No install? Use cloud.anythingmcp.com directly.
Sign in, install the Buffer in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Manage Buffer (social media scheduling: channels, posts, idea queue, analytics) from any AI agent via GraphQL. 8 tools, Bearer token.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → Buffer klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
Buffer + Gemini
Manage Buffer (social media scheduling: channels, posts, idea queue, analytics) from any AI agent via GraphQL. 8 tools, Bearer token.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
BUFFER_ACCESS_TOKEN
Schritt 1 — Zugangsdaten holen
This connector wraps the Buffer Publish GraphQL API (graphql.buffer.com).
Setup:
- Sign in at https://publish.buffer.com → top-right avatar → Settings → API access → Generate personal access token.
- Set
BUFFER_ACCESS_TOKEN.
Authentication: Authorization: Bearer ${BUFFER_ACCESS_TOKEN}.
GraphQL-only: Buffer's modern API is GraphQL. The auto-injected buffer_graphql_query / buffer_graphql_mutation / buffer_graphql_schema builtins cover anything not in the typed wrappers below.
Channel = connected social account (Twitter, LinkedIn, Facebook, Instagram, Mastodon, TikTok, Pinterest, YouTube, Bluesky, Threads). Each has an ID; posts must specify channelId(s).
…(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 —Buffersollte 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 |
|---|---|
buffer_current_user | Return the authenticated user with their orgs |
buffer_list_channels | List connected social channels for an organization |
buffer_list_posts | List posts on a channel with status filter |
buffer_create_post | Schedule or save a draft post on one or more channels |
buffer_update_post | Update a scheduled post's text, schedule, or media |
buffer_delete_post | Delete a post |
buffer_send_now | Send a scheduled post immediately, regardless of due_at |
buffer_list_ideas | List ideas from the org-wide idea queue |
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?