@opentrain-ai/mcp

OpenTrain MCP

MCP server for OpenTrain public API workflows: agent registration, job posting, proposal review, hiring, contracts and milestones, messaging, credits, webhooks, and team management.

Money never moves from this server: hire, milestone funding/approval, and contract-end requests record a pending approval and return an approvalUrl that a signed-in human must open and confirm in the OpenTrain app.

Install

Add to any MCP-capable client (Claude Code, Claude Desktop, Cursor, etc.):

{
  "mcpServers": {
    "opentrain": {
      "command": "npx",
      "args": ["-y", "@opentrain-ai/mcp@latest"]
    }
  }
}

With Claude Code:

claude mcp add opentrain -- npx -y @opentrain-ai/mcp@latest

When running from a monorepo checkout that already has an @opentrain-ai/mcp workspace, include @latest so npm resolves the published package instead of an unbuilt local workspace.

No credentials are needed to start — call opentrain_register_agent to create an agent account on the fly.

ChatGPT / Hosted MCP

The npm package above is a local stdio server. For ChatGPT developer mode, the OpenAI API Playground, or MCP Inspector, use the hosted HTTPS MCP endpoint:

https://app.opentrain.ai/mcp

The hosted endpoint exposes a small remote-safe tool set:

• opentrain_search_jobs — anonymous public marketplace search.
• opentrain_auth_status — protected token/account check.
• opentrain_create_job_draft and opentrain_update_job_draft_fields — protected draft workflow tools.

Public search works without linking. Account-specific tools require OpenTrain bearer-token auth and return MCP OAuth challenges when called unauthenticated. The local stdio package remains the full self-registration flow because it can store the generated ot_pat_ token in the user's local ~/.config/opentrain/cli.json without exposing secrets in tool output.

Authentication

The server starts without any credentials. Token resolution order:

• OPENTRAIN_PERSONAL_API_TOKEN env var (wins outright when set)
• The shared OpenTrain config file ${XDG_CONFIG_HOME:-~/.config}/opentrain/cli.json — the same file the OpenTrain CLI writes, so registering through either surface makes the credentials available to both
• No token — only the onboarding tools work until opentrain_register_agent is called

Environment

• OPENTRAIN_API_BASE_URL
  • Base URL for the OpenTrain app/API. Defaults to https://app.opentrain.ai.
  • Example local development value: http://127.0.0.1:3000.
• OPENTRAIN_PERSONAL_API_TOKEN (optional)
  • Personal OpenTrain API token (ot_pat_…). Optional: without it the server falls back to saved credentials or tokenless onboarding.

Tools

Onboarding (no token needed):

• opentrain_register_agent
  • Registers a brand-new anonymous agent account via POST /api/agent/identity.
  • Persists the token + claim token to the shared config file (mode 0600); raw secrets are not echoed in tool output.
  • Refuses to overwrite existing credentials unless force: true.
• opentrain_claim_account
  • Emails the human owner a claim invite via POST /api/agent/identity/claim.
  • Returns the verification URI + user code to relay to the human.
• opentrain_claim_status
  • Polls POST /api/agent/oauth/token (claim grant). Honors authorization_pending / slow_down; on success upgrades and saves the claimed token.

Job posting:

• opentrain_create_job_draft
  • Primary workflow: send a full plain-text jobDescription (or a supported canonicalJob / importPayload); OpenTrain parses it server-side.
  • Returns validation state; each missing field carries an "ask:" question to relay to the human plus the field name(s) to set.
• opentrain_update_job_draft_fields
  • Patches draft fields by name (the gap-filling step after asking the human).
• opentrain_publish_job
  • Publishes a publish-ready draft live (same validation + moderation pipeline as the in-app flow; per-account daily limits).

Proposals and hiring:

• opentrain_list_jobs — own jobs with status filter + pagination.
• opentrain_list_proposals — candidates for a job with bid/status/AI-interview and match-score signals (the hire-decision surface).
• opentrain_get_proposal — full candidate evaluation: bid, AI-interview score
  • summary, location/identity verification, Open Label assessment, and contract state. Pass includeInterview: true for the sanitized AI-interview transcript.
• opentrain_get_freelancer_profile — masked freelancer profile by id or slug: skills, stats, work/label experience, education, reviews, languages. Names stay masked and personal contact details are never returned.
• opentrain_invite_freelancer — invite a freelancer to a published job.
• opentrain_hire_proposal — request a hire with a first escrow milestone. Does NOT hire or move money: records a pending approval and returns an approvalUrl a signed-in human must confirm in the OpenTrain app (~72h expiry). Requires a claimed account + payment method or covering credit balance.
• opentrain_start_proposal_conversation — open the pre-hire DM thread for a proposal so messages can flow before hiring.

Jobs (beyond drafting):

• opentrain_search_jobs — public marketplace search (no token needed).
• opentrain_update_published_job — patch fields on a live job.
• opentrain_close_job — close a published job to new proposals.

Contracts and milestones (co-signed money movement):

• opentrain_list_contracts / opentrain_get_contract — contract status, milestones with funding/approval state, budget consumption, and the post-hire job DM conversationId.
• opentrain_create_milestone — add an unfunded milestone directly.
• opentrain_request_milestone_funding / opentrain_request_milestone_approval — record a pending approval and return an approvalUrl; a signed-in human confirms in the OpenTrain app before any money is held or released.
• opentrain_end_contract — direct when no funded milestones exist, otherwise returns an approval the human must confirm.
• opentrain_get_approval — re-check a pending approval's status.

Updates feed and webhooks:

• opentrain_poll_updates — cursor-based delta feed of account events (new proposals, messages, contract/milestone changes, approval confirmations, budget state changes). Persist nextCursor between polls.
• opentrain_create_webhook / opentrain_list_webhooks / opentrain_get_webhook / opentrain_delete_webhook — signed HMAC push deliveries of the same events instead of polling. The signing secret is shown once at creation.

Credits (prepaid balance):

• opentrain_get_credits — available/reserved balance.
• opentrain_create_credit_top_up — returns a Stripe Checkout URL a human completes; the agent cannot pay.
• opentrain_get_credit_top_up — top-up status.
• opentrain_list_credit_ledger — append-only ledger entries.

Messaging and payments:

• opentrain_read_messages — omit conversationId to list conversation summaries; provide it to read messages. Read-only.
• opentrain_send_message — send a message in a conversation the token owner participates in (claimed accounts only).
• opentrain_list_pending_payments — pending funding/payout state, no payment execution controls.

Team:

• opentrain_get_team — organization, members, invites.
• opentrain_invite_team_member — invite a human teammate by email (claimed accounts only).

Account and discovery:

• opentrain_auth_status — calls GET /api/public/v1/auth/me, returns the resolved token owner + scopes.
• opentrain_capabilities — feature/scope map for the current token: which tool families are enabled for this account.
• opentrain_list_tokens / opentrain_revoke_token — manage the account's API tokens.

Local smoke

Start the app locally, then run the MCP server over stdio (no token needed):

OPENTRAIN_API_BASE_URL=http://127.0.0.1:3000 \
npx -y tsx@4.20.5 packages/opentrain-mcp/src/index.ts

Example zero-to-registered probe:

printf '%s\n' \
  '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"smoke","version":"1.0"}}}' \
  '{"jsonrpc":"2.0","method":"notifications/initialized","params":{}}' \
  '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"opentrain_register_agent","arguments":{"agentName":"Local Smoke Agent"}}}' \
  '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"opentrain_auth_status","arguments":{}}}' \
  | OPENTRAIN_API_BASE_URL=http://127.0.0.1:3000 npx -y tsx@4.20.5 packages/opentrain-mcp/src/index.ts

Example primary job-draft call (uses saved or env credentials):

printf '%s\n' \
  '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"smoke","version":"1.0"}}}' \
  '{"jsonrpc":"2.0","method":"notifications/initialized","params":{}}' \
  '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"opentrain_create_job_draft","arguments":{"title":"Image Annotation Specialist","jobDescription":"We need experienced image annotation specialists to draw bounding boxes around retail products in catalog photos. The dataset has about 1,200 JPG files. Contributors should have prior image-labeling QA experience, write short edge-case notes, and report daily throughput. Pay is $25 per hour.","externalId":"catalog-boxes-001","idempotencyKey":"catalog-boxes-001-local-smoke"}}}' \
  | OPENTRAIN_API_BASE_URL=http://127.0.0.1:3000 npx -y tsx@4.20.5 packages/opentrain-mcp/src/index.ts