FunASR
Verified · 6 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
MarkGrab
Verified · 9 days agoUniversal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.
Install
claude mcp add markgrab -- uvx markgrab
Our take
This server focuses on extracting web and document content into markdown that is easier for LLMs to consume, including sources like PDFs, DOCX files, and YouTube pages. It is most useful for ingestion pipelines, research agents, or RAG preprocessing where normalized text matters more than fidelity to the original format. The scope is practical, but the project signals are still thin, so reliability across edge-case formats is not yet well established.
Verification record
- 9 days ago
- 0
- 4 mo ago
- no
- MIT
- 2026-03-17
More in media
browse all →Figma-Context-MCP
Verified · 8 days agoGive your coding agent access to your Figma data. Implement designs in any framework in one-shot.
openshorts
Verified · 16 days agoTurn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
claude-real-video
Verified · 16 days agoLet any LLM watch a video locally — and search everything it has ever watched.
Figma MCP Server
Verified · 11 days agoThe Figma MCP server brings Figma design context directly into your AI workflow.
voicemode
Verified · 9 days agoNatural voice conversations for AI assistants - STT/TTS via MCP