FOAAS MCP Server
A Docker-based MCP server that exposes humorous and explicit FOAAS operations for responding to development scenarios like bug reports, code reviews, and pull requests.
README
FOAAS MCP Server
⚠️ EXPLICIT CONTENT WARNING ⚠️
A secure, Docker-based Model Context Protocol server exposing FOAAS (Fuck Off As A Service) operations. Perfect for adding humorous (and explicit) responses to development workflows.
Demo
See FOAAS MCP in action responding to GitHub issues with GitHub Copilot:

See it yourself: Demo repository with sample issues and PRs, or create your own demo repo.
Features
- 🐳 Docker-first (Debian 12, Node.js 20.19.5, non-root)
- 🔧 23 MCP tools covering common dev scenarios
- � Scenario-based organization (bug reports, code reviews, PRs, etc.)
- 🔒 stdio-only transport (no network exposure)
Quick Start
Using Pre-built Image
docker pull ghcr.io/gusztavvargadr/foaas-mcp:latest
VS Code Configuration (.vscode/mcp.json):
{
"mcpServers": {
"foaas": {
"command": "docker",
"args": ["run", "--rm", "-i", "ghcr.io/gusztavvargadr/foaas-mcp:latest"]
}
}
}
Building from Source
git clone https://github.com/gusztavvargadr/foaas-mcp.git
cd foaas-mcp
npm run docker:build
Restart MCP server in VS Code (GitHub Copilot status bar → Restart MCP Servers).
Available Tools (23 Total)
All tools provide direct 1:1 mapping to FOAAS operations with foaas_ prefix:
Appreciation & Praise (4): thanks, awesome, legend, dalton
Rejections & Dismissals (3): because, zero, bye
Direct Confrontations (4): off, gfy, chainsaw, keep
General Frustration (3): everyone, flying, asshole
Code Review & Quality (9): logs, rtfm, think, thinking, shutup, look, ridiculous, understand, cool
Usage Scenarios
Bug Reports & Debugging
"Works on my machine" / Runtime errors
foaas_logs- When the solution is clearly in the logs
"How do I use X?" / Questions already in docs
foaas_rtfm- When documentation exists but wasn't read
General confusion
foaas_zero- Express complete disinterestfoaas_everyone- Universal dismissalfoaas_flying- Maximum level of not caring
Code Reviews
Questionable code / Bad decisions
foaas_think- Question someone's thought processfoaas_thinking- Alternative phrasing for questioning decisions
Pointing out issues
foaas_look- Request someone examine something specific
Nitpicking / Endless debates
foaas_shutup- Stop bikeshedding and trivial arguments
Great contributions
foaas_legend- Genuine praise for someonefoaas_dalton- Call someone a problem-solving hero
Pull Requests & Issues
Spam / Duplicates
foaas_off- Classic dismissalfoaas_bye- End the conversationfoaas_thanks- Sarcastic gratitude
Absurd requests / Scope creep
foaas_ridiculous- For unrealistic requirementsfoaas_chainsaw- Dramatic reaction to absurdity
Unclear requirements
foaas_understand- Express genuine confusion
Sarcastic approval
foaas_cool- Dismiss excuses with peak sarcasmfoaas_awesome- Enthusiastic (but maybe ironic) celebration
Team Communication
General frustration
foaas_everyone- Dismiss all partiesfoaas_flying- Express not caringfoaas_asshole- General purpose frustration
Rejecting requests
foaas_because- Answer "why not?" emphaticallyfoaas_zero- Show complete disinterest
Direct confrontation
foaas_gfy- Military-style professional profanityfoaas_keep- Extended dismissal for persistent issues
Team praise
foaas_legend- Call someone a legendfoaas_dalton- Acknowledge problem-solving skills
Example Usage
GitHub Copilot Integration
Ask Copilot to use FOAAS MCP tools in natural language:
"Respond to this bug report with no logs" → foaas_logs
"Acknowledge @contributor's excellent fix" → foaas_legend
"This feature request is unrealistic" → foaas_ridiculous
"Stop bikeshedding on variable names" → foaas_shutup
Direct Tool Calls
All tools require a from parameter. Tools with a target require to:
{
"name": "foaas_legend",
"arguments": {
"to": "contributor",
"from": "maintainer"
}
}
{
"name": "foaas_logs",
"arguments": {
"from": "support-bot"
}
}
Documentation
- Contributing Guide - Setup, architecture, development workflow
- Demo Materials - LinkedIn GIFs, demo repository setup
- Roadmap - Development roadmap and feature tracking
Image Tags
latest- Latest stable releasev1.0.0- Semantic versionssha-<commit>- Specific commits (testing)
Security
- Process isolation via Docker
- Non-root user (nodejs UID 1001)
- Minimal Debian 12 Bookworm Slim base
- stdio-only transport (no network)
- Regular security updates
License
MIT License - See LICENSE file for details
Links
- FOAAS - Original API
- Model Context Protocol - MCP specification
- GitHub Copilot - AI integration
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。