Skip to content
LumixAI logo

LumixAI MCP server

Which MCP servers are LumixAI's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-20

← Back to LumixAI

Whose server it is
  • Addresshttps://lumixai.live/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on lumixai.live when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools3
  • Server calls itselfLumixAI Agent Discovery
  • Server version1.0.0
  • Protocol version2024-11-05

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 390 ms.

Should an agent connect itConnect it, with care
  • Its tools do compare image and video models before spending credits, but not generate cheap draft images and videos for concept testing; produce short fast video clips for social posts.

Once connected

  • For "compare image and video models before spending credits", the likely first call is get-lumixai-model-catalog.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 9, the first on 2026-10-27
  • INITE MCP score78 of 100answers 100 · does the job 33 · definitions 83 · context 100 · connects 100
  • What an agent can do with it1 of 3 use cases
  • Answered100% of days9 of 9 daily checks
  • Median first answer631 ms
  • Space in an agent's context≈ 175 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 3 of 3

What an agent can do with it

  • cannot · generate cheap draft images and videos for concept testing
  • cannot · produce short fast video clips for social posts
  • can do · compare image and video models before spending credits

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers3 tools · read 2026-10-27
  • get-lumixai-model-catalog

    Fetch LumixAI public image and video model catalog with pricing tiers.

  • get-lumixai-video-capabilities

    Fetch LumixAI video model durations, resolutions, aspect ratios, sound, and reference support.

  • get-lumixai-agent-docs

    Return key LumixAI agent discovery URLs for API integration.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "lumixai": {
      "type": "http",
      "url": "https://lumixai.live/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http lumixai https://lumixai.live/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://lumixai.live/mcp as a custom connector in the settings.

OpenAPI spec

13 paths, read 2026-10-20. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.