Ariel

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.

Category
Visit Server

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 limits
  • ariel_auth_logout — Log out and clear stored session

Reading

  • ariel_get_timeline — Home timeline
  • ariel_get_author_feed — A user's posts
  • ariel_get_post_thread — Post with thread context
  • ariel_get_posts — Multiple posts by AT URI (max 25)
  • ariel_get_profile — User profile
  • ariel_get_feed — Custom feed generator posts
  • ariel_search_posts — Search posts
  • ariel_search_users — Search users
  • ariel_get_trends — Trending topics
  • ariel_get_saved_feeds — Your saved/pinned feeds
  • ariel_get_list — List metadata and members
  • ariel_get_list_feed — Posts from a list feed
  • ariel_resolve_url — Convert bsky.app URL to AT URI

Writing

  • ariel_create_post — Create a post with auto-detected mentions/links/hashtags
  • ariel_create_thread — Create a multi-post thread
  • ariel_reply — Reply to a post (auto-resolves thread root)
  • ariel_quote_post — Quote-post another post
  • ariel_delete_post — Delete your post

Media

  • ariel_upload_image — Upload an image blob
  • ariel_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 users
  • ariel_get_followers / ariel_get_follows — View follower/following lists
  • ariel_like / ariel_unlike — Like/unlike posts
  • ariel_repost / ariel_unrepost — Repost/remove reposts
  • ariel_mute / ariel_unmute — Mute/unmute users
  • ariel_block / ariel_unblock — Block/unblock users

Notifications

  • ariel_get_notifications — Recent notifications
  • ariel_get_unread_count — Unread notification count
  • ariel_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 state
  • ariel://tool-conventions — URL acceptance, error format, the format parameter, and viewer state auto-resolution
  • ariel://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 summary
  • draft-thread — Research a topic and draft a thread for review before posting
  • review-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

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured