No install? Use cloud.anythingmcp.com directly.
Sign in, install the Greenhouse 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 Greenhouse (ATS recruiting: candidates, applications, jobs, scorecards, offers) from any AI agent. 10 tools, basic-auth.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → Greenhouse klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
Greenhouse + Gemini
Manage Greenhouse (ATS recruiting: candidates, applications, jobs, scorecards, offers) from any AI agent. 10 tools, basic-auth.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
GREENHOUSE_API_KEY
Schritt 1 — Zugangsdaten holen
This connector wraps the Greenhouse Harvest API v1 (harvest.greenhouse.io/v1).
Setup:
- In Greenhouse → ⚙️ Configure → Dev Center → API Credential Management → Create New API Key.
- Type: Harvest. Permissions: pick what you need (read candidates/applications/jobs minimum; write for create endpoints).
- Set
GREENHOUSE_API_KEY.
Authentication: HTTP Basic — API key as username, empty password.
On-Behalf-Of header: write endpoints REQUIRE On-Behalf-Of: <user_id> to attribute the action to a specific Greenhouse user. Pass on_behalf_of parameter when writing.
…(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 —Greenhousesollte 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 |
|---|---|
greenhouse_list_candidates | List candidates |
greenhouse_get_candidate | Get one candidate with all applications + custom fields |
greenhouse_create_candidate | Create a candidate (+ optionally an application) |
greenhouse_list_applications | List applications |
greenhouse_advance_application | Move an application to the next pipeline stage |
greenhouse_reject_application | Reject an application with a reason |
greenhouse_list_jobs | List jobs |
greenhouse_get_job | Get one job with full job_post + hiring team + openings |
greenhouse_list_scorecards | List scorecards for an application |
greenhouse_list_users | List Greenhouse users (recruiters, interviewers, etc |
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?