No install? Use cloud.anythingmcp.com directly.
Sign in, install the Mastodon 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 any Mastodon instance from any AI agent. 10 tools, Bearer token auth.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → Mastodon klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
Mastodon + Gemini
Read & post on any Mastodon instance from any AI agent. 10 tools, Bearer token auth.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
MASTODON_INSTANCE_URL, MASTODON_ACCESS_TOKEN
Schritt 1 — Zugangsdaten holen
This connector wraps the Mastodon REST API (any instance — set baseUrl to your instance).
Setup:
- Pick your instance (e.g.
https://mastodon.social,https://fosstodon.org, your self-hosted one). - Log in → Preferences → Development → New application.
- Name it (e.g. 'mcp'). Scopes:
read,write,follow,push— tick whatever your use case needs (don't over-grant). - Save → copy the Your access token value (shown only once). This is a personal access token tied to your account.
- Set
MASTODON_INSTANCE_URL(e.g.https://mastodon.social) andMASTODON_ACCESS_TOKEN.
Authentication: Authorization: Bearer ${MASTODON_ACCESS_TOKEN} on every request.
…(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 —Mastodonsollte 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 |
|---|---|
mastodon_verify_credentials | Return the authenticated account: id, username, acct (full handle), display_name, note, avatar, statuses_count, followers_count, following_c |
mastodon_get_account | Fetch a public account by ID |
mastodon_account_statuses | Get a user's recent statuses (toots) |
mastodon_home_timeline | Get the authenticated user's home timeline (their follows) |
mastodon_public_timeline | Get the public timeline |
mastodon_hashtag_timeline | Get statuses tagged with a hashtag (no # prefix) |
mastodon_search | Full-text search across accounts, statuses and hashtags |
mastodon_get_status | Fetch a single status by ID |
mastodon_post_status | Post a new status (toot) |
mastodon_delete_status | Delete one of your own statuses |
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?