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 agentmods add skills/opensquad-ai/opensquad/mcp_auto_deploynpx skills add opensquad-ai/opensquad --skill mcp_auto_deploygit clone --depth 1 https://github.com/opensquad-ai/opensquadWrote 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/opensquad-ai/opensquad/mcp_auto_deploy)<a href="https://agentmods.dev/skills/opensquad-ai/opensquad/mcp_auto_deploy"><img src="https://agentmods.dev/badge/skills/opensquad-ai/opensquad/mcp_auto_deploy.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.03787 |
| Opus 5 | $0.00018 | $0.01894 |
| Sonnet 5 | $0.00007 | $0.00757 |
| Haiku 4.5 | $0.00004 | $0.00379 |
Grade A, and why
mcp_auto_deploy scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Auto Deploy — Agent Self-Service Guide
1. MCP 架构概述
OpenSquad 的 MCP 分为两层：
| 层级 | 文件路径 | 说明 |
|---|---|---|
| 中央配置 (Central) | <workspace>/data/mcp_config.json |
统一的 MCP 服务器列表，所有 agent 共享 |
| Agent 配置 (Per-agent) | <workspace>/agents/<agent_name>/mcp_config.json |
从中央配置自动同步，也可单独覆盖 |
Agent 启动时，Launcher 会读取中央配置并同步到每个 agent。所有 Agent 共享同一套 MCP 服务器。
💡 MCP 配置存储路径（中央）：
{workspace}/data/mcp_config.json通过 filesystem 工具可读写此文件。
2. MCP Server 配置格式 (mcpServers)
中央 mcp_config.json 的结构如下：
{
"mcpServers": {
"<server-name>": {
"enabled": true,
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/allowed/dir"],
"timeout": 60,
"env": {
"API_KEY": "YOUR_API_KEY_HERE"
},
"autoApprove": ["read_file", "write_file"]
},
"<server-name-2>": {
"enabled": false,
"command": "uvx",
"args": ["mcp-server-google-maps"],
"timeout": 30
}
}
}
| 字段 | 必填 | 说明 |
|---|---|---|
enabled |
是 | true=启用，false=禁用但在 UI 中可见 |
command |
是 | 可执行命令，如 npx、uvx、python、node |
args |
是 | 命令行参数数组 |
timeout |
否 | 超时秒数 (默认 60) |
env |
否 | 环境变量字典，传递给子进程 |
autoApprove |
否 | 不需要用户确认即可自动调用的工具名列表 |
3. 部署一个新的 MCP 服务器
步骤 1: 确定 MCP 服务器来源
MCP 服务器可来自：
- npm 包:
npx -y @modelcontextprotocol/server-xxx - Python 包:
uvx mcp-server-xxx - 本地脚本:
python path/to/server.py - 自定义二进制: 任何可执行文件
常用 MCP 服务器示例：
| 名称 | 安装命令 | 用途 |
|---|---|---|
filesystem |
npx -y @modelcontextprotocol/server-filesystem /path |
文件系统操作 |
puppeteer |
npx -y @modelcontextprotocol/server-puppeteer |
浏览器自动化 |
brave-search |
npx -y @modelcontextprotocol/server-brave-search |
Brave 搜索引擎 |
fetch |
npx -y @modelcontextprotocol/server-fetch |
网页抓取 |
git |
npx -y @modelcontextprotocol/server-git |
Git 操作 |
步骤 2: 确认目标机器上已安装所需运行时
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 · 429 lines · 36 tokens per session scan A 12c98b28c224
mcp_auto_deploy is a skill published in the GitHub repository opensquad-ai/opensquad (5 stars, last pushed 21d ago), licensed MIT. It adds 36 tokens to every session and 3,787 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
typescript-expert
TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling.
electron-pro
Expert in building cross-platform desktop applications using web technologies (HTML/CSS/JS) with the Electron framework.
lat-md
Writing and maintaining lat.md documentation files — structured markdown that describes a project's architecture, design decisions, and test specs. Use when creating, editing, or reviewing files in the lat.md/ directory.
git-workflow
When the user asks you to perform git operations, create branches, open PRs, manage releases, or resolve conflicts, follow this guide. These are the procedural patterns you should apply consistently.
x-intelligence
When the user asks you to search, monitor, or analyze content on X (formerly Twitter), follow this guide. All operations use the official X API v2 and optionally the xAI Grok API for analysis. Never scrape. Never use unofficial endpoints.
life-automation-audit
Use this as an on-demand long prompt. Do not paste it into SOUL.md / PRINCIPLES.md / AGENTS.md. When the user asks to audit their life for automation opportunities, load and follow this prompt.