← 返回 Skills 市场
videomp3word MCP
作者
shuyueW1991
· GitHub ↗
· v2.0.3
· MIT-0
203
总下载
0
收藏
0
当前安装
17
版本数
在 OpenClaw 中安装
/install videomp3word-mcp
功能描述
Structured knowledge extraction MCP server for ClawHub/OpenClaw. Converts remote media URLs into summary, topics, action items, Q&A, flashcards, entities, co...
安全使用建议
This package is mostly coherent with its stated purpose, but proceed cautiously:
- Expect to provide a sensitive upstream credential (VIDEOMP3WORD_SESSION_COOKIE). Use a dedicated upstream account and never reuse personal credentials. The registry listing incorrectly stated 'no required env vars' even though the package enforces this cookie — don't rely on registry metadata alone.
- The default knowledge model endpoint is dashscope.aliyuncs.com (an Aliyun-compatible endpoint). If you need data to remain within trusted providers, override KNOWLEDGE_MODEL_API_BASE and KNOWLEDGE_MODEL_API_KEY or disable model forwarding.
- Audit the upstream transcription service and model endpoint before sending transcripts or media URLs — transcripts and media URLs will be transmitted to those services.
- If you deploy this server publicly, set MCP_ACCESS_KEYS and run behind a firewall / internal network. In production NODE_ENV the server will refuse to start without access keys according to the code; still verify your deployment defaults (host/port) and CORS settings.
- If you need persistent storage, provide a MONGO_URI that you control; otherwise the server will use in-memory storage (development). Review stored artifacts if you have privacy concerns.
- Because package metadata and SKILL.md disagree about required env vars, review src/config.ts and package.json directly (they govern runtime behavior) before installing. If you are not comfortable providing the upstream session cookie or exposing transcripts to external model APIs, do not install or run this service in your environment.
功能分析
Type: OpenClaw Skill
Name: videomp3word-mcp
Version: 2.0.3
The videomp3word-mcp bundle is a well-structured MCP server designed to extract structured knowledge from audio and video URLs. It implements a modular agent-based workflow (planning, transcription, semantic analysis, and knowledge generation) with clear separation of concerns. Security best practices are evident, including SSRF protection via DNS lookups and private IP filtering (src/utils/network.ts), mandatory HTTPS for remote service endpoints (src/config.ts), and bearer token authorization for its API (src/httpServer.ts). While it requires a sensitive session cookie for the upstream videomp3word.com service, this requirement is explicitly documented and the credential is used only for its stated purpose of transcription.
能力标签
能力评估
Purpose & Capability
The code and SKILL.md implement a server that ingests remote media URLs, calls an upstream transcription service and a knowledge-model endpoint, and returns structured JSON — exactly as the description says. Requested items like VIDEOMP3WORD_SESSION_COOKIE, optional model API keys, and MONGO_URI are coherent with that purpose. However, the registry summary claims no required env vars while package.json and src/config.ts enforce a required VIDEOMP3WORD_SESSION_COOKIE; this metadata mismatch is noteworthy and may mislead users about what credentials are needed.
Instruction Scope
Runtime instructions are explicit: build and run the server, provide the upstream session cookie and optionally model/API and DB settings. The SKILL.md and README clearly state that transcript text, chunks, and media URLs are sent to upstream transcription and model endpoints, and they advise auditing those endpoints. The instructions do not instruct access to unrelated local files or other credentials.
Install Mechanism
There is no automated download/install in the registry entry (manual npm build/start is required). The bundle includes full TypeScript source and a standard package.json; dependencies are from npm (express, mongodb, zod, and a modelcontext sdk). Nothing is fetched from obscure/personal URLs nor is there an extract-from-URL install step in the metadata.
Credentials
The server requires a sensitive upstream session cookie (VIDEOMP3WORD_SESSION_COOKIE) and can be configured with knowledge model API keys and a MongoDB URI. Those are proportionate to the declared functionality, but they are sensitive: the required session cookie is effectively a credential for a third-party transcription service and should come from a dedicated account. Additionally, the default knowledge model base is set to https://dashscope.aliyuncs.com/compatible-mode/v1 (non-obvious third-party endpoint) which may surprise deployers who expect OpenAI or a different provider. Finally, the registry-level metadata claimed no required env vars while package.json marks the session cookie as required — this mismatch increases risk of accidental credential exposure by users who assume no secrets are needed.
Persistence & Privilege
The skill does not request 'always: true' and does not modify other skills. It runs as a standalone HTTP / MCP server (binds host/port, default 0.0.0.0:3000) and can persist to MongoDB if MONGO_URI is provided. That persistence capability is expected for this product; ensure you do not expose the service publicly without configuring MCP_ACCESS_KEYS (the code enforces requiring access keys in production).
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install videomp3word-mcp - 安装完成后，直接呼叫该 Skill 的名称或使用
/videomp3word-mcp触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v2.0.3
- Added support for DashScope API keys (DASHSCOPE_API_KEY) as a fallback for the knowledge model when KNOWLEDGE_MODEL_API_KEY is not set.
- Updated default settings: knowledge model API base now defaults to DashScope-compatible endpoint; default model name set to qwen-plus.
- Clarified environmental variable handling and fallback logic for API keys in documentation.
- Expanded documentation to explicitly note data flow to upstream knowledge model/transcription services.
- No breaking changes to existing inputs/outputs or core functionality.
v2.0.1
Version 2.0.1
- Updated documentation with clearer installation steps and security recommendations.
- Added explicit install and start commands to the SKILL.md notes.
- Emphasized the requirement for HTTPS when configuring non-local upstream URLs containing credentials.
- No code or API changes; changes are documentation-only.
v2.0.0
**Major update: Introduces a structured knowledge extraction engine for media files.**
- Added new MCP tool (`video_to_knowledge`) for turning remote video/audio URLs into structured outputs: summaries, Q&A pairs, flashcards, tasks, topics, entities, and workflow trace.
- Modularized codebase with agent-based workflow (agents for transcription, semantic analysis, planning, evaluation, etc.).
- Added extensive persistent resource support (optional MongoDB storage for caching and artifact export).
- New examples and Python SDK for integrating media-to-knowledge workflows in downstream products.
- REST API and stdio interfaces remain, with access keys now gating the main workflow.
- Documentation, environment variables, and output schema updated for easier automation and enterprise integration.
v1.1.6
- Updated package.json version to 1.1.6.
- No functional changes to the skill or documentation.
v1.1.5
- Updated package.json version to 1.1.5.
- No functional or documentation changes outside of version bump.
v1.1.4
- Adds transcript workflow and YouTube helper tools, including transcript transformation, YouTube transcript lookup, and embed checking.
- Introduces a token estimation endpoint for conversion cost prediction.
- Updates documentation to reflect new endpoints and expanded capabilities.
- No breaking changes to existing conversion or payment flows.
v1.1.3
- Added support for an upstream host allowlist via the new VIDEOMP3WORD_ALLOWED_UPSTREAM_HOSTS environment variable
- Clarified the use of VIDEOMP3WORD_API_KEY as a supplemental credential alongside the required session cookie
- Updated documentation to reflect new environment options and security recommendations
- Removed obsolete patch.py file
- Minor dependency and configuration updates for improved maintainability
v1.1.2
videomp3word-mcp 1.1.2
- Updated 10-token price to $0.99 (was $0.90) in documentation.
- Added a new patch.py file.
- Minor documentation and metadata updates.
v1.1.1
- Security note in SKILL.md now emphasizes that MCP_ACCESS_KEYS should be set to avoid draining token balance, and calls special attention to VIDEOMP3WORD_SESSION_COOKIE being required.
- Clarified deployment warnings and consequences for unset access gating variables.
- No functional code changes; documentation updates only.
v1.1.0
videomp3word-mcp 1.1.0 adds autonomous payment and OpenClaw Stdio support.
- Added autonomous payment tool (`videomp3word_pay`) for bots with payment authority.
- Introduced native support for Clawhub/OpenClaw via Stdio execution mode.
- Expanded documentation to highlight new payment and Stdio features.
- Improved positioning for AI agent/bot integration and autonomous workflows.
v1.0.6
- Added src/config.ts for improved configuration handling.
- Updated package.json and src/index.ts to integrate new config module.
- No changes to environment variable names or usage.
- General internal code cleanup and structure improvement.
v1.0.5
- Dependency updates in package.json.
- No user-facing changes in functionality or documentation.
- Codebase remains consistent with previous operational and usage guidance.
v1.0.4
- Dependency versions updated in package.json for improved compatibility and security.
- Source code (src/index.ts) and smoke test (src/smoke.test.ts) updated to reflect latest changes.
- Documentation (SKILL.md) remains unchanged.
v1.0.3
- Updated dependencies in package-lock.json and package.json for improved security and stability.
- Enhanced TypeScript source (src/index.ts) with minor updates or fixes.
- Refined or extended smoke tests in src/smoke.test.ts.
- No changes to user-facing documentation or usage.
v1.0.2
- Renamed the skill to "videomp3word-mcp" and updated all references.
- Expanded and clarified environment variable configuration, adding options for base URLs, support, artifacts TTL, and server settings.
- Improved SKILL.md documentation for deployment security, operator guidance, and best practices.
- Added smoke test (src/smoke.test.ts) to improve automated test coverage.
- Updated package dependencies and metadata.
v1.0.1
- Added documentation for required and optional environment variables, improving deployment clarity.
- Included a security and implementation notice about handling sensitive credentials.
- No code or behavioral changes; documentation only.
v1.0.0
- Initial release introducing the videomp3word-bot-mcp skill.
- Explains single-endpoint media conversion for bots (video, audio, and text).
- Details token-based pricing, usage-based billing, and simple price packages.
- Describes onboarding for bot access and purchase options.
- Guides on operational usage, including mode selection and output expectations.
元数据
常见问题
videomp3word MCP 是什么？
Structured knowledge extraction MCP server for ClawHub/OpenClaw. Converts remote media URLs into summary, topics, action items, Q&A, flashcards, entities, co... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 203 次。
如何安装 videomp3word MCP？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install videomp3word-mcp」即可一键安装，无需额外配置。
videomp3word MCP 是免费的吗？
是的，videomp3word MCP 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
videomp3word MCP 支持哪些平台？
videomp3word MCP 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 videomp3word MCP？
由 shuyueW1991（@shuyuew1991）开发并维护，当前版本 v2.0.3。
推荐 Skills