LMX Cloud LLM Inference MCP server

• chat_completionFree

  Call LMX Cloud OpenAI-compatible chat completions. Prefers a pre-funded API key (Bearer / api_key); when omitted and x402 is enabled, requires a USDC pay-per-call payment. Optional image_url / images enable vision input (OpenAI content-parts format) — use a vision model such as llama-3.2-90b-vision, qwen-3.6-35b, or qwen-3.5-35b.

• extract_pdfFree

  Extract text and light structure (title, headings, page count) from a PDF via LMX pdf-extract. Provide file_url and/or file_base64. Requires a real LMX API key (same gate as web_search).

• get_balanceFree

  Fetch USD credit balance for the caller API key. Requires authentication.

• get_pricingFree

  Fetch current LMX Cloud per-call pricing catalog.

• get_statusFree

  Fetch LMX Cloud provider health, fallback chain, and anchoring status.

• get_usageFree

  Fetch request and token usage totals for the caller API key. Requires authentication.

• list_modelsFree

  List currently supported LMX model aliases and providers.

• quote_priceFree

  Estimate USDC cost for a single model call. Uses GET /v1/pricing with model and token params.

• web_searchFree

  Real-time web search via LMX (Brave Search passthrough). Fixed per-call USDC price from the caller's API key balance. Returns title/url/snippet results.

• –Code scanremote-only server, no package to scann/a
• Live reliabilityremote reachable in 919ms20/20
• Tool poisoning9 tool descriptions checked15/15
• Auth qualityopen endpoint, read-only tools10/15
• Maintenanceno repository listed3/15
• Maintainer identityno repository or website to verify2/10

LMX Cloud LLM Inference: common questions

Is LMX Cloud LLM Inference MCP server safe?

With care: it is graded C, so read the findings first (67/100). Read the LMX Cloud LLM Inference safety report

How do I install LMX Cloud LLM Inference?

It runs remotely at mcp.lmxcloud.io. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.

Does LMX Cloud LLM Inference need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is LMX Cloud LLM Inference maintained?

The latest release is v0.1.0.

Is LMX Cloud LLM Inference up?

100% of our last 28 checks got an answer. We check remote servers about four times a day.

What can I use instead of LMX Cloud LLM Inference?

Servers from other publishers that do the same job: Agoragentic Agent OS MCP server, Alibaba Cloud DashScope — Qwen MCP server and Lm MCP server. Compare all LMX Cloud LLM Inference alternatives.