Model Context Protocol · Live

Find best lens/CMOS sensor solutions for your imaging applications, directly in AI chat apps

A public MCP server that lets Claude, ChatGPT, Cursor and any MCP-compatible AI models direct access to our 350+ lens dataset utilizing our powerful Optics-Wizards™ tools to find the best lens/CMOS imager solutions for automotive, robotics, drone, medical and physical AI applications. Based in the U.S. and serving customers worldwide for 25 years, Sunex has shipped over 100M+ lenses and imaging solutions for mission-critical systems with unmatched reliability.

5
AI-callable tools
Live
Real-time catalog
Free
Public, no API key

What your AI assistant can do

Ask in natural language. The assistant picks the right tool, queries our live catalog, and returns structured results with spec-sheet, sample-order, and RFQ links.

Find sensors fast

Search by part number, manufacturer, or resolution class. Get full specs plus computed sensor geometry in millimeters.

Match lenses to imagers

Feed any imager PN and get compatible M12 lenses with per-lens FOV, angular resolution, and F/# filters.

Quote & spec in one turn

Every result includes sample pricing, spec sheet URL, sample order link, and volume RFQ link. No separate lookup.

Ask"Recommend a wide-angle lens for the Sony IMX577 sensor, F/2.0 or faster."
recommend_lens_for_imager
Resolves IMX577 geometry (4056×3040, 1.55µm), then filters lens catalog:
  • DSL945 — EFL 2.2mm, F/1.8, HFOV 150°
  • DSL219 — EFL 1.9mm, F/2.0, HFOV 168°
  • Plus spec sheet, sample order & RFQ links
Ask"I need fisheye lenses under $100. What do you have?"
search_products
Scans full catalog, returns PN, description, sample price, and:
  • Direct spec-sheet URLs
  • One-click sample order
  • Volume quote request
Ask"What's the diagonal of the IMX477 in mm? And what's its Nyquist?"
get_imager_detail
Returns full specs plus:
  • Effective width / height / diagonal in mm
  • Nyquist frequencies (mono, green, red/blue)
  • Pre-built lens-wizard URL
Ask"Compare lenses for a 1920×1080 sensor with 3µm pixels, 100-180° HFOV."
find_compatible_lenses
Applies FOV, F/#, and image-circle filters:
  • Per-lens HFOV, VFOV, DFOV in degrees
  • Angular resolution px/deg (on-axis and edge)
  • Image-circle clamp flags

Connect in 30 seconds

No account, no API key, no install. Just paste one URL into your MCP-compatible client.

https://mcp.sunex-ai.com/sse

This is the canonical MCP endpoint. https://sunex-ai.com/sse also works.

1 Claude (web & desktop)

Anthropic · Pro / Team / Enterprise
  1. Open claude.aiSettings → Connectors
  2. Click Add custom connector
  3. Paste the URL above
  4. Name it Sunex Optics and save

2 Cursor / Continue / Zed

IDE assistants · MCP support built-in
  1. Open your MCP config (e.g. ~/.cursor/mcp.json)
  2. Add an entry with transport sse and the URL above
  3. Restart the editor
  4. Tools appear in the assistant's tool picker

3 ChatGPT (custom GPTs)

OpenAI · via MCP bridge
  1. Create a custom GPT with Actions enabled
  2. Use any MCP→OpenAPI bridge (e.g. mcp-openapi)
  3. Point it at the URL above
  4. The 5 tools become Actions

4 Your own code

Python / TypeScript / any language
  1. Install the MCP client SDK for your language
  2. Connect via SSE to the URL above
  3. Call tools by name with the documented params
  4. See manifest for schema

Five tools, one endpoint

All tools return structured JSON. Parameters are self-documenting — your AI client sees descriptions and types automatically.

search_imagers
Search sensor catalog by PN, manufacturer, or resolution class. Returns full specs from SunexOOL.ImagerList.
get_imager_detail
Full sensor specs plus computed geometry (width / height / diagonal in mm) and pre-built lens-wizard URL.
find_compatible_lenses
Given pixel count and pitch, return lenses whose image circle and resolving power cover the sensor, with per-lens FOV and angular resolution.
search_products
Search full product catalog by PN prefix and/or description keyword. Returns sample pricing and URLs for spec sheet, sample order, and RFQ.

For developers

A thin MCP server on Cloudflare Workers, proxying Sunex's live product database. Everything is public, documented, and auditable.

Call a tool directly (MCP SSE)

# List available tools
curl https://mcp.sunex-ai.com/sse

# Inspect the public manifest
curl https://mcp.sunex-ai.com/.well-known/mcp.json

# From Python with the MCP SDK
from mcp import ClientSession
from mcp.client.sse import sse_client

async with sse_client("https://mcp.sunex-ai.com/sse") as (r, w):
    async with ClientSession(r, w) as session:
        await session.initialize()
        result = await session.call_tool(
            "recommend_lens_for_imager",
            {"imagerPn": "IMX577", "fNumMax": 2.0}
        )

What's under the hood

  • Transport
    HTTP + Server-Sent Events (SSE) per MCP 2024-11-05 spec
  • Runtime
    Cloudflare Workers, global edge, free tier
  • Backend
    Sunex's production catalog at optics-online.com
  • Auth
    None — public read-only endpoint
  • Rate limit
    Fair use; contact us for high-volume access
  • Status
    Live · manifest

Frequently asked

The essentials, for engineers and buyers alike.

What is MCP, and why should I care?

Model Context Protocol is an open standard (originally from Anthropic, now supported by OpenAI, Google, Cursor, Zed, and others) that lets AI assistants call external tools. Think "USB-C for LLMs." If your assistant supports MCP, it can talk to our catalog without any custom integration work on your end — you just paste a URL.

Is this really free? What's the catch?

Free and public. Sunex maintains it because helping engineers find the right lens faster is good for everyone — including us. The server is stateless, read-only, and rate-limited fairly. If you want high-volume programmatic access or custom tools, contact us.

Does it work with ChatGPT?

MCP is native in Claude, Cursor, Continue, Zed, and a growing list of clients. ChatGPT supports it indirectly via a bridge to Actions / custom GPTs. OpenAI has announced MCP support, and we'll update this page when native connectors ship.

How current is the data?

Live. The MCP server proxies Sunex's production catalog in real time — same data as optics-online.com. When we add a new lens, it's callable within minutes.

Can I self-host or white-label this?

The server code is open and deployable to any Cloudflare account. If you're an integrator or distributor who wants your own branded MCP endpoint against our catalog, contact us — we're happy to help.

What if a tool returns wrong or surprising results?

The math and database come directly from our lens wizard, which has been in production for years. But if you see something off, we want to know — email support@sunex.com with the prompt and the response.

Will you add write actions (RFQ submit, sample order)?

Yes, on the roadmap. Current tools are read-only by design — anything that creates an order or RFQ will require explicit auth and per-session confirmation.