No install? Use cloud.anythingmcp.com directly.
Sign in, install the Workable 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 Workable ATS (candidates, jobs, members, stages, comments) from any AI agent. 9 tools, Bearer token auth.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Workable, paste your credentials, mint an MCP API key — done. No Docker, no
git clone, no local server.
Workable + Gemini
Manage Workable ATS (candidates, jobs, members, stages, comments) from any AI agent. 9 tools, Bearer token 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:
WORKABLE_SUBDOMAIN, WORKABLE_ACCESS_TOKEN
Step 1 — Get credentials
This connector wraps the Workable Hiring API (per-subdomain — yoursub.workable.com/spi/v3).
Setup:
- Log into your Workable account → top-right avatar → Integrations → Workable API → Generate access token.
- Note your subdomain (the part before
.workable.com). - Set
WORKABLE_SUBDOMAINandWORKABLE_ACCESS_TOKEN.
Authentication: Authorization: Bearer ${WORKABLE_ACCESS_TOKEN}.
Per-tenant baseUrl: https://${WORKABLE_SUBDOMAIN}.workable.com/spi/v3. Substituted at import time.
Job 'shortcode': Workable identifies jobs by short hash strings (AC123ABCDE) in URLs/API. Use workable_list_jobs to discover.
…(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 —Workableshould 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 |
|---|---|
workable_account_info | Returns the account info (subdomain, name, summary) |
workable_list_jobs | List jobs |
workable_get_job | Get a single job by shortcode with full description + requirements + benefits |
workable_list_candidates | List candidates for a job |
workable_get_candidate | Get one candidate by ID with full profile + answers to job questions |
workable_create_candidate | Create a candidate on a job (sourced / referral) |
workable_move_candidate_stage | Move a candidate to a different pipeline stage |
workable_disqualify_candidate | Disqualify (reject) a candidate with a reason |
workable_list_stages | List pipeline stages defined in the account |
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?