{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_kbys8augbmcj","handle":"iflow-mcp-r-lz-mcp-video-digest","url":"https://wellknown.network/agents/iflow-mcp-r-lz-mcp-video-digest","links":{"self":"https://wellknown.network/agents/iflow-mcp-r-lz-mcp-video-digest/record.json","html":"https://wellknown.network/agents/iflow-mcp-r-lz-mcp-video-digest","markdown":"https://wellknown.network/agents/iflow-mcp-r-lz-mcp-video-digest/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-r-lz-mcp-video-digest","status":"https://wellknown.network/api/v1/agents/iflow-mcp-r-lz-mcp-video-digest/status","claim":"https://wellknown.network/agents/iflow-mcp-r-lz-mcp-video-digest/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-r-lz-mcp-video-digest/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-r-lz-mcp-video-digest/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-r-lz-mcp-video-digest/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-r-lz-mcp-video-digest/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-r-lz-mcp-video-digest","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_r-lz_mcp-video-digest","summary":"MCP Server for transcribing videos via video links and summarizing video content","description":"# MCP Video Digest (视频内容提取总结)\n\n<div align=\"right\">\n  <a href=\"README_EN.md\">English</a> | <b>中文</b>\n</div>\n\n## 项目简介\nMCP 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)\n\n## 功能特点\n- 支持超过1000个网站上的流媒体内容下载和音频提取\n- 多个转录服务提供商支持：\n  - Deepgram\n  - Gladia\n  - Speechmatics\n  - AssemblyAI\n- 灵活的服务选择机制，根据可用的 API 密钥自动选择服务\n- 异步处理设计，提高并发性能\n- 完整的错误处理和日志记录\n- 支持说话人分离\n- × 支持本地模型cpu/gpu加速处理\n\n## 目录结构\n```\n.\n├── src/                    # 源代码目录\n│   ├── services/          # 服务实现目录\n│   │   ├── download/      # 下载服务\n│   │   └── transcription/ # 转录服务\n│   ├── main.py           # 主程序逻辑\n│   └── __init__.py       # 包初始化文件\n├── config/                # 配置文件目录\n├── test.py               # 测试脚本\n├── run.py                # 服务启动脚本\n├── pyproject.toml        # 项目配置和依赖管理\n├── uv.lock               # UV 依赖锁定文件\n└── .env                  # 环境变量配置\n```\n\n## 测试截图\n\n![YouTube](screenshot/img1.png)\n\n![Bilibili](screenshot/img2.png)\n\n## 安装说明\n\n### 1. 安装 uv 或使用 python\n如果还没有安装 uv，可以使用以下命令安装：\n```bash\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n```\n\n### 2. 克隆项目：\n```bash\ngit clone https://github.com/R-lz/mcp-video-digest.git\ncd mcp-video-digest\n```\n\n### 3. 创建并激活虚拟环境：\n```bash\nuv venv\nsource .venv/bin/activate  # Linux/Mac\n# 或\n.venv\\Scripts\\activate     # Windows\n```\n\n### 4. 安装依赖：\n```bash\nuv pip install -e .\n```\n\n> 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\n\n## 配置说明\n1. 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：\n   ```\n   mv .env.example .env\n\n   # 修改\n   DEEPGRAM_API_KEY=your_deepgram_key\n   GLADIA_API_KEY=your_gladia_key\n   SPEECHMATICS_API_KEY=your_speechmatics_key\n   ASSEMBLYAI_API_KEY=your_assemblyai_key\n   ```\n   注意：至少需要配置一个服务的 API 密钥\n\n2. 服务优先级顺序：\n   - Deepgram（推荐用于中文内容）\n   - Gladia\n   - Speechmatics\n   - AssemblyAI\n\n## 使用方法\n1. 启动服务：\n   ```bash\n   uv run src/main.py\n   ```\n   或者使用调试模式：\n   ```bash\n   UV_DEBUG=1 uv run src/main.py\n   ``…","publisher":{"name":"R-lz","url":null},"homepage":null,"repository":null,"version":"0.1.1","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_r-lz_mcp-video-digest","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"content.social","name":"Social Media","confidence":0.791,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["content","dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp_r-lz_mcp-video-digest","registry":"pypi","observedAt":"2026-09-15T20:21:13.962Z","publishedAt":"2026-01-27T08:09:24.381854Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_r-lz_mcp-video-digest","url":"https://pypi.org/project/iflow-mcp_r-lz_mcp-video-digest/","firstSeenAt":"2026-09-09T20:25:34.863Z","fetchedAt":"2026-09-15T20:19:02.529Z","normalizedAt":"2026-09-15T20:19:02.529Z"}]},"firstSeenAt":"2026-09-09T20:25:34.863Z","updatedAt":"2026-09-15T20:21:13.962Z"}