Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@M-Team MCP Server search for the movie Inception and show me the top results"
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-server-mteam 是一个基于 FastMCP 框架开发的 MCP（Model Context Protocol）服务器，让 AI 助手（如 Claude、Cursor 等）能够直接调用 M-Team（馒头）私有种子站的 API，实现资源搜索、种子详情获取和种子文件下载功能。
工具 | 说明 |
| 按关键词搜索种子资源，支持多种分类模式 |
| 根据种子 ID 获取种子详细信息 |
| 根据种子 ID 下载 |
Python 3.10 或以上版本（或安装 uv 由 uv 自动管理）
M-Team 账号及 API Key
方式一：使用 uv 零安装运行（推荐）
uvx mcp-server-mteam首次运行会自动从 PyPI 拉取并执行，无需手动安装。若需持久安装：
uv tool install mcp-server-mteam方式二：从源码安装
克隆或下载本项目：
git clone https://github.com/07freedom/mcp-server-mteam.git
cd mcp-server-mteam安装依赖（使用 uv）：
uv sync或使用 pip：
pip install -e .配置 API Key：
复制 .env_example 为 .env，并填入你的 M-Team API Key：
cp .env_example .env编辑 .env 文件：
MTEAM_API_KEY="your_mteam_api_key_here"你可以在 M-Team 网站的个人设置 → API Key 处获取 API Key。
变量名 | 默认值 | 说明 |
| （必填） | M-Team API 鉴权密钥 |
|
| API 根地址 |
|
| 种子文件保存目录 |
在 MCP 客户端配置文件中添加：
{
"mcpServers": {
"mteam": {
"command": "uvx",
"args": ["mcp-server-mteam"],
"env": {
"MTEAM_API_KEY": "your_mteam_api_key_here"
}
}
}
}若从源码运行，可将
command改为uv，args设为["run", "mcp-server-mteam"]，或在项目目录下使用["run", "/path/to/mcp-server-mteam/server.py"]。也可不在配置中填写env，在项目目录创建.env文件即可。
# 使用 uvx（推荐，零安装）
uvx mcp-server-mteam或
# 项目内运行（需先 uv sync）
uv run mcp-server-mteam或
# pip 安装后
mcp-server-mteamuv run python server.py
# 或
uv run mcp-server-mteamsearch_torrents — 搜索种子搜索 M-Team 上的种子资源。
输入参数
参数 | 类型 | 必填 | 默认值 | 说明 |
| string | 是 | — | 搜索关键词，支持中文和英文 |
| string | 否 |
| 搜索模式，可选值见下表 |
| integer | 否 |
| 页码（从 1 开始） |
| integer | 否 |
| 每页结果数（最大 100） |
mode 可选值
值 | 说明 |
| 普通资源 |
| 成人资源 |
| 电影 |
| 音乐 |
| 剧集 |
| 瀑布流 |
| RSS |
| 排行榜 |
| 全部 |
输出示例
Search results for "黑暗骑士" (mode=normal)
Total: 25 | Page 1, showing 20 items
------------------------------------------------------------
[1125330] The Dark Knight 2008 IMAX UHD BluRay 2160p DDP 5.1 DV HDR x265-hallowed
Size: 17.74 GB Seeders: 17 Leechers: 0
Labels: 中字, 4k, hdr10, DoVi Discount: PERCENT_50
IMDB: 9.1 Douban: 9.2
...get_torrent_detail — 获取种子详情根据种子 ID 获取完整的种子信息。
输入参数
参数 | 类型 | 必填 | 说明 |
| string | 是 | 种子 ID，如 |
输出示例
Torrent Detail: [1125330]
============================================================
Name : The Dark Knight 2008 IMAX UHD BluRay 2160p DDP 5.1 DV HDR x265-hallowed
Description: 蝙蝠侠：黑暗骑士崛起|类型: 剧情 / 动作 / 科幻 / 惊悚 / 犯罪
Size : 17.74 GB (1 file(s))
Labels : 中字, 4k, hdr10, DoVi
Discount : PERCENT_50
Seeders : 17 Leechers: 0 Completed: 71
Created : 2026-01-29 15:16:42
Visible : True Banned: False
IMDB : https://www.imdb.com/title/tt0468569/ Rating: 9.1
Douban : https://movie.douban.com/subject/1851857/ Rating: 9.2download_torrent — 下载种子文件根据种子 ID 下载 .torrent 文件。
输入参数
参数 | 类型 | 必填 | 说明 |
| string | 是 | 种子 ID，如 |
输出示例
成功时：
Torrent saved to: /home/user/mcp-server-mteam/seed/[M-TEAM]The.Dark.Knight.2008.IMAX.UHD.BluRay.2160p.DDP.5.1.DV.HDR.x265-hallowed.torrent失败时：
Failed to get download token: {'code': '403', 'message': 'Forbidden'}本工具仅供个人学习和合法使用，请遵守 M-Team 的使用条款。
API Key 属于敏感信息，请勿将 .env 文件提交到公开代码仓库。
下载种子功能需要账号有足够的权限。
Related MCP server: yarr-media-stack-mcp
M-Team MCP is a FastMCP-based MCP (Model Context Protocol) server that allows AI assistants (Claude, Cursor, etc.) to interact with the M-Team private torrent tracker API — enabling torrent search, detail retrieval, and .torrent file downloads.
Tool | Description |
| Search torrents by keyword with optional category mode |
| Get full details for a torrent by its ID |
| Download a |
Python 3.10 or higher (or install uv for automatic management)
An M-Team account with a valid API Key
Option 1: Run with uv (no install, recommended)
uvx mcp-server-mteamOn first run, uv will fetch from PyPI and execute without manual install. To install persistently:
uv tool install mcp-server-mteamOption 2: Install from source
Clone or download this project:
git clone https://github.com/07freedom/mcp-server-mteam.git
cd mcp-server-mteamInstall dependencies (with uv):
uv syncOr with pip:
pip install -e .Configure your API Key:
Copy .env_example to .env and fill in your M-Team API Key:
cp .env_example .envEdit .env:
MTEAM_API_KEY="your_mteam_api_key_here"You can obtain your API Key from M-Team's user settings page under API Key.
Variable | Default | Description |
| (required) | M-Team API authentication key |
|
| API base URL |
|
| Directory to save downloaded torrent files |
Add the following to your MCP client config file:
{
"mcpServers": {
"mteam": {
"command": "uvx",
"args": ["mcp-server-mteam"],
"env": {
"MTEAM_API_KEY": "your_mteam_api_key_here"
}
}
}
}For source install, use
"command": "uv"with"args": ["run", "mcp-server-mteam"], or["run", "/path/to/mcp-server-mteam/server.py"]in the project directory. You can also omitenvand use a.envfile in the project directory.
# With uvx (recommended, no install)
uvx mcp-server-mteamor
# From project (after uv sync)
uv run mcp-server-mteamor
# After pip install
mcp-server-mteamuv run python server.py
# or
uv run mcp-server-mteamsearch_torrents — Search TorrentsSearch for torrents on M-Team by keyword.
Input Parameters
Parameter | Type | Required | Default | Description |
| string | Yes | — | Search keyword (Chinese or English) |
| string | No |
| Search mode (see table below) |
| integer | No |
| Page number (1-based) |
| integer | No |
| Results per page (max 100) |
Available mode Values
Value | Description |
| General resources |
| Adult content |
| Movies |
| Music |
| TV shows |
| Waterfall view |
| RSS |
| Rankings |
| All categories |
Example Output
Search results for "The Dark Knight" (mode=movie)
Total: 25 | Page 1, showing 20 items
------------------------------------------------------------
[1125330] The Dark Knight 2008 IMAX UHD BluRay 2160p DDP 5.1 DV HDR x265-hallowed
Size: 17.74 GB Seeders: 17 Leechers: 0
Labels: 中字, 4k, hdr10, DoVi Discount: PERCENT_50
IMDB: 9.1 Douban: 9.2
...get_torrent_detail — Get Torrent DetailsRetrieve full information for a specific torrent.
Input Parameters
Parameter | Type | Required | Description |
| string | Yes | Torrent ID, e.g. |
Example Output
Torrent Detail: [1125330]
============================================================
Name : The Dark Knight 2008 IMAX UHD BluRay 2160p DDP 5.1 DV HDR x265-hallowed
Description: 蝙蝠侠：黑暗骑士崛起|类型: 剧情 / 动作 / 科幻 / 惊悚 / 犯罪
Size : 17.74 GB (1 file(s))
Labels : 中字, 4k, hdr10, DoVi
Discount : PERCENT_50
Seeders : 17 Leechers: 0 Completed: 71
Created : 2026-01-29 15:16:42
Visible : True Banned: False
IMDB : https://www.imdb.com/title/tt0468569/ Rating: 9.1
Douban : https://movie.douban.com/subject/1851857/ Rating: 9.2download_torrent — Download Torrent FileDownload a .torrent file for the given torrent ID.
Input Parameters
Parameter | Type | Required | Description |
| string | Yes | Torrent ID, e.g. |
Example Output
On success:
Torrent saved to: /home/user/mcp-server-mteam/seed/[M-TEAM]The.Dark.Knight.2008.IMAX.UHD.BluRay.2160p.DDP.5.1.DV.HDR.x265-hallowed.torrentOn failure:
Failed to get download token: {'code': '403', 'message': 'Forbidden'}This project is for personal and lawful use only. Please comply with M-Team's Terms of Service.
Your API Key is sensitive — never commit your .env file to a public repository.
Torrent downloads require sufficient account privileges on M-Team.
Download a .torrent file for the given torrent ID.
This tool first obtains a temporary download token from the M-Team API, then downloads the .torrent file and saves it to the configured download directory (default: ./seed/).
Args: torrent_id: The numeric torrent ID (e.g. "1125330").
Returns: The absolute path to the saved .torrent file on success, or an error message on failure.
| Name | Required | Description | Default |
|---|---|---|---|
| torrent_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description reveals internal steps (token acquisition, file save) and return value (path or error). It does not mention permissions or side effects, but for a download tool, this is adequate. No annotations are present, so description carries the full burden.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a clear header and structured details (Args, Returns). It is front-loaded with the main action. Slightly verbose in explaining process, but overall efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given one parameter, no annotations, and an existing output schema, the description covers the tool's purpose, process, parameter, and return value. It could include more on error handling, but it is sufficiently complete for this simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'torrent_id' has no schema description, but the description adds meaning by specifying it is numeric and giving an example ('1125330'). This compensates for the 0% schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Download a .torrent file for the given torrent ID,' which is a specific verb and resource. It distinguishes from siblings 'get_torrent_detail' and 'search_torrents' as these serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description outlines the process (obtain token, download, save to directory) and implies use for downloading torrent files. It does not explicitly state when not to use or alternatives, but the context is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed information for a specific torrent by its ID.
Args: torrent_id: The numeric torrent ID (e.g. "1125330").
Returns: A formatted string with full torrent details including name, size, description, ratings, file count, seeder/leecher counts, etc.
| Name | Required | Description | Default |
|---|---|---|---|
| torrent_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so description carries burden. Lists return fields (name, size, etc.) indicating read-only behavior, but doesn't disclose error handling, permissions, or rate limits. Adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise, front-loaded purpose, clear Args/Returns structure. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Complete for a simple one-param read tool with no annotations: covers purpose, parameter, return. Lacks error info but acceptable for given complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but description adds full meaning: param is numeric ID, with example and explanation. Alone it fully documents the parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it retrieves detailed info for a specific torrent by ID, with a specific verb and resource. Distinguishes from siblings (search_torrents, download_torrent) by focusing on detail retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies use when you have a torrent ID via 'by its ID' and example, but no explicit when-not or alternatives. Context is clear but lacks exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search torrents on M-Team by keyword.
Args: keyword: Search keyword (supports Chinese / English). mode: Search mode. One of: normal, adult, movie, music, tvshow, waterfall, rss, rankings, all. Defaults to "normal". page_number: Page number (1-based). Defaults to 1. page_size: Number of results per page (max 100). Defaults to 20.
Returns: A formatted string listing matching torrents with their IDs, names, sizes, seeder/leecher counts, labels, ratings, and discount info.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | normal | |
| keyword | Yes | ||
| page_size | No | ||
| page_number | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It describes parameters, return format, and the search action, which is inherently read-only. However, it does not explicitly state that it is non-destructive, nor does it mention any potential side effects, auth requirements, or rate limits. The transparency is adequate but not exceptional.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured with a one-line summary followed by clear Args and Returns sections. Every sentence adds value; there is no redundant or missing information. It is appropriately sized and front-loaded with the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
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, but an output schema, the description covers all necessary aspects: the search context (M-Team), parameter details, and return format (listing IDs, names, sizes, etc.). It is complete enough for an agent to use correctly, and the output schema is leveraged by describing the return value.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage, but the description fully compensates by explaining each parameter: keyword supports Chinese/English, mode lists all allowed values (including default), page_number and page_size have defaults and max for page_size. This adds significant meaning beyond the raw schema types and defaults.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search torrents on M-Team by keyword', specifying the verb (search), resource (torrents on M-Team), and key parameter (keyword). It distinguishes itself from sibling tools like download_torrent (download) and get_torrent_detail (get detail of a single torrent), making it unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives. It implies usage through the name and siblings, but lacks explicit guidance like 'Use for searching; use download_torrent for downloading'. The usage context is inferred, not stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0download_torrentget_torrent_detailsearch_torrentsv0.1.1download_torrentget_torrent_detailsearch_torrentsEach tool serves a unique purpose: search finds torrents, detail retrieves information, and download fetches the torrent file. No overlap or ambiguity exists.
All tool names follow a consistent verb_noun snake_case pattern (download_torrent, get_torrent_detail, search_torrents), making it predictable for agents.
With 3 tools, the set is small but covers essential torrent operations (search, detail, download). Slightly under for full lifecycle but reasonable for a basic client.
The tools cover searching, viewing details, and downloading torrents, but miss uploads, deletions, or seed management. Notable gaps exist for a complete torrent management server.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Manage Superlist tasks and lists in plain language from any MCP-compatible AI agent.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/07freedom/mcp-server-mteam'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
