No install? Use cloud.anythingmcp.com directly.
Sign in, install the Bluesky in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Read & post on Bluesky (the AT Protocol social network) from any AI agent. 9 tools, app-password auth.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → Bluesky klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
Bluesky + Gemini
Read & post on Bluesky (the AT Protocol social network) from any AI agent. 9 tools, app-password auth.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
BLUESKY_HANDLE, BLUESKY_APP_PASSWORD
Schritt 1 — Zugangsdaten holen
This connector wraps the Bluesky AT Protocol XRPC API (bsky.social).
Setup:
- In the Bluesky app or web client → Settings → Privacy and Security → App Passwords → Add App Password.
- Name it (e.g. 'mcp') and copy the generated
xxxx-xxxx-xxxx-xxxxpassword. App passwords scope down what they can do — never use your account password. - Set
BLUESKY_HANDLE(e.g.you.bsky.social) andBLUESKY_APP_PASSWORD.
…(continued in the in-app connector instructions)
Schritt 2 — Adapter installieren
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Schritt 3 — Connector in Gemini hinzufügen
Gemini CLI liest MCP-Server aus ~/.gemini/settings.json (oder %APPDATA%\gemini\settings.json unter Windows). Hinzufügen:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Hole deinen MCP API Key aus AnythingMCP → Profil → MCP API Keys → Neuer Key.
- Speichern und
geminineu starten. /mcpin Gemini CLI ausführen —Blueskysollte als verfügbar gelistet sein.- Vertex AI Studio:
https://cloud.anythingmcp.com/mcpimtools-Array der Anfrage mit demselben Bearer-Header übergeben.
Verfügbare Tools
| Tool | What it does |
|---|---|
bluesky_create_session | Exchange handle + app password for an access JWT (lasts ~2h) and refresh JWT |
bluesky_refresh_session | Refresh an access JWT using the refresh JWT |
bluesky_resolve_handle | Resolve a Bluesky handle (e |
bluesky_get_profile | Get a user's public profile: handle, did, displayName, description, followers, follows, posts count, avatar URL |
bluesky_get_timeline | Get the authenticated user's home timeline (chronological feed of follows) |
bluesky_get_author_feed | Get posts by a specific user (their public feed) |
bluesky_search_posts | Full-text search across public posts |
bluesky_create_post | Post a new skeet |
bluesky_delete_post | Delete one of your own posts by its rkey (record key, the last segment of the at:// URI) |
FAQ
Unterstützen Gemini 1.5 Pro oder 2.x MCP? Ja — Gemini CLI ≥ 0.4 und die Vertex AI Tools API akzeptieren MCP httpUrl-Connectors mit Bearer-Header.
Nächste Schritte
War dieser Guide hilfreich?