Ariel
Ariel is an MCP server that exposes AT Protocol (Bluesky) operations as tools, enabling AI assistants to read, write, and interact on Bluesky with human-in-the-loop control.
README
Ariel — Bluesky MCP Server
Ariel is an MCP (Model Context Protocol) server that exposes AT Protocol (Bluesky) operations as tools. It enables AI assistants to read, write, and interact on Bluesky with human-in-the-loop control — nothing posts without explicit action.
Installation
npm install -g @ticktockbent/ariel
Or run directly with npx:
npx @ticktockbent/ariel
Or build from source:
git clone https://github.com/TickTockBent/ariel.git
cd ariel
npm install
npm run build
Configuration
Environment Variables
| Variable | Required | Description |
|---|---|---|
BLUESKY_IDENTIFIER |
Yes | Your Bluesky handle or email |
BLUESKY_APP_PASSWORD |
Yes | A Bluesky app password |
BLUESKY_SERVICE_URL |
No | PDS URL (default: https://bsky.social) |
ARIEL_DATA_DIR |
No | Session storage directory (default: ~/.ariel/) |
MCP Client Configuration
Add to your MCP client config (e.g. claude_desktop_config.json):
{
"mcpServers": {
"ariel": {
"command": "npx",
"args": ["-y", "@ticktockbent/ariel"],
"env": {
"BLUESKY_IDENTIFIER": "your.handle.bsky.social",
"BLUESKY_APP_PASSWORD": "your-app-password"
}
}
}
}
Tools
Ariel exposes 33 tools across six categories.
Authentication
ariel_auth_status— Check auth state, handle, DID, and rate limitsariel_auth_logout— Log out and clear stored session
Reading
ariel_get_timeline— Home timelineariel_get_author_feed— A user's postsariel_get_post_thread— Post with thread contextariel_get_posts— Multiple posts by AT URI (max 25)ariel_get_profile— User profileariel_get_feed— Custom feed generator postsariel_search_posts— Search postsariel_search_users— Search usersariel_get_trends— Trending topicsariel_get_saved_feeds— Your saved/pinned feedsariel_get_list— List metadata and membersariel_get_list_feed— Posts from a list feedariel_resolve_url— Convert bsky.app URL to AT URI
Writing
ariel_create_post— Create a post with auto-detected mentions/links/hashtagsariel_create_thread— Create a multi-post threadariel_reply— Reply to a post (auto-resolves thread root)ariel_quote_post— Quote-post another postariel_delete_post— Delete your post
Media
ariel_upload_image— Upload an image blobariel_create_post_with_images— Post with images (max 4)ariel_create_post_with_link_card— Post with Open Graph link card
Social
ariel_follow/ariel_unfollow— Follow/unfollow usersariel_get_followers/ariel_get_follows— View follower/following listsariel_like/ariel_unlike— Like/unlike postsariel_repost/ariel_unrepost— Repost/remove repostsariel_mute/ariel_unmute— Mute/unmute usersariel_block/ariel_unblock— Block/unblock users
Notifications
ariel_get_notifications— Recent notificationsariel_get_unread_count— Unread notification countariel_mark_notifications_read— Mark all notifications as read
Resources
Ariel provides three MCP resources with reference material that clients can pull into context:
ariel://at-protocol-concepts— DIDs, handles, AT URIs, facets, embeds, and viewer stateariel://tool-conventions— URL acceptance, error format, theformatparameter, and viewer state auto-resolutionariel://post-schema— Post record structure, embed types, facet format, and thread mechanics
Prompts
Three built-in prompts for common workflows:
summarize-timeline— Fetch your home timeline and produce a thematic summarydraft-thread— Research a topic and draft a thread for review before postingreview-notifications— Review recent notifications and suggest responses
Development
npm run dev # Watch mode TypeScript compilation
npm test # Run tests
npm run build # Production build
npm start # Run the server
See CONTRIBUTING.md for development guidelines.
License
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。