Atlas / MCP servers / r-lz / Video Digest

Video DigestSAFE

mcp/r-lz/video-digest

MCP Server for transcribing videos via video links and summarizing video content

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
sse
License
MIT
Stars
28
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

English | 中文

项目简介

MCP Video Digest 是一个视频内容处理服务,,能够从 YouTube、Bilibili、TikTok、Twitter... 视频中提取音频并转换为文本。该服务支持多个转录服务提供商,包括 Deepgram、Gladia、Speechmatics 和 AssemblyAI,可以根据配置的 API 密钥灵活选择使用。(第一个MCP练手的项目,主要熟悉MCP的开发和运行流程)

功能特点

  • 支持超过1000个网站上的流媒体内容下载和音频提取
  • 多个转录服务提供商支持:
  • Deepgram
  • Gladia
  • Speechmatics
  • AssemblyAI
  • 灵活的服务选择机制,根据可用的 API 密钥自动选择服务
  • 异步处理设计,提高并发性能
  • 完整的错误处理和日志记录
  • 支持说话人分离
  • × 支持本地模型cpu/gpu加速处理

目录结构

.
├── src/                    # 源代码目录
│   ├── services/          # 服务实现目录
│   │   ├── download/      # 下载服务
│   │   └── transcription/ # 转录服务
│   ├── main.py           # 主程序逻辑
│   └── __init__.py       # 包初始化文件
├── config/                # 配置文件目录
├── test.py               # 测试脚本
├── run.py                # 服务启动脚本
├── pyproject.toml        # 项目配置和依赖管理
├── uv.lock               # UV 依赖锁定文件
└── .env                  # 环境变量配置

测试截图

安装说明

1. 安装 uv 或使用 python

如果还没有安装 uv,可以使用以下命令安装:

curl -LsSf https://astral.sh/uv/install.sh | sh

2. 克隆项目:

git clone https://github.com/R-lz/mcp-video-digest.git
cd mcp-video-digest

3. 创建并激活虚拟环境:

uv venv
source .venv/bin/activate  # Linux/Mac
# 或
.venv\Scripts\activate     # Windows

4. 安装依赖:

uv pip install -e .
speechmatics 在使用requests调试的时候出现了各种问题(不是speechmatics的问题, 是我菜),所以使用了speechmatics sdk

配置说明

  1. 在项目根目录创建 .env 文件或者重命名.env.example,配置所需的 API 密钥:
mv .env.example .env

# 修改
DEEPGRAM_API_KEY=your_deepgram_key
GLADIA_API_KEY=your_gladia_key
SPEECHMATICS_API_KEY=your_speechmatics_key
ASSEMBLYAI_API_KEY=your_assemblyai_key

注意:至少需要配置一个服务的 API 密钥

  1. 服务优先级顺序:
  2. Deepgram(推荐用于中文内容)
  3. Gladia
  4. Speechmatics
  5. AssemblyAI

使用方法

  1. 启动服务:
uv run src/main.py

或者使用调试模式:

UV_DEBUG=1 uv run src/main.py
``
Read from source at commit d5e285e25d9dOBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add mcp-video-digest --env ASSEMBLYAI_API_KEY=${ASSEMBLYAI_API_KEY} --env DEEPGRAM_API_KEY=${DEEPGRAM_API_KEY} --env GLADIA_API_KEY=${GLADIA_API_KEY} --env SPEECHMATICS_API_KEY=${SPEECHMATICS_API_KEY} -- uvx mcp-video-digest
claude-desktop
{
  "mcpServers": {
    "mcp-video-digest": {
      "command": "uvx",
      "args": [
        "mcp-video-digest"
      ],
      "env": {
        "ASSEMBLYAI_API_KEY": "${ASSEMBLYAI_API_KEY}",
        "DEEPGRAM_API_KEY": "${DEEPGRAM_API_KEY}",
        "GLADIA_API_KEY": "${GLADIA_API_KEY}",
        "SPEECHMATICS_API_KEY": "${SPEECHMATICS_API_KEY}"
      }
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
get_video_contentreadctx = MCPContext(mcp)
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (5 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (2)

INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:51
curl -LsSf https://astral.sh/uv/install.sh | sh
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README_EN.md:51
curl -LsSf https://astral.sh/uv/install.sh | sh

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha d5e285e25d9dfull audit observations/trust-audit/mcp-server/r-lz__video-digest.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-08d5e285e25d9dSAFEB89first audit
06

Questions

What is the Video Digest MCP server?

MCP Server for transcribing videos via video links and summarizing video content

What tools does Video Digest expose?

1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Video Digest safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Video Digest need?

It reads ASSEMBLYAI_API_KEY, DEEPGRAM_API_KEY, GLADIA_API_KEY and SPEECHMATICS_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Video Digest run?

It speaks sse, so it runs as a service you connect to over the network. It is published on PyPI as mcp-video-digest.

How current is this page?

The grade is for one exact copy of the source (d5e285e25d9d), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement