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.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Greenhouse, paste your credentials, mint an MCP API key — done. No Docker, no
git clone, no local server.
Greenhouse + Gemini
Manage Greenhouse (ATS recruiting: candidates, applications, jobs, scorecards, offers) from any AI agent. 10 tools, basic-auth.
Prerequisites
See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:
GREENHOUSE_API_KEY
Step 1 — Get credentials
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)
Step 2 — Install the adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Step 3 — Add the connector in Gemini
Gemini CLI reads MCP servers from ~/.gemini/settings.json (or %APPDATA%\gemini\settings.json on Windows). Add:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Get your MCP API key from AnythingMCP → Profile → MCP API Keys → New Key.
- Save the file and restart
gemini. - Run
/mcpinside the Gemini CLI —Greenhouseshould be listed as available. - Vertex AI Studio: pass
https://cloud.anythingmcp.com/mcpto thetoolsarray of your request with the same Bearer header.
Available 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
Does Gemini 1.5 Pro or 2.x support MCP? Yes — Gemini CLI ≥ 0.4 and Vertex AI tools API both accept MCP httpUrl connectors with Bearer headers.
Next steps
Was this guide helpful?