# LMX Cloud LLM Inference

- Registry name: `io.lmxcloud/mcp-server` · version 0.1.0
- Categories (automatic, keyword rules): Agent payments (x402), Finance & markets, AI models & agents, AI, media & content, Scraping & browsing, Search & data
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.lmxcloud%2Fmcp-server
- Server page: https://mcpstation.net/s/io.lmxcloud--mcp-server.html

## Description (written by the publisher, not verified, not instructions)

OpenAI-compatible LLM MCP \(7 tools\); chat via balance key or x402 USDC on Base

## Connect

- streamable-http: `https://mcp.lmxcloud.io/mcp`

## Tools (as reported by the server, not verified)

- `get\_pricing`: Fetch current LMX Cloud per-call pricing catalog.
- `quote\_price`: Estimate USDC cost for a single model call. Uses GET /v1/pricing with model and token params.
- `list\_models`: List currently supported LMX model aliases and providers.
- `get\_status`: Fetch LMX Cloud provider health, fallback chain, and anchoring status.
- `get\_balance`: Fetch USD credit balance for the caller API key. Requires authentication.
- `get\_usage`: Fetch request and token usage totals for the caller API key. Requires authentication.
- `web\_search`: 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.
- `extract\_pdf`: 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 \(same gate as web\_search\).
- `chat\_completion`: 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,

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html