bibigpt-video-summarizer
mcpsmitheryBibiGPT is an AI-powered video and audio assistant that turns hours of content into actionable knowledge in seconds. What it does: - Summarize videos and podcasts from YouTube, Bilibili, TikTok, Twitter/X, Xiaohongshu, Douyin, Apple Podcasts, Spotify, and 20+ platforms - Extract full transcripts with timestamps — even for videos without subtitles (powered by Whisper ASR) - Generate chapter-by-chapter summaries for lectures, tutorials, and long-form content - Async task processing for videos over 2 hours Why agents love it: - 6 MCP tools with clear, composable APIs — summarize, get subtitles, chapter breakdown, async task creation & polling - Works with any AI model (GPT-4o, Claude, Gemini, etc.) via custom prompt config - Output in 5 languages: English, Chinese, Japanese, Korean, Traditional Chinese - OAuth 2.1 + Bearer token auth — compatible with Claude, ChatGPT, Cursor, Codex, and all MCP clients Who uses it: 500,000+ users — content creators, researchers, students, and knowledge workers who process video content at scale. Built by BibiGPT (bibigpt.co).
By Smithery | 17 findings | Scanned 4/19/2026 | tooltrust-scanner/v0.3.8
Risk Summary
Needs ApprovalExcessive Permissions plus Dep Visibility raises enough risk that this tool should not be auto-trusted.
Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.
Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (17)
tool declares network permission
summarize_videosummarize_video_with_configsummarize_by_chaptercreate_summary_taskget_subtitleFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
create_summary_task:tool declares fs permission
Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
summarize_videosummarize_video_with_configsummarize_by_chaptercreate_summary_taskget_subtitleFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
summarize_videosummarize_video_with_configsummarize_by_chaptercreate_summary_taskget_task_statusget_subtitleFix: Review and remediate the identified issue.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y bibigpt-video-summarizer"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)