dcc-itchio
Enables secure acquisition of itch.io game assets via official RSS feeds and authenticated Butler daemon downloads, and preview-gated publishing of game builds with hash-bound receipts and license verification.
README
DCC itch.io Skills
Two independently installable DCC-MCP Skills for safe itch.io asset acquisition and preview-gated game publishing.

Illustration generated for this repository; it contains no third-party logos, copied marketplace thumbnails, or product UI.
Skills
itchio-assets
- Browse only itch.io's official game-assets RSS feed.
- List and inspect asset projects with direct download-key ownership on the authenticated account through the official Butler daemon API.
- Download one exact owned upload without running installers or downloaded code.
- Require explicit license evidence before any download, then return a validated
DCC-MCP
AssetDescriptorwith hashes and attribution.
This Skill does not buy assets, scrape project pages, infer a license from price or ownership, or import downloaded content into a DCC application. Version 0.1 fails closed for bundle-only ownership.
itchio-publish
- List projects owned by the authenticated creator account.
- Inspect Butler channels and their head/pending build states.
- Create a hash-bound preview receipt for a prepared game build.
- Revalidate the source tree, license provenance, Butler binary, channel parent,
and preview result before an authenticated
butler push.
Publishing consumes license-provenance.json produced by the marketplace
game-release-package Skill. Core's asynchronous job cancellation terminates
the local Butler process only; it is not a remote build rollback.
Runtime requirements
- DCC-MCP Core 0.19.91 or newer
- Python 3.7 or newer for production scripts
- itch.io Butler 15.30.0 or newer
BUTLER_API_KEYin the local environment for authenticated operations
The API key is never accepted as a tool argument, written to a receipt, placed on a command line, or returned in tool output. The asset Skill passes it to an ephemeral, isolated Butler daemon over JSON-RPC and removes that daemon's local state after the request.
Development
python -m pip install "dcc-mcp-core>=0.19.91" "pytest>=7.4,<9" "PyYAML>=6" "ruff>=0.9" Pillow
python scripts/validate_skills.py
python -m pytest -q
ruff check .
All network and Butler unit tests use fixtures or fake processes. CI never performs a real upload or download.
License
MIT
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。