATH> with the actual installation path.
Project Structure
qwen3-mcp/
├── src/
│ ├── index.js # MCP server (stdio, uses @modelcontextprotocol/sdk)
│ └── tools/ # Tool implementations
│ ├── filesystem.js # read_file, write_file, list_directory, etc.
│ ├── edit.js # edit_file, insert_at_line, replace_lines
│ ├── bash.js # execute_command, execute_background
│ ├── git.js # git_status, git_commit, git_push, etc.
│ ├── search.js # glob_search, grep_search, find_definition
│ ├── web.js # web_search, web_image_search, web_fetch
│ ├── memory.js # memory_store, memory_recall, scratchpad_*
│ ├── planning.js # plan_create, plan_status, plan_step_complete
│ ├── tasks.js # task_add, task_list, task_update
│ ├── thinking.js # think, reason, evaluate_options
│ ├── context.js # conversation_log, conversation_context
│ ├── interaction.js # ask_user, confirm, present_choices
│ ├── media.js # read_image, read_pdf, take_screenshot
│ ├── notebook.js # notebook_read, notebook_edit_cell
│ ├── comfyui.js # 32 ComfyUI workflow tools
│ ├── github-blog.js # Jekyll blog tools
│ └── skills.js # list_skills, load_skill, install_skill
├── frontend/
│ ├── server.js # HTTP server (port 3847) with all tools
│ ├── chat.html # Browser chat interface
│ └── index.html # Image viewer interface
├── docs/ # GitHub Pages static site (auto-generated)
│ ├── index.html # Built from README.md by build-docs.cjs
│ ├── .nojekyll # Tells GitHub Pages to serve as static HTML
│ └── assets/
│ ├── css/style.css # Dark theme matching marduk191.github.io
│ ├── js/main.js # Mobile menu toggle
│ └── images/banner.jpg # Hero banner image
├── scripts/
│ └── build-docs.cjs # Converts README.md → docs/index.html
├── .github/
│ └── workflows/
│ └── build-docs.yml # Auto-rebuilds docs on README.md changes
├── skills/ # Installed agent skills (16)
│ ├── chrome-extension/ # Chrome extension development (MV3)
│ ├── code-review/ # Code review methodology
│ ├── comfyui-nodes/ # ComfyUI custom node development (V1 + V3 API, v2.1.0)
│ ├── comfyui-workflow/ # ComfyUI workflow creation (SD1.5/SDXL/SD3.5/Flux)
│ ├── differential-review/ # Security-focused diff review
│ ├── docx/ # Word document creation (Anthropic)
│ ├── frontend-design/ # Frontend UI/UX
│ ├── github-blog/ # Jekyll blog for GitHub Pages
│ ├── mcp-builder/ # Build MCP servers
│ ├── modern-python/ # Python tooling (Trail of Bits)
│ ├── react-best-practices/ # React patterns (Vercel)
│ ├── shadcn-ui/ # Modern component library
│ ├── static-analysis/ # CodeQL, Semgrep, SARIF
│ ├── testing-handbook-skills/ # Fuzzers, sanitizers
│ ├── web-artifacts-builder/ # HTML/React prototypes
│ └── web-design-guidelines/ # UI/UX fundamentals
├── start-chat.bat # Start HTTP server
├── stop-chat.bat # Stop server
├── restart-chat.bat # Restart server
└── install-skill.bat # Install skills from GitHub
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.
- 10d ago First seen · 640 lines · 5,679 tokens per session scan A 9dbfc6ac01e4
qwen3_mcp CLAUDE.md is an instructions file published in the GitHub repository marduk191/qwen3_mcp (13 stars, last pushed 7mo ago), licensed MIT. It adds 5,679 tokens to every session, about $0.0284 per session on Opus 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.