Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Teamwork Projects in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Manage Teamwork.com (projects, tasks, milestones, time entries, comments, people) from any AI agent. 10 tools, basic-auth with API key.
Frag einfach
Beispiel-Prompts für Teamwork Projects
Klick auf einen Prompt, um ihn zu kopieren. In Claude, ChatGPT, Cursor, Gemini, Copilot oder OpenClaw einfügen — und gegen diesen Konnektor laufen lassen.
Claude ist KI und kann Fehler machen. Bitte Antworten gegenprüfen.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → Teamwork Projects klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
Teamwork Projects + Gemini
Manage Teamwork.com (projects, tasks, milestones, time entries, comments, people) from any AI agent. 10 tools, basic-auth with API key.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
TEAMWORK_SUBDOMAIN, TEAMWORK_API_KEY
Schritt 1 — Zugangsdaten holen
This connector wraps the Teamwork Projects REST API v3 (per-subdomain — yoursubdomain.teamwork.com/projects/api/v3).
Setup:
- Log into your Teamwork account → top-right avatar → Edit my details → API & Mobile → Get my API Key.
- Note your subdomain (the part before
.teamwork.com). - Set
TEAMWORK_SUBDOMAINandTEAMWORK_API_KEY.
Authentication: HTTP Basic — API key as username, literal x as password.
Per-tenant baseUrl: https://${TEAMWORK_SUBDOMAIN}.teamwork.com/projects/api/v3. Substituted at import time.
API versions: v3 is the modern REST. v1/v2 still exist for some endpoints. This adapter uses v3 where available.
…(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 —Teamwork Projectssollte 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 |
|---|---|
teamwork_list_projects | List projects |
teamwork_get_project | Get one project with summary metrics |
teamwork_create_project | Create a project |
teamwork_list_tasks | List tasks across all projects (or one) |
teamwork_get_task | Get one task with all custom fields, time logs, dependencies |
teamwork_create_task | Create a task inside a task list |
teamwork_complete_task | Mark a task complete |
teamwork_log_time | Log time on a task or project |
teamwork_list_milestones | List milestones across projects |
teamwork_list_people | List users (people) |
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?