No install? Use cloud.anythingmcp.com directly.
Sign in, install the Slab in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Drive Slab (team wiki) from any AI agent via its GraphQL API: posts, topics, users, search. 6 tools, Bearer auth.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → Slab klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
Slab + Gemini
Drive Slab (team wiki) from any AI agent via its GraphQL API: posts, topics, users, search. 6 tools, Bearer auth.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
SLAB_API_TOKEN
Schritt 1 — Zugangsdaten holen
slab.com/v1/graphql).
Setup:
- Sign in to Slab → top-right avatar → Account Settings → Tokens → Create token.
- Pick scopes: at minimum
read posts,read topics,read users. - Set
SLAB_API_TOKEN.
Authentication: Authorization: Bearer ${SLAB_API_TOKEN}.
GraphQL-only: Slab has no REST. The adapter exposes a few curated mutations + queries as wrappers; for arbitrary queries use the auto-injected GraphQL builtins (each GRAPHQL adapter gets slab_graphql_schema, slab_graphql_query, slab_graphql_mutation automatically).
…(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 —Slabsollte 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 |
|---|---|
slab_me | Return the user the token belongs to (id, name, email, organization) |
slab_get_post | Fetch a post by ID with title + content (in markdown) + topics + owner |
slab_search_posts | Search posts by query text |
slab_list_topics | List top-level topics in the organization |
slab_get_topic_posts | List posts within a topic |
slab_create_post | Create a post from markdown content |
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?