MCP MeasureMCP Measure

インデックス観測済み

LMX Cloud LLM Inference

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

使うべきか

品質と安全性

A
説明の品質
98%
スキーマの完全性
93%
命名の品質
91%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~1,508トークン数（ツール定義）
~1.4 KB一般的なレスポンスサイズ
注意への影響は中程度（128k コンテキストの 1.18%）

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "mcp-server": {
      "url": "https://mcp.lmxcloud.io/mcp"
    }
  }
}

リモートエンドポイント

https://mcp.lmxcloud.io/mcpstreamable-http

できること

ツール一覧

ツール（9）

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢get_pricing(api_key)

Fetch current LMX Cloud per-call pricing catalog.

入力スキーマ

{
  "type": "object",
  "properties": {
    "api_key": {
      "type": "string",
      "pattern": "^lmx_[0-9a-f]{32}$",
      "description": "Optional LMX API key (lmx_...). Prefer MCP client Authorization header or env; use this to override per call."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢quote_price(model, max_tokens, prompt_tokens, api_key)

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

入力スキーマ

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "minLength": 1,
      "description": "Model alias to quote (e.g. llama-3-70b)."
    },
    "max_tokens": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 4096,
      "description": "Optional max completion tokens for the quote."
    },
    "prompt_tokens": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 128000,
      "description": "Optional estimated prompt tokens (default: 1)."
    },
    "api_key": {
      "type": "string",
      "pattern": "^lmx_[0-9a-f]{32}$",
      "description": "Optional LMX API key (lmx_...). Prefer MCP client Authorization header or env; use this to override per call."
    }
  },
  "required": [
    "model"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_models(api_key)

List currently supported LMX model aliases and providers.

入力スキーマ

{
  "type": "object",
  "properties": {
    "api_key": {
      "type": "string",
      "pattern": "^lmx_[0-9a-f]{32}$",
      "description": "Optional LMX API key (lmx_...). Prefer MCP client Authorization header or env; use this to override per call."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_status(api_key)

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

入力スキーマ

{
  "type": "object",
  "properties": {
    "api_key": {
      "type": "string",
      "pattern": "^lmx_[0-9a-f]{32}$",
      "description": "Optional LMX API key (lmx_...). Prefer MCP client Authorization header or env; use this to override per call."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_balance(api_key)

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

入力スキーマ

{
  "type": "object",
  "properties": {
    "api_key": {
      "type": "string",
      "pattern": "^lmx_[0-9a-f]{32}$",
      "description": "Optional LMX API key (lmx_...). Prefer MCP client Authorization header or env; use this to override per call."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_usage(api_key)

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

入力スキーマ

{
  "type": "object",
  "properties": {
    "api_key": {
      "type": "string",
      "pattern": "^lmx_[0-9a-f]{32}$",
      "description": "Optional LMX API key (lmx_...). Prefer MCP client Authorization header or env; use this to override per call."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢web_search(query, max_results, api_key)

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.

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "Search query string."
    },
    "max_results": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20,
      "description": "Max results to return (1–20, default 5)."
    },
    "api_key": {
      "type": "string",
      "pattern": "^lmx_[0-9a-f]{32}$",
      "description": "Optional LMX API key (lmx_...). Prefer MCP client Authorization header or env; use this to override per call."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢extract_pdf(file_url, file_base64, api_key)

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).

入力スキーマ

{
  "type": "object",
  "properties": {
    "file_url": {
      "type": "string",
      "minLength": 1,
      "description": "Optional https URL to fetch the PDF from. Provide this and/or file_base64."
    },
    "file_base64": {
      "type": "string",
      "minLength": 1,
      "description": "Optional base64-encoded PDF bytes (raw base64 or data:application/pdf;base64,...). Provide this and/or file_url."
    },
    "api_key": {
      "type": "string",
      "pattern": "^lmx_[0-9a-f]{32}$",
      "description": "Optional LMX API key (lmx_...). Prefer MCP client Authorization header or env; use this to override per call."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪chat_completion(prompt, image_url, images, model, max_tokens, ...)

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.

入力スキーマ

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "minLength": 1,
      "description": "User prompt to send to the selected model."
    },
    "image_url": {
      "type": "string",
      "minLength": 1,
      "description": "Optional image as an https URL or data:image/...;base64,... URI. Requires a vision-capable model."
    },
    "images": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "description": "Optional additional images (https URLs or data:image/...;base64,... URIs). Requires a vision-capable model."
    },
    "model": {
      "type": "string",
      "description": "Optional model name or alias. Uses default if omitted."
    },
    "max_tokens": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 4096,
      "description": "Optional max completion tokens."
    },
    "temperature": {
      "type": "number",
      "minimum": 0,
      "maximum": 2,
      "description": "Optional sampling temperature."
    },
    "api_key": {
      "type": "string",
      "pattern": "^lmx_[0-9a-f]{32}$",
      "description": "Optional LMX API key (lmx_...). Prefer MCP client Authorization header or env; use this to override per call."
    }
  },
  "required": [
    "prompt"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

推奨プロンプト

search_research
Search for information about [topic] using LMX Cloud LLM Inference
想定されるツール: web_search
find_specific
Find [specific item] using LMX Cloud LLM Inference
想定されるツール: web_search
retrieve_data
Get details about [item] from LMX Cloud LLM Inference
想定されるツール: get_pricing
fetch_info
Fetch [information type] using LMX Cloud LLM Inference
想定されるツール: get_pricing
list_items
List all [items] available in LMX Cloud LLM Inference
想定されるツール: list_models

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 9 件
検証済みバージョンは記録されていませんツール 9 件