{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_u55evr48awnu","handle":"chatcut-mcp-server","url":"https://wellknown.network/agents/chatcut-mcp-server","links":{"self":"https://wellknown.network/agents/chatcut-mcp-server/record.json","html":"https://wellknown.network/agents/chatcut-mcp-server","markdown":"https://wellknown.network/agents/chatcut-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/chatcut-mcp-server","status":"https://wellknown.network/api/v1/agents/chatcut-mcp-server/status","claim":"https://wellknown.network/agents/chatcut-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/chatcut-mcp-server/claim.json","badge":"https://wellknown.network/agents/chatcut-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/chatcut-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/chatcut-mcp-server/tools"},"ard":{"identifier":"urn:air::server:chatcut-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"chatcut-mcp-server","summary":"Model Context Protocol (MCP) server for local video editing, presentation overlays, transcription, and hardware-accelerated rendering.","description":"# ChatCut MCP Server 🎬🤖\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Python: 3.10+](https://img.shields.io/badge/Python-3.10+-blue.svg)](https://www.python.org/)\n[![Model Context Protocol: 1.0](https://img.shields.io/badge/MCP-1.0-green.svg)](https://modelcontextprotocol.io/)\n\n**ChatCut MCP Server** is a Model Context Protocol (MCP) server that empowers AI coding agents (such as **Claude Code**, **Cursor**, **Codex**, or **Antigravity**) with local video editing, media processing, transcription, and hardware-accelerated rendering capabilities.\n\nWith this server, you can give your AI agent natural language instructions like *\"trim the silences from this video, overlay slide 2 at second 20, and render it using my GPU\"* or *\"transcribe this video, find the most engaging segment, and create a vertical 9:16 Short\"*, and the agent will know exactly which tools to call to physically process the video on your local machine.\n\n---\n\n## 🛠️ Tools Reference\n\nThe server automatically registers the following tools with the MCP client:\n\n| Tool Name | Arguments | Description |\n| :--- | :--- | :--- |\n| `detect_hardware` | None | Auto-detects the system's active GPU (NVIDIA, Apple Silicon, Intel, AMD) and checks if FFmpeg has hardware encoders enabled. |\n| `parse_video_guidelines_excel` | `file_path: str` | Parses an Excel video editing guidelines file and outputs the cut ranges and slide overlay times in seconds. |\n| `convert_pptx` | `pptx_path: str`, `output_dir: str` | Converts a PowerPoint presentation to PNG slides and pre-scales them to $1920 \\times 1080$ in a cache directory (significantly speeds up FFmpeg rendering). |\n| `transcribe_video_file` | `video_path: str`, `gemini_api_key: str` (optional), `force_local: bool` (optional) | Transcribes a video file to JSON with timestamps. Uses the Gemini API (cloud-based, free/fast) or **local Whisper** (`faster-whisper` running on CPU or GPU). |\n| `find_short_clips`…","publisher":null,"homepage":null,"repository":null,"version":"0.2.1","license":"MIT","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:chatcut-mcp-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"media.speech-recognition","name":"Speech Recognition","confidence":1,"provenance":"derived"},{"slug":"documents.presentations","name":"Presentations","confidence":1,"provenance":"derived"},{"slug":"media.video-editing","name":"Video Editing","confidence":0.848,"provenance":"derived"}],"categories":["documents","media"],"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":"chatcut-mcp-server","registry":"pypi","observedAt":"2026-10-21T19:22:56.575Z","publishedAt":"2026-05-27T03:07:55.071403Z","latestVersion":"0.2.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"chatcut-mcp-server","url":"https://pypi.org/project/chatcut-mcp-server/","firstSeenAt":"2026-09-09T11:30:10.121Z","fetchedAt":"2026-10-21T19:21:27.404Z","normalizedAt":"2026-10-21T19:21:27.404Z"}]},"firstSeenAt":"2026-09-09T11:30:10.121Z","updatedAt":"2026-10-21T19:22:56.575Z"}