> ## Documentation Index > Fetch the complete documentation index at: https://opentrain.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Build With Your Coding Agent > Point Claude Code, Codex, Cursor, or any coding agent at OpenTrain's machine-readable docs and let it build your platform integration autonomously. The whole platform integration — webhook consumer, provisioning calls, usage reporting — is plain HTTP work with no SDK dependency, which makes it an ideal task for a coding agent. Every contract it needs is machine-readable: the Platform API ships a served OpenAPI spec, and every page of these docs exports as clean Markdown. Give your agent those URLs and a goal, and it can build, test, and harden the integration in one session. The [reference integration](/docs/developers/annotation-platforms/reference-integration) on the next page was built exactly this way. ## Give Your Agent the Docs Three surfaces cover everything; none of them require authentication: | Surface | What it contains | | -------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | [`https://app.opentrain.ai/api/partner/v1/openapi.json`](https://app.opentrain.ai/api/partner/v1/openapi.json) | The Platform API's OpenAPI spec — the machine-readable contract of record for every endpoint, parameter, and response shape. Generated from the same code that serves the requests. | | [`https://www.opentrain.ai/docs/llms.txt`](https://www.opentrain.ai/docs/llms.txt) | Index of all documentation pages with one-line summaries ([`llms-full.txt`](https://www.opentrain.ai/docs/llms-full.txt) is the whole site in one file). | | Any docs page + `.md` | Append `.md` to any page URL for clean Markdown — for example [`/docs/developers/annotation-platforms/webhooks.md`](https://www.opentrain.ai/docs/developers/annotation-platforms/webhooks.md). Code blocks and tab contents survive the export. | The pages worth feeding in full, in reading order: [overview](/docs/developers/annotation-platforms/overview), [register your app](/docs/developers/annotation-platforms/register-your-app), [consent and installs](/docs/developers/annotation-platforms/consent-and-installs), [project links](/docs/developers/annotation-platforms/project-links), [webhooks](/docs/developers/annotation-platforms/webhooks), [usage sync](/docs/developers/annotation-platforms/usage-sync), and the [reference integration](/docs/developers/annotation-platforms/reference-integration). ## A Bootstrap Prompt Adapt and paste this into your agent to start the session: ```text theme={null} You are building an OpenTrain integration for , an annotation platform. OpenTrain is a marketplace where employers (and their agents) hire human AI trainers; our platform is where the hired AI trainers do the work. Fetch this context first: 1. https://www.opentrain.ai/docs/llms.txt — docs index; fetch any page with .md appended 2. https://app.opentrain.ai/api/partner/v1/openapi.json — Platform API spec (no auth needed) 3. In full: - https://www.opentrain.ai/docs/developers/annotation-platforms/overview.md - https://www.opentrain.ai/docs/developers/annotation-platforms/webhooks.md - https://www.opentrain.ai/docs/developers/annotation-platforms/usage-sync.md - https://www.opentrain.ai/docs/developers/annotation-platforms/reference-integration.md Build a webhook consumer that: - verifies X-OpenTrain-Signature (t=...,v1=... HMAC-SHA256 over ".") and dedupes by X-OpenTrain-Delivery - on contract.started: find-or-create the hired AI trainer in our workspace by their OpenTrain workEmail and add them to the linked project - on contract.ended: remove their project access - reports cumulative per-day work totals to POST /api/partner/v1/contracts/{contractId}/usage - on milestone.budget_low / milestone.budget_depleted: surface a "funded budget is running out — top up on OpenTrain" notice in our UI Constraints: - The platform token is in env OPENTRAIN_PARTNER_TOKEN (ot_ptk_...); the webhook secret is in OPENTRAIN_WEBHOOK_SECRET. Never print either. - Usage reports are cumulative day totals per worker, not deltas — re-sending the same day is safe, so retry freely. - Use only our platform's existing user/membership APIs on our side. ``` Keep a human in the loop where OpenTrain does: anything that moves money (funding, payment release, ending a funded contract) is [co-signed](/docs/developers/concepts/human-approvals) on OpenTrain itself, so your agent can build and test the full loop without being able to spend anything. ## Optional: Let Your Agent Drive the Employer Side Testing the integration end-to-end needs an employer on the other side — someone to post a job, link it to your project, and hire. Your agent can play that role too: the [OpenTrain MCP server](/docs/developers/mcp/overview) exposes the employer surface (jobs, proposals, contracts, milestones) as tools, using a separate personal `ot_pat_` token from an employer test account. The same surface is available as a [CLI](/docs/developers/cli/commands) and [plain HTTP](/docs/developers/api-reference/overview). ```bash theme={null} claude mcp add opentrain --env OPENTRAIN_PERSONAL_API_TOKEN=ot_pat_... -- npx -y @opentrain-ai/mcp ``` Add `--scope user` to make it available in every project. Full setup: [Claude Code](/docs/developers/agents/claude-code). ```bash theme={null} codex mcp add opentrain --env OPENTRAIN_PERSONAL_API_TOKEN=ot_pat_... -- npx -y @opentrain-ai/mcp ``` Or declare it in `~/.codex/config.toml`. Full setup: [Codex CLI](/docs/developers/agents/codex-cli). `.cursor/mcp.json` (project) or `~/.cursor/mcp.json` (global): ```json theme={null} { "mcpServers": { "opentrain": { "command": "npx", "args": ["-y", "@opentrain-ai/mcp"], "env": { "OPENTRAIN_PERSONAL_API_TOKEN": "ot_pat_..." } } } } ``` Full setup (including keeping the token out of JSON with `envFile`): [Cursor](/docs/developers/agents/cursor). `~/.gemini/config/mcp_config.json`: ```json theme={null} { "mcpServers": { "opentrain": { "command": "npx", "args": ["-y", "@opentrain-ai/mcp"], "env": { "OPENTRAIN_PERSONAL_API_TOKEN": "ot_pat_..." } } } } ``` Full setup: [Antigravity](/docs/developers/agents/antigravity). Reads Claude Code-format `.mcp.json` at the project root (same `mcpServers` shape as Cursor above), or use the `/mcps` modal in-session. Full setup: [Grok Build](/docs/developers/agents/grok-build). Run `/mcp add` in-session, or edit `~/.copilot/mcp-config.json`: ```json theme={null} { "mcpServers": { "opentrain": { "type": "stdio", "command": "npx", "args": ["-y", "@opentrain-ai/mcp"], "env": { "OPENTRAIN_PERSONAL_API_TOKEN": "${OPENTRAIN_PERSONAL_API_TOKEN}" } } } } ``` Full setup: [Copilot CLI](/docs/developers/agents/copilot-cli). `opencode.json` — note the key is `mcp`, the command is an array, and env lives under `environment`: ```json theme={null} { "$schema": "https://opencode.ai/config.json", "mcp": { "opentrain": { "type": "local", "command": ["npx", "-y", "@opentrain-ai/mcp"], "environment": { "OPENTRAIN_PERSONAL_API_TOKEN": "{env:OPENTRAIN_PERSONAL_API_TOKEN}" }, "enabled": true } } } ``` Full setup: [OpenCode](/docs/developers/agents/opencode). Aider has no MCP support — use the CLI instead: ```bash theme={null} npm install -g @opentrain-ai/cli opentrain auth login --api-key ot_pat_... ``` Then run commands from the chat with `/run opentrain ... --json`. Full setup: [Aider](/docs/developers/agents/aider). Any MCP-capable agent works with the generic `mcpServers` shape — `command: "npx"`, `args: ["-y", "@opentrain-ai/mcp"]`, token in `env`. Examples for Claude Desktop and Windsurf: [Other MCP Agents](/docs/developers/agents/other-mcp-agents). ## Next Steps Self-serve: create the app, get your client credentials, send your first consent link. The complete worked example your agent can use as a blueprint. Report work back and keep funded budgets ahead of consumption.