Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "lmxcloud": {
      "type": "http",
      "url": "https://mcp.lmxcloud.io/mcp"
    }
  }
}

claude mcp add --transport http lmxcloud https://mcp.lmxcloud.io/mcp

[mcp_servers.lmxcloud]
url = "https://mcp.lmxcloud.io/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lmxcloud": {
      "type": "remote",
      "url": "https://mcp.lmxcloud.io/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "lmxcloud": {
      "type": "http",
      "url": "https://mcp.lmxcloud.io/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=lmxcloud&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmxteGNsb3VkLmlvL21jcCJ9"
}

{
  "servers": {
    "lmxcloud": {
      "type": "http",
      "url": "https://mcp.lmxcloud.io/mcp"
    }
  }
}

{
  "mcpServers": {
    "lmxcloud": {
      "httpUrl": "https://mcp.lmxcloud.io/mcp"
    }
  }
}

extensions:
  "lmxcloud":
    enabled: true
    name: "lmxcloud"
    type: streamable_http
    uri: "https://mcp.lmxcloud.io/mcp"
    timeout: 300

Quality 79 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene71 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_pricing (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); quote_price (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); web_search (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
pass
tools.token_costabout 1,402 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changesno tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

9 tools, about 1,402 tokens to load them all · tool set e610c6cf36ff · checked 2026-10-20 11:08 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 73 / 100

no-repository

provenance45

liveness100

freshness65

hygiene80

+dns-namespace +reachable +uptime-99% ~updated-98d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://mcp.lmxcloud.io/mcp` streamable-http	none	yes	99%	384 ms	2025-11-25	2026-10-20

Tools (9)

`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, qwen-3.6-35b, or qwen-3.5-35b.
`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).
`get_balance`	Fetch USD credit balance for the caller API key. Requires authentication.
`get_pricing`	Fetch current LMX Cloud per-call pricing catalog.
`get_status`	Fetch LMX Cloud provider health, fallback chain, and anchoring status.
`get_usage`	Fetch request and token usage totals for the caller API key. Requires authentication.
`list_models`	List currently supported LMX model aliases and providers.
`quote_price`	Estimate USDC cost for a single model call. Uses GET /v1/pricing with model and token params.
`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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "io.lmxcloud/mcp-server",
  "title": "LMX Cloud LLM Inference",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.lmxcloud.io/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.1.0",
  "description": "OpenAI-compatible LLM MCP (7 tools); chat via balance key or x402 USDC on Base"
}