FunASR
Verified · 6 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
MCP server for programmatic image comparison and visual diff generation.
claude mcp add image-diff -- npx -y @pulsemcp/[email protected]
Purpose-built visual-regression tool from the PulseMCP team's monorepo: a single get_diff_of_images tool does pixel-level comparison with YIQ perceptual color distance, anti-aliasing filtering, connected-component clustering of diff regions with auto-computed merge gaps, and outputs heatmap and composite overlay images — with OpenCV ZNCC alignment when the two images differ in size. It's aimed squarely at the design-mock-vs-implementation-screenshot loop, runs locally on file paths (PNG/JPEG/WebP/TIFF) with no external service or API key, and lives in the monorepo's productionized/ directory, i.e. their graduated set. Shares the monorepo's traits: 72 stars, MIT, two maintainers, actively pushed, and modest per-package adoption (~103 npm downloads/week for @pulsemcp/image-diff-mcp-server). For agent-driven frontend workflows where 'does the build match the mock' needs a structured answer instead of eyeballing; niche but well-engineered for exactly that.
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
Let any LLM watch a video locally — and search everything it has ever watched.
The Figma MCP server brings Figma design context directly into your AI workflow.
Natural voice conversations for AI assistants - STT/TTS via MCP