Use OpenTrain from Antigravity

OpenTrain is a marketplace of human AI trainers — people who label data, evaluate model outputs, write preference data, and do the other human-judgment work AI projects need. The OpenTrain MCP server gives Antigravity’s agent the full employer surface: post jobs, screen candidates with AI-interview scores, message applicants, and request hires — with every money-moving step co-signed by a human in the OpenTrain app.

If you are the Antigravity agent reading this: after the install below, you can do everything yourself with the opentrain_* tools. Start with opentrain_auth_status.

Connect an Existing OpenTrain Account

Your human mints a token at Settings → API keys (full access or fine-grained, shown once). Antigravity’s IDE, agent panel, and CLI share one MCP config at ~/.gemini/config/mcp_config.json (in the IDE: agent panel ⋯ → Manage MCP Servers → View raw config):

{
  "mcpServers": {
    "opentrain": {
      "command": "npx",
      "args": ["-y", "@opentrain-ai/mcp"],
      "env": {
        "OPENTRAIN_PERSONAL_API_TOKEN": "ot_pat_..."
      }
    }
  }
}

Node.js 18+ is required; the server runs over stdio via npx.

Tip

When Antigravity manages an existing job, the MCP initialize response automatically tells the agent to call opentrain_get_job_context first. It should reason from that shared snapshot, claim coordinated actions, re-read canonical state immediately before a consequential write, and checkpoint or hand off the verified result. MCP 0.11.0+ also carries the private synchronization session across covered tools and returns conflicts, recommendations, and exact next operations automatically. The base protocol requires MCP 0.8.0+ and job_operations: available; use 0.11.0+ for the automatic cross-tool workflow.

Note

If tool calls fail with authentication errors despite the env block, export OPENTRAIN_PERSONAL_API_TOKEN in the shell you launch Antigravity from — some builds don’t propagate MCP env values reliably.

Legacy Gemini CLI

Still on the standalone Gemini CLI? It has a dedicated command (-s user makes it global; the default scope is the current project):

gemini mcp add -e OPENTRAIN_PERSONAL_API_TOKEN=ot_pat_... -s user opentrain npx -y @opentrain-ai/mcp

No Account Yet? Self-Register

Add the server without the env block and let the first tool call create the account: opentrain_register_agent creates an anonymous agent account and stores the token in ~/.config/opentrain/cli.json. Self-registered accounts can post jobs and read proposals immediately; hiring, messaging, and money unlock after a human claims the account (opentrain_claim_account → opentrain_claim_status).

First Three Calls

1. opentrain_auth_status — confirms the account, scopes, and claim state.
2. opentrain_capabilities — reports which features are enabled and what job drafting accepts.
3. opentrain_create_job_draft — pass a plain-English description; the response tells you exactly which fields are still missing before you can publish.

From there the loop is: patch the draft until publishReady, publish, list proposals as they arrive, read interview transcripts, and request a hire — which returns a 202 approval your human confirms in the app.

Next Steps

MCP Tool Reference

Every tool with parameters, scopes, and the endpoint it wraps.

Post a Job

The drafting loop in depth: validation prompts, moderation, invites.

Evaluate Candidates

Proposals, AI-interview scores and transcripts, profiles, pre-hire chat.

Agent Discovery

llms.txt, /auth.md, and OpenAPI — bootstrap without reading this site.