{
  "markdown": "# @suprsonic/mcp\n\nMCP server for [Suprsonic](https://suprsonic.ai). Gives any AI agent dozens of capabilities through one connection.\n\n## Quick Start\n\n```bash\nSUPRSONIC_API_KEY=omk_your_key npx -y @suprsonic/mcp\n```\n\nGet your API key at [suprsonic.ai/app/apis](https://suprsonic.ai/app/apis).\n\n## Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"suprsonic\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@suprsonic/mcp\"],\n      \"env\": {\n        \"SUPRSONIC_API_KEY\": \"omk_your_key\"\n      }\n    }\n  }\n}\n```\n\n## Cursor / VS Code\n\nAdd to `.cursor/mcp.json` or VS Code MCP config:\n\n```json\n{\n  \"suprsonic\": {\n    \"command\": \"npx\",\n    \"args\": [\"-y\", \"@suprsonic/mcp\"],\n    \"env\": {\n      \"SUPRSONIC_API_KEY\": \"omk_your_key\"\n    }\n  }\n}\n```\n\n## Remote HTTP (for Claude API, ChatGPT, programmatic agents)\n\n```bash\nSUPRSONIC_API_KEY=omk_your_key npx -y @suprsonic/mcp --http --port 3100\n```\n\nThen connect to `http://localhost:3100/mcp`.\n\n## Available Tools\n\n| Tool | What it does |\n|------|-------------|\n| search | Search the web (AI synthesis, SERP, or both) |\n| scrape | Extract content from any URL as Markdown |\n| profiles | Find professional profiles by name or LinkedIn URL |\n| emails | Find professional email addresses |\n| images | Generate images from text prompts |\n| tts | Convert text to speech |\n| stt | Transcribe audio to text |\n| sms | Send SMS or WhatsApp messages |\n| documents | Extract structured data from URLs |\n| companies | Look up company data by domain |\n| email-verify | Check if an email is deliverable |\n| transcribe | Transcribe audio with speaker labels |\n| invoice-parse | Extract data from invoices |\n| subtitle | Generate SRT/VTT subtitles |\n| file-convert | Convert files between 200+ formats |\n| bg-remove | Remove image backgrounds |\n| screenshot | Capture webpage screenshots |\n\n## Response Format\n\nEvery tool returns a unified response object:\n\n```json\n{\n  \"success\": true,\n  \"data\": {\n    \"results\": [\n      { \"title\": \"OpenAI raises $6.6B\", \"url\": \"https://...\", \"snippet\": \"...\" }\n    ]\n  },\n  \"error\": null,\n  \"metadata\": {\n    \"provider_used\": \"serperdev\",\n    \"providers_tried\": [\"serperdev\"],\n    \"response_time_ms\": 1200,\n    \"request_id\": \"req_abc123\"\n  },\n  \"credits_used\": 1\n}\n```\n\nOn failure, `success` is `false` and `error` contains the details (see below).\n\n## Error Handling\n\nError object structure (returned when `success` is `false`):\n\n```json\n{\n  \"type\": \"billing_error\",\n  \"title\": \"Insufficient credits\",\n  \"status\": 402,\n  \"detail\": \"Your account has 0 credits remaining. Add credits at suprsonic.ai/app/billing.\",\n  \"is_retriable\": false,\n  \"retry_after_seconds\": null,\n  \"error_category\": \"billing\"\n}\n```\n\nError categories: `transient` (retry safe), `permanent` (bad request), `authentication` (invalid key), `billing` (out of credits).\n\nWhen using MCP, the AI agent receives the error in the tool response and can decide whether to retry based on `is_retriable` and `retry_after_seconds`.\n\nFull API reference with all parameters and example responses: [suprsonic.ai/apis](https://suprsonic.ai/apis)\n",
  "bytes": 3133,
  "sha": "b14065d3843bb39b869435f056c83c37585339f87388fe7d7485e6c40df0e78a",
  "repo_slug": "o-mega-enterprise/suprsonic-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_o_mega_enterprise_suprsonic_mc_9aeccf9c/readme"
}