# Resolve MCP Server (guycochran)

Solves: Asking Resolve Studio to swap B-roll, add captions and tighten silences on your timeline

Lets an AI assistant read and edit a DaVinci Resolve 21 timeline: find clips and moments, replace B-roll, transform clips, add captions and transcripts, tighten silences and handle multi-track podcast or interview edits. README lists 77 tools.

* Page: https://agentcut.dev/tools/resolve-mcp-server-guycochran/
* Source: https://github.com/guycochran/resolve-mcp-server
* Works with: DaVinci Resolve
* Type: MCP server
* Setup difficulty: medium
* Supported versions: DaVinci Resolve Studio 21; 64-bit Python 3.10+; live tested on Windows and macOS per README
* Resolve edition: Studio only
* Price: free
* License: MIT
* GitHub stars: 13
* Last updated: 2026-09-16
* Checked: 2026-10-19

Setup steps:

1. Install DaVinci Resolve Studio 21 and set External scripting to Local in Preferences > System > General.
2. Install 64-bit Python 3.10 or newer.
3. Clone the repo, create a virtual environment and run pip install -e . as the README shows.
4. Run resolve-mcp --doctor to check that it can see Resolve.
5. Add the server to your MCP client config (Claude Desktop, Cursor, etc.) using the full path to the venv's Python and the args -m resolve_mcp.
6. Open a project and ask your assistant what's in the timeline.

Safety notes:

* Needs Resolve Studio with Preferences > System > General > External scripting set to Local. The README says it does not promise full functionality on the free edition.
* Optional cloud vision tools send frames to Moondream and need its API key; ffmpeg is only needed for silence tightening.
* Remote HTTP mode needs a bearer token of 32+ characters. Keep it on localhost unless you put it behind your own HTTPS gateway.
* Some less common Resolve AI features are only unit tested or partly exercised (see the README's validation notes).

More DaVinci Resolve tools: https://agentcut.dev/davinci-resolve-mcp/

---
AgentCut: https://agentcut.dev/ · All tools as JSON: https://agentcut.dev/tools.json · Overview for agents: https://agentcut.dev/llms.txt