No install? Use cloud.anythingmcp.com directly.
Sign in, install the Lever 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 Lever ATS (candidates, opportunities, postings, stages, feedback) from any AI agent. 10 tools, basic-auth.
💡 Niente installazione? Vai direttamente su cloud.anythingmcp.com. Accedi, clicca Connectors → Lever, inserisci le credenziali, genera una MCP API key — fatto. Niente Docker, niente
git clone, niente server locale.
Lever + Gemini
Manage Lever ATS (candidates, opportunities, postings, stages, feedback) from any AI agent. 10 tools, basic-auth.
Prerequisiti
Le istruzioni di setup complete sono incluse nel connettore stesso (visibili nello store quando lo selezioni). Le variabili d'ambiente richieste sono:
LEVER_API_KEY
Step 1 — Ottieni le credenziali
This connector wraps the Lever Hire API v1 (api.lever.co/v1).
Setup:
- In Lever → Settings → Integrations and API → API Credentials → Generate new key.
- Set
LEVER_API_KEY. - Sandbox: use
https://api.sandbox.lever.co/v1instead during testing.
Authentication: HTTP Basic — API key as username, empty password.
Opportunity vs Candidate: in Lever's modern API, an Opportunity represents a candidate's interest in a single posting. A person can have multiple opportunities (one per role). The legacy Candidate endpoint still works but Opportunity is preferred.
…(continued in the in-app connector instructions)
Step 2 — Installa l'adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Step 3 — Aggiungi il connettore in Gemini
Gemini CLI legge i server MCP da ~/.gemini/settings.json (o %APPDATA%\gemini\settings.json su Windows). Aggiungi:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Ottieni la tua MCP API key da AnythingMCP → Profilo → MCP API Keys → Nuova Key.
- Salva il file e riavvia
gemini. - Esegui
/mcpnella Gemini CLI —Leverdovrebbe essere elencato come disponibile. - Vertex AI Studio: passa
https://cloud.anythingmcp.com/mcpnell'arraytoolsdella richiesta con lo stesso header Bearer.
Tool disponibili
| Tool | What it does |
|---|---|
lever_list_opportunities | List opportunities (candidate × posting) |
lever_get_opportunity | Get one opportunity with full contact, links, tags, applications |
lever_create_opportunity | Create an opportunity (candidate with associated posting) |
lever_update_opportunity_stage | Move an opportunity to a different stage |
lever_archive_opportunity | Archive an opportunity with an archive reason |
lever_list_postings | List job postings |
lever_list_stages | List pipeline stages |
lever_list_users | List Lever users (recruiters, hiring managers) |
lever_list_archive_reasons | List archive reasons configured in the org |
lever_list_feedback | List interview feedback forms attached to an opportunity |
FAQ
Gemini 1.5 Pro o 2.x supportano MCP? Sì — Gemini CLI ≥ 0.4 e la Vertex AI tools API accettano connettori MCP httpUrl con header Bearer.
Prossimi passi
Questa guida ti è stata utile?