Optics MCP Server

Thin proxy on Cloudflare Workers (free tier) over Sunex's production catalog. Streamable HTTP transport per MCP spec 2025-03-26 (with legacy SSE

Remote serverstreamable-httpPython

What is the Optics MCP MCP server?

Connect Optics MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Thin 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. The optics mcp mcp server is what makes that connection.

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • recommend_lens_for_imager — Give it an imager PN → compatible lenses with FOV and angular resolution. One shot
  • search_imagers — Find sensors by PN, manufacturer, or resolution class
  • get_imager_detail — Full sensor specs plus computed geometry (width / height / diagonal in mm)
  • find_compatible_lenses — Given pixel count + pitch, return lenses whose image circle covers the sensor
  • search_products — Full catalog search by PN or keyword, with sample pricing and RFQ links
  • Claude — Settings → Connectors → Add custom connector → paste https://mcp.sunex-ai.com/mcp
  • ChatGPT — The ChatGPT tool exposed by this server

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Plenty of cloud and infrastructure servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Optics MCP's toolset — recommend_lens_for_imager, search_imagers, get_imager_detail and 4 more — is a fair guide to whether it matches your workflow. It is maintained by sunex-ai; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
recommend_lens_for_imagerGive it an imager PN → compatible lenses with FOV and angular resolution. One shot.
search_imagersFind sensors by PN, manufacturer, or resolution class.
get_imager_detailFull sensor specs plus computed geometry (width / height / diagonal in mm).
find_compatible_lensesGiven pixel count + pitch, return lenses whose image circle covers the sensor.
search_productsFull catalog search by PN or keyword, with sample pricing and RFQ links.
ClaudeSettings → Connectors → Add custom connector → paste https://mcp.sunex-ai.com/mcp
ChatGPTThe ChatGPT tool exposed by this server.

How to install the Optics MCP MCP server

{
  "mcpServers": {
    "optics": {
      "command": "npx",
      "args": ["-y", "wrangler"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Optics MCP to recommend lens for imager.
  • Use Optics MCP to search imagers.
  • Use Optics MCP to get imager detail.

Frequently asked questions

It connects Optics MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (recommend_lens_for_imager, search_imagers, get_imager_detail, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Optics MCP directly.