Hologram Model Hub

Find open models and get download links with the SHA-256 each file must have.

我该使用它吗

质量与安全性

A
描述质量
90%
模式完整度
88%
命名质量
93%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现(1)

  • LOWTool 'get_model' description lacks action verb在 get_model 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~437token 数(工具定义)
~998 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.34%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "model-hub": {
      "url": "https://hub.uor.foundation/mcp"
    }
  }
}

远程端点

https://hub.uor.foundation/mcpstreamable-http

它能做什么

工具清单

工具(3)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search_models(query, task, license, format, max_weights_gb, ...)

Find open models in the hub's index. Every result has all of its files addressed by SHA-256. Returns id, task, library, licence, parameters, weight size, downloads and where the bytes live.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Part of the model id, e.g. 'qwen' or 'whisper'."
    },
    "task": {
      "type": "string",
      "description": "Hugging Face pipeline tag, e.g. text-generation, text-to-speech, feature-extraction."
    },
    "license": {
      "type": "string",
      "description": "SPDX-style licence id, e.g. apache-2.0, mit."
    },
    "format": {
      "type": "string",
      "description": "gguf, safetensors, mlx, onnx …"
    },
    "max_weights_gb": {
      "type": "number",
      "description": "Upper bound on the total size of the weights."
    },
    "sort": {
      "type": "string",
      "enum": [
        "trending",
        "downloads",
        "likes",
        "newest"
      ],
      "default": "trending"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10
    }
  },
  "additionalProperties": false
}
🟢get_model(id)

The pinned revision of one model, its files with size and SHA-256, its GGUF quantisations if any, and its sources with their current health.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "org/name, as on Hugging Face."
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
🟢resolve_file(id, path, quant)

Where to download one file of a model right now, the SHA-256 it must have, how to check it, and the commands that hand it to an engine (hf, Ollama, llama.cpp). Give either a path or, for GGUF models, a quantisation such as Q4_K_M.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "path": {
      "type": "string"
    },
    "quant": {
      "type": "string"
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}

社区

评价此服务器

证据

最近观测

已验证未记录版本3 个工具
已验证未记录版本3 个工具