What can you do with this server?

MCP HuggingFetch enables high-speed downloading and management of HuggingFace models at 3-5x faster speeds through concurrent downloads, resume support, and intelligent retries. Core Features: * Download Models: Fetch HuggingFace models with specific file selection, revision control, and pattern-based filtering * List Repository Files: Browse contents including file paths, sizes, and types with sorting options (by size, name, or type) * Advanced Filtering: Include/exclude files using glob patterns (e.g., *.json, *.safetensors) and filter by sub-paths * Flexible Configuration: Choose custom download directories, specific Git branches/tags/commits, and force redownload options * Reliability Features: Resume interrupted downloads and automatic retry for failed transfers * Authentication: Access private repositories using HuggingFace tokens via environment variables

Which integrations are available for this server?

Enables downloading and managing models from HuggingFace repositories, with support for file filtering, size limits, and selective downloads

How do I use MCP HuggingFetch?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP HuggingFetch download the ChatTTS model to ./models, only .bin files" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

MCP HuggingFetch

by freefish1218

Overview Schema Related Servers Score Discussions

JavaScript

Hybrid

MCP HuggingFace Fast Download Tool

npm version npm downloads

⚡ High-speed HuggingFace model downloads with concurrent downloading, resume support, and intelligent retry - 3-5x faster than traditional methods. Supports Claude Desktop, Claude Code, Cursor, VS Code, and other clients.

中文版 | 日本語 | Français | Deutsch

📋 Quick Setup

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "huggingfetch": {
      "command": "npx",
      "args": ["-y", "mcp-huggingfetch@latest"],
      "env": {
        "HUGGINGFACE_TOKEN": "your_token_here"
      }
    }
  }
}

Claude Code

Add to .claude/claude_config.json:

{
  "mcpServers": {
    "huggingfetch": {
      "command": "npx",
      "args": ["-y", "mcp-huggingfetch@latest"],
      "env": {
        "HUGGINGFACE_TOKEN": "your_token_here"
      }
    }
  }
}

Cursor / VS Code (Continue Extension)

Add to config.json:

{
  "mcp": [
    {
      "name": "huggingfetch",
      "command": "npx",
      "args": ["-y", "mcp-huggingfetch@latest"],
      "env": {
        "HUGGINGFACE_TOKEN": "your_token_here"
      }
    }
  ]
}

Related MCP server: mcp-hfspace MCP Server

🔑 Get HuggingFace Token

Visit HuggingFace Settings
Create a new Access Token
Copy the token to HUGGINGFACE_TOKEN in the above configuration

🛠 Usage

After configuration, use the following features directly in conversations:

📋 List Files

View and filter repository files:

List JSON files in the 2Noise/ChatTTS repository

🔍 Explore Repository

Understand repository structure:

Explore the directory structure of microsoft/DialoGPT-medium

🔎 Search Files

Find specific files by name:

Search for config files in openai/whisper-large-v3

📥 Download Models

Selectively download required files:

Please download the ChatTTS model to ./models directory

Download microsoft/DialoGPT-medium model, only .bin files

Download openai/whisper-large-v3 model, exclude test files

📝 Available Tools

File Listing (`list_huggingface_files`)

List and filter repository files with pattern matching and sorting.

Parameter	Type	Description	Default
`repo_id`	string	HuggingFace repository ID	-
`revision`	string	Git branch/tag	`"main"`
`pattern`	string	File filter pattern (glob)	-
`exclude`	string	Exclusion pattern	-
`max_files`	number	Maximum files to return	`100`
`sort`	string	Sort by: `name`, `size`, `type`	`"name"`

Repository Explorer (`explore_huggingface_repo`)

Explore repository structure and get hierarchical file tree.

Parameter	Type	Description	Default
`repo_id`	string	HuggingFace repository ID	-
`revision`	string	Git branch/tag	`"main"`
`max_depth`	number	Maximum scan depth	`3`
`tree_view`	boolean	Generate ASCII tree view	`false`

File Search (`search_huggingface_files`)

Search files by name or pattern within repository.

Parameter	Type	Description	Default
`repo_id`	string	HuggingFace repository ID	-
`query`	string	Search keyword or pattern	-
`revision`	string	Git branch/tag	`"main"`
`max_results`	number	Maximum results to return	`50`

Download Tool Options (`download_huggingface_model`)

Parameter	Type	Description	Example
`repo_id`	string	HuggingFace repository ID	`"2Noise/ChatTTS"`
`download_dir`	string	Download directory	`"./models"`
`files`	array	Specific file list	`["model.bin", "config.json"]`
`allow_patterns`	string/array	Include patterns	`".json"` or `[".pt", "*.bin"]`
`ignore_patterns`	string/array	Exclude patterns	`"test_"` or `[".onnx", "test_*"]`
`revision`	string	Git branch/tag	`"main"`, `"v1.0"`
`force_redownload`	boolean	Force re-download	`true`, `false`

🔧 Environment Variables

Variable	Required	Default	Description
`HUGGINGFACE_TOKEN`	✅	-	HuggingFace access token
`HUGGINGFETCH_DOWNLOAD_DIR`	❌	`~/Downloads/huggingface_models`	Default download directory
`HF_HOME`	❌	`~/.cache/huggingface`	Cache directory
`LOG_LEVEL`	❌	`info`	Log level (`debug`, `info`, `warn`, `error`)

❓ FAQ

Q: Token authentication failed, what should I do?
A: Check if HUGGINGFACE_TOKEN is correctly set, ensure the token is valid and has sufficient permissions.

Q: Download speed is slow, what can I do?
A: The tool supports resume downloads and concurrent downloading. Network issues may cause slow speeds, automatic retry will occur.

Q: How to download private models?
A: Ensure your HuggingFace account has access permissions and use a valid token.

Q: What file formats are supported?
A: All file formats on HuggingFace are supported, including .pt, .bin, .safetensors, .json, .txt, etc.

🏗 Development

Prerequisites

Node.js 18+
npm or yarn

Installation

git clone https://github.com/freefish1218/mcp-huggingfetch.git
cd mcp-huggingfetch
npm install

Development Commands

npm run dev          # Run with file watching
npm start           # Run the MCP server
npm run test:basic  # Run basic functionality tests
npm test            # Run Jest unit tests
npm run lint        # Check code style
npm run lint:fix    # Auto-fix linting issues

Release Commands

npm run release:patch  # Release patch version (1.0.0 -> 1.0.1)
npm run release:minor  # Release minor version (1.0.0 -> 1.1.0)
npm run release:major  # Release major version (1.0.0 -> 2.0.0)

The release scripts will automatically:

Run tests and linting
Update version number
Create git tag
Push to GitHub
Publish to npm

For more details, see Release Guide

Building

npm run build       # Build single binary
npm run build:all   # Build for all platforms (Linux, macOS, Windows)

📄 License

MIT License - see LICENSE file for details.

📖 Links

🤝 Contributing

Contributions are welcome! Please see CONTRIBUTING.md for guidelines.

Available Tools

4 tools

download_huggingface_modelC

⚡ 高速下载 HuggingFace 模型到本地

ParametersJSON Schema

Name	Required	Description	Default
`repo_id`	Yes	HuggingFace 仓库 ID（格式：owner/repo）
`download_dir`	No	下载目录（默认：~/Downloads/huggingface_models）
`revision`	No	Git 分支或标签	main
`pattern`	No	下载文件模式（例：*.safetensors）
`exclude`	No	排除文件模式（例：*.bin）
`files`	No	指定下载的文件列表
`max_files`	No	最大下载文件数
`force`	No	强制重新下载
`max_concurrent`	No	最大并发下载数

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions '高速下载' (high-speed download) which hints at performance, but doesn't cover critical aspects like: whether this requires authentication, network usage implications, disk space requirements, error handling, or what happens when files already exist (beyond the 'force' parameter). For a download operation with 9 parameters and no annotations, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise - a single sentence with an emoji. It's front-loaded with the core action and contains no wasted words. Every element (emoji, action, resource, destination) serves a clear purpose in communicating the tool's function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 9 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what the tool returns, error conditions, performance characteristics beyond 'high-speed', or how it interacts with the HuggingFace ecosystem. The user must rely entirely on the input schema for operational details, which is insufficient for proper tool selection and usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all parameters are documented in the schema. The description doesn't add any parameter-specific information beyond what's already in the schema descriptions. It only mentions the general action of downloading models to local storage, which doesn't provide additional semantic context for individual parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('高速下载' - high-speed download) and resource ('HuggingFace 模型' - HuggingFace models) with the destination ('到本地' - to local). It's specific about what the tool does, though it doesn't explicitly differentiate from sibling tools like explore_huggingface_repo or list_huggingface_files beyond the download action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools, prerequisites, or specific scenarios where this download tool is preferred over other approaches. The user must infer usage from the action alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

explore_huggingface_repoB

探索 HuggingFace 仓库的目录结构，返回层级化的文件树

ParametersJSON Schema

Name	Required	Description	Default
`repo_id`	Yes	HuggingFace 仓库 ID（格式：owner/repo）
`revision`	No	Git 分支或标签	main
`max_depth`	No	最大扫描深度
`tree_view`	No	是否生成ASCII树形视图

TDQS

B3.3/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool explores directory structure and returns a hierarchical file tree, but lacks details on permissions, rate limits, error handling, or what happens with large repositories. For a tool with 4 parameters and no annotation coverage, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence in Chinese that front-loads the core purpose. Every word earns its place, with no redundant or vague phrasing, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters, no annotations, and no output schema, the description is minimally adequate but incomplete. It covers the basic purpose but lacks behavioral context (e.g., performance, limitations) and output details. For a tool with moderate complexity, it should do more to compensate for missing structured data.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents all 4 parameters. The description adds no additional parameter semantics beyond what the schema provides (e.g., it doesn't explain how 'max_depth' affects traversal or what 'tree_view' output looks like). Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('探索' meaning explore), the resource ('HuggingFace 仓库的目录结构'), and the output format ('返回层级化的文件树'). It distinguishes from sibling tools like 'download_huggingface_model' (which downloads), 'list_huggingface_files' (which might list without hierarchy), and 'search_huggingface_files' (which searches).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus its siblings. It doesn't mention alternatives like 'list_huggingface_files' for flat listings or 'search_huggingface_files' for filtered searches, nor does it specify prerequisites or exclusions. Usage is implied only by the action described.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_huggingface_filesC

列出 HuggingFace 仓库中的文件，支持过滤和排序

ParametersJSON Schema

Name	Required	Description	Default
`repo_id`	Yes	HuggingFace 仓库 ID（格式：owner/repo）
`revision`	No	Git 分支或标签	main
`pattern`	No	Glob 模式过滤（例：*.safetensors）
`exclude`	No	排除模式（例：*.bin）
`max_files`	No	最大文件数
`max_depth`	No	最大递归深度
`sort`	No	排序方式	name

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions filtering and sorting capabilities, but does not cover critical aspects such as rate limits, authentication requirements, error handling, or pagination behavior. For a tool with 7 parameters and no annotations, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise—a single sentence in Chinese that directly states the tool's function and key features (filtering and sorting). It is front-loaded with the core purpose and wastes no words, making it efficient for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (7 parameters, no annotations, no output schema), the description is insufficient. It lacks details on behavioral traits, output format, error conditions, and differentiation from siblings. While the schema covers parameters well, the description does not compensate for the missing contextual information needed for effective tool invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, meaning all parameters are well-documented in the input schema. The description adds minimal value by hinting at filtering and sorting, but does not provide additional semantics beyond what the schema already explains. This meets the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: '列出 HuggingFace 仓库中的文件' (list files in a HuggingFace repository). It specifies the action (list) and resource (files in a HuggingFace repo), making it easy to understand. However, it does not explicitly differentiate from sibling tools like 'explore_huggingface_repo' or 'search_huggingface_files', which might have overlapping functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It mentions '支持过滤和排序' (supports filtering and sorting), but does not specify scenarios, prerequisites, or exclusions. With sibling tools like 'search_huggingface_files' available, the lack of differentiation leaves the agent without clear usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_huggingface_filesC

在 HuggingFace 仓库中搜索特定文件

ParametersJSON Schema

Name	Required	Description	Default
`repo_id`	Yes	HuggingFace 仓库 ID（格式：owner/repo）
`query`	Yes	搜索关键词或模式
`revision`	No	Git 分支或标签	main
`max_results`	No	最大结果数

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool searches for files but doesn't describe what happens (e.g., returns file paths/metadata, pagination behavior, error handling for invalid repos). It lacks details on rate limits, authentication needs, or whether it's read-only (implied but not explicit).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence in Chinese that directly states the tool's purpose without unnecessary words. It's front-loaded with the core action ('搜索') and resource, making it easy to parse. Every part of the sentence contributes to understanding the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 4 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., list of file names, metadata), error conditions, or behavioral constraints. For a search tool with multiple inputs, more context is needed to use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, providing clear details for all 4 parameters (repo_id format, query purpose, revision default, max_results default). The description adds no additional parameter semantics beyond the schema, so it meets the baseline of 3 for high schema coverage without compensating value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('搜索' - search) and resource ('HuggingFace 仓库中...文件' - files in HuggingFace repository). It distinguishes from siblings like 'download_huggingface_model' (downloads models) and 'list_huggingface_files' (lists files without search). However, it doesn't explicitly differentiate from 'explore_huggingface_repo', which might have overlapping functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when to prefer 'search_huggingface_files' over 'list_huggingface_files' (e.g., for filtered results) or 'explore_huggingface_repo' (e.g., for broader repository exploration). There's no context about prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv1.0.0Jan 3, 2026

Changeddownload_huggingface_model14 fields changed

removedInput schema / properties / allow_patterns

Removed value: -{
-  "description": "允许下载的文件模式（glob 语法），支持单个或多个模式",
-  "examples": [
-    "*.json",
-    [
-      "*.safetensors",
-      "*.bin"
-    ],
-    "**/model-*.safetensors"
-  ],
-  "oneOf": [
-    {
-      "type": "string"
-    },
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    }
-  ]
-}

changedInput schema / properties / download_dir / description

Previous value: -"下载保存目录（支持相对/绝对路径），默认：~/Downloads/huggingface_models"New value: +"下载目录（默认：~/Downloads/huggingface_models）"

addedInput schema / properties / exclude

Added value: +{
+  "description": "排除文件模式（例：*.bin）",
+  "type": "string"
+}

changedInput schema / properties / files / description

Previous value: -"指定下载的具体文件列表（精确匹配文件路径）"New value: +"指定下载的文件列表"

removedInput schema / properties / files / examples

Removed value: -[
-  [
-    "config.json",
-    "model.safetensors"
-  ]
-]

addedInput schema / properties / force

Added value: +{
+  "default": false,
+  "description": "强制重新下载",
+  "type": "boolean"
+}

removedInput schema / properties / force_redownload

Removed value: -{
-  "default": false,
-  "description": "强制重新下载（忽略本地缓存）",
-  "type": "boolean"
-}

removedInput schema / properties / ignore_patterns

Removed value: -{
-  "description": "忽略的文件模式（glob 语法），支持单个或多个模式",
-  "examples": [
-    "*.h5",
-    [
-      "*.msgpack",
-      "*.ckpt"
-    ],
-    "vocab.json"
-  ],
-  "oneOf": [
-    {
-      "type": "string"
-    },
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    }
-  ]
-}

addedInput schema / properties / max_concurrent

Added value: +{
+  "default": 5,
+  "description": "最大并发下载数",
+  "type": "integer"
+}

addedInput schema / properties / max_files

Added value: +{
+  "default": 100,
+  "description": "最大下载文件数",
+  "type": "integer"
+}

addedInput schema / properties / pattern

Added value: +{
+  "description": "下载文件模式（例：*.safetensors）",
+  "type": "string"
+}

changedInput schema / properties / repo_id / description

Previous value: -"HuggingFace 仓库 ID，格式：用户名/模型名"New value: +"HuggingFace 仓库 ID（格式：owner/repo）"

changedInput schema / properties / repo_id / examples

Previous value: -[
-  "2Noise/ChatTTS",
-  "microsoft/DialoGPT-medium",
-  "openai/whisper-large-v3",
-  "meta-llama/Meta-Llama-3.1-8B"
-]New value: +[
+  "2Noise/ChatTTS",
+  "microsoft/DialoGPT-medium"
+]

changedInput schema / properties / revision / description

Previous value: -"Git 分支、标签或 commit hash，默认：main"New value: +"Git 分支或标签"

Addedexplore_huggingface_repo

Changedlist_huggingface_files10 fields changed

addedInput schema / properties / exclude

Added value: +{
+  "description": "排除模式（例：*.bin）",
+  "type": "string"
+}

addedInput schema / properties / max_depth

Added value: +{
+  "default": 3,
+  "description": "最大递归深度",
+  "type": "integer"
+}

addedInput schema / properties / max_files

Added value: +{
+  "default": 100,
+  "description": "最大文件数",
+  "type": "integer"
+}

removedInput schema / properties / path

Removed value: -{
-  "description": "仓库内的子路径（可选，用于浏览特定目录）",
-  "type": "string"
-}

changedInput schema / properties / pattern / description

Previous value: -"文件名过滤模式（glob 模式），例如: *.safetensors, *.json"New value: +"Glob 模式过滤（例：*.safetensors）"

changedInput schema / properties / repo_id / description

Previous value: -"HuggingFace 仓库 ID，格式：用户名/模型名"New value: +"HuggingFace 仓库 ID（格式：owner/repo）"

changedInput schema / properties / repo_id / examples

Previous value: -[
-  "2Noise/ChatTTS",
-  "microsoft/DialoGPT-medium",
-  "openai/whisper-large-v3"
-]New value: +[
+  "2Noise/ChatTTS",
+  "microsoft/DialoGPT-medium"
+]

changedInput schema / properties / revision / description

Previous value: -"Git 分支或标签，默认为 main"New value: +"Git 分支或标签"

addedInput schema / properties / sort

Added value: +{
+  "default": "name",
+  "description": "排序方式",
+  "enum": [
+    "name",
+    "size",
+    "type"
+  ],
+  "type": "string"
+}

removedInput schema / properties / sort_by

Removed value: -{
-  "default": "name",
-  "description": "排序方式: size（按大小）, name（按名称）, type（按类型）",
-  "enum": [
-    "size",
-    "name",
-    "type"
-  ],
-  "type": "string"
-}

Addedsearch_huggingface_files

2 tool updatesAug 15, 2025
- First observeddownload_huggingface_model
- First observedlist_huggingface_files

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.2/5.0

Disambiguation3/5

The tools have overlapping purposes that could cause confusion. 'explore_huggingface_repo' and 'list_huggingface_files' both deal with repository file listings, though 'explore' emphasizes hierarchical structure while 'list' focuses on filtering and sorting. 'search_huggingface_files' is distinct for searching, but the boundary between listing and exploring is unclear without more context in descriptions.

Naming Consistency5/5

Tool names follow a highly consistent verb_noun pattern with 'huggingface' as a common prefix. All tools use snake_case and start with an action verb (download, explore, list, search) followed by the target noun, making them predictable and easy to understand.

Tool Count4/5

Four tools is a reasonable number for a server focused on HuggingFace operations, covering downloading, exploring, listing, and searching. It's slightly thin but well-scoped for basic interactions, with no obvious bloat or missing core functions given the domain.

Completeness3/5

The tool set covers key operations for accessing HuggingFace repositories but has notable gaps. There's no support for uploading, updating, or deleting models/files, and no tools for model inference or metadata retrieval, which are common in HuggingFace workflows. This limits agents to read-only and download tasks.

Maintenance

ActivityInactive

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

hugging-bay B
io.github.barneywohl
Verified open AI artifact search, trust evidence, downloads, and agent workflows from Hugging Bay.
AI & Machine Learning Search
2
suma-memory A
io.github.sumanaddanki
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Knowledge & Memory Developer Tools Autonomous Agents
2
SirroOAuth
io.github.Jonathanmberg
Shared memory for AI coding agents. Save once, reuse from Cursor, Claude Code, Codex.
Knowledge & Memory Developer Tools
1
Hugging Face A
co.huggingface
Connect to Hugging Face Hub and thousands of Gradio AI Applications
RAG Systems Developer Tools
42

Related MCP Servers

mcp-hfspace
Image & Video Processing Audio Processing App Automation
evalstate
A
license
C
quality
C
maintenance
Use HuggingFace Spaces directly from Claude. Use Open Source Image Generation, Chat, Vision tasks and more. Supports Image, Audio and text uploads/downloads.
Updated a year ago (2025-06-13 17:05 UTC)
3
928
387
MIT
mcp-hfspace MCP Server
Agent Orchestration Image & Video Processing Speech Processing
xiyuefox
A
license
C
quality
D
maintenance
Connects Claude Desktop to Hugging Face Spaces with minimal setup, enabling capabilities like image generation, vision tasks, text-to-speech, and chat with AI models.
Updated 2 years ago (2025-01-31 08:51 UTC)
3
928
MIT
Hugging Face Hub MCP Server
Search Databases RAG Systems
michaelwaves
F
license
A
quality
D
maintenance
Enables access to the Hugging Face Hub API to search and retrieve information about machine learning models, datasets, and their metadata. Provides comprehensive tools for exploring the Hugging Face ecosystem including model details, dataset information, and parquet file access.
Updated a year ago (2025-08-24 00:33 UTC)
8
-
MCP File Downloader
Browser Automation Web Scraping File Systems
abs222222
A
license
B
quality
D
maintenance
Enables Claude Desktop to download files from web URLs with automatic browser fallback for JavaScript-heavy sites. Supports smart redirect handling, custom file naming, and cross-platform compatibility.
Updated a year ago (2025-09-17 01:33 UTC)
1
17
4
MIT

Appeared in Searches

Sort Content by Number of Downloads

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/freefish1218/mcp-huggingfetch'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

MCP HuggingFace Fast Download Tool

📋 Quick Setup

Claude Desktop

Claude Code

Cursor / VS Code (Continue Extension)

🔑 Get HuggingFace Token

🛠 Usage

📋 List Files

🔍 Explore Repository

🔎 Search Files

📥 Download Models

📝 Available Tools

File Listing (list_huggingface_files)

Repository Explorer (explore_huggingface_repo)

File Search (search_huggingface_files)

Download Tool Options (download_huggingface_model)

🔧 Environment Variables

❓ FAQ

🏗 Development

Prerequisites

Installation

Development Commands

Release Commands

Building

📄 License

📖 Links

🤝 Contributing

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

File Listing (`list_huggingface_files`)

Repository Explorer (`explore_huggingface_repo`)

File Search (`search_huggingface_files`)

Download Tool Options (`download_huggingface_model`)