{
  "markdown": "# Sunex Optics MCP Server\n\nA public [Model Context Protocol](https://modelcontextprotocol.io) server that lets AI assistants search [Sunex](https://www.optics-online.com)'s lens and imager catalog in natural language.\n\n**Live endpoint:** `https://mcp.sunex-ai.com/mcp`\n**Landing page:** [sunex-ai.com](https://sunex-ai.com)\n**Transport:** Streamable HTTP (MCP spec 2025-03-26). Legacy SSE endpoint at `/sse` preserved for older clients.\n\n## Connect in 30 seconds\n\n### Claude\nSettings → Connectors → Add custom connector → paste `https://mcp.sunex-ai.com/mcp`\n\n### Cursor / Continue / Zed\nAdd to your MCP config with transport `streamable-http` and the URL above.\n\n### ChatGPT\nVia any MCP → OpenAPI bridge as a custom GPT Action.\n\n## Five tools\n\n| Tool | What it does |\n|---|---|\n| `recommend_lens_for_imager` | Give it an imager PN → compatible lenses with FOV and angular resolution. One shot. |\n| `search_imagers` | Find sensors by PN, manufacturer, or resolution class. |\n| `get_imager_detail` | Full sensor specs plus computed geometry (width / height / diagonal in mm). |\n| `find_compatible_lenses` | Given pixel count + pitch, return lenses whose image circle covers the sensor. |\n| `search_products` | Full catalog search by PN or keyword, with sample pricing and RFQ links. |\n\n## Example prompts\n\n- *\"Recommend a wide-angle lens for the Sony IMX577 with F/2.0 or faster.\"*\n- *\"I need fisheye lenses under $100.\"*\n- *\"What's the diagonal of the IMX477 in mm?\"*\n- *\"Find lenses for a 1920×1080 sensor with 3µm pixels, 100–180° HFOV.\"*\n\n## Architecture\n\n```\nClaude / Cursor / ChatGPT  →  mcp.sunex-ai.com  →  optics-online.com/api/v1\n     (MCP client)         (Cloudflare Worker)      (ASP JSON API)\n```\n\nThin proxy on Cloudflare Workers (free tier) over Sunex's production catalog. Streamable HTTP transport per MCP spec 2025-03-26 (with legacy SSE preserved). No auth, read-only.\n\n## Endpoints\n\n| Path | Purpose |\n|---|---|\n| `/mcp` | **Primary** — Streamable HTTP transport (current MCP standard) |\n| `/sse` | Legacy SSE transport, preserved for backward compatibility |\n| `/.well-known/mcp.json` | Public discovery manifest |\n| `/` | Landing page with install instructions |\n\n## Self-host\n\n```bash\ngit clone https://github.com/Sunex-AI/Optics-mcp\ncd Optics-mcp\nnpm install\nnpx wrangler login\nnpx wrangler deploy\n```\n\n## Calling a tool directly (Python)\n\n```python\nfrom mcp import ClientSession\nfrom mcp.client.streamable_http import streamablehttp_client\n\nasync with streamablehttp_client(\"https://mcp.sunex-ai.com/mcp\") as (r, w, _):\n    async with ClientSession(r, w) as session:\n        await session.initialize()\n        result = await session.call_tool(\n            \"recommend_lens_for_imager\",\n            {\"imagerPn\": \"IMX577\", \"fNumMax\": 2.0}\n        )\n```\n\n## Discovery\n\nPublic manifest: [`https://mcp.sunex-ai.com/.well-known/mcp.json`](https://mcp.sunex-ai.com/.well-known/mcp.json)\n\n## Contributing\n\nIssues and PRs welcome. For requests about the backend API (pricing, additional catalog fields, new endpoints), email [support@sunex.com](mailto:support@sunex.com).\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n",
  "bytes": 3129,
  "sha": "90d2cdc292c5e0db13df97039c8b6c72af540f735fda45c8ff62870b9c3913a0",
  "repo_slug": "sunex-ai/optics-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_sunex_optics_mcp_62db3619/readme"
}