Quickstart

1. Create An Account

Open the production sign-in page:

https://aiworkflowmcp.com/en/sign-in/

https://aiworkflowmcp.com/en/account/api-keys/

Create a key, copy it once, and store it as AIWORKFLOWMCP_API_KEY.

2. Add The MCP Endpoint

Claude Code:

claude mcp add --transport http aiworkflowmcp https://mcp.aiworkflowmcp.com/mcp

HTTP MCP clients:

{
  "mcpServers": {
    "aiworkflowmcp": {
      "url": "https://mcp.aiworkflowmcp.com/mcp",
      "headers": {
        "Authorization": "Bearer ${AIWORKFLOWMCP_API_KEY}"
      }
    }
  }
}

Public basic queries can run without a key. Authenticated keys add account-level usage history and quota routing.

3. Run A REST Smoke Test

curl -fsS "https://mcp.aiworkflowmcp.com/v1/models/list?limit=1"
curl -fsS "https://api.aiworkflowmcp.com/health"

Authenticated REST:

curl -fsS \
  -H "Authorization: Bearer ${AIWORKFLOWMCP_API_KEY}" \
  "https://mcp.aiworkflowmcp.com/v1/models/list?limit=1"

4. Call One MCP Tool

curl -fsS https://mcp.aiworkflowmcp.com/mcp \
  -H "content-type: application/json" \
  -H "Authorization: Bearer ${AIWORKFLOWMCP_API_KEY}" \
  --data '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "get_ai_model",
      "arguments": {
        "model_id": "gpt-5"
      }
    }
  }'

The response contains chat-ready content and typed structuredContent.

5. Check Production Health

curl -fsS https://mcp.aiworkflowmcp.com/health

For production automation, treat status: "ok" and data_quality.latest_eval_status: "PASS" as the green path. Treat stale entities or source errors as a reason to retry later or disable fresh_only=true only for non-critical discovery.