davinci-resolve-mcp
Drive DaVinci Resolve from Claude Code (or any MCP client) to edit videos on the free Community edition, using a bridge to bypass scripting restrictions.
README
DaVinci Resolve MCP — Free / Community edition
Drive DaVinci Resolve from Claude Code (or any MCP client) to edit videos — on the free Community edition, which blocks normal external scripting.
Why this is different
DaVinci Resolve Free does not allow an external process to connect via the
scripting API (scriptapp("Resolve") returns nil); the permission toggle that
Studio exposes is absent. Verified on Resolve 21.0.0.48 across Python 3.9–3.14.
However, scripts running inside Resolve have full API access. So this project uses a bridge:
Claude Code ──MCP──► server.py (this repo) ──files──► resolve_bridge.lua (inside Resolve) ──► live `resolve` object
bridge/resolve_bridge.lua— runs inside Resolve, polls a request file, executes against theresolveobject, writes a JSON response.davinci_mcp/— the external MCP server; each tool sends one RPC to the bridge.
Request/response are exchanged via files in ~/.davinci-mcp-bridge/.
Setup
-
Install deps and the bridge helper:
uv sync python3 scripts/install_bridge.pyThe installer copies the bridge into Resolve's Scripts folder and prints the exact start/registration commands for your machine.
-
Start the bridge inside Resolve (it must be running for any tool to work):
- Workspace ▸ Scripts ▸ Comp ▸ MCP_Bridge (after restarting Resolve once), or
- Workspace ▸ Console, switch to Lua, and run
dofile("<repo>/bridge/resolve_bridge.lua").
You should see
[bridge] UPandops registered=.... It keeps running and does not freeze the Resolve UI. -
Register the MCP server with Claude Code:
claude mcp add davinci-resolve -- uv run --directory <repo> davinci-resolve-mcpThen in Claude Code, call
bridge_statusto confirm the connection.
Tools
resolve_info, list_projects, current_project, open_project,
create_project, save_project, import_media, list_media,
list_timelines, current_timeline, create_timeline,
append_all_to_timeline, add_marker, and resolve_eval (run arbitrary Lua —
escape hatch for anything not yet wrapped).
Limitations (Free edition)
- Studio-only API calls return errors: transcription, subtitles-from-audio, AutoSync, Magic Mask, IntelliSearch, motion-deblur, speech gen, Dolby Vision.
- Render limits: 8-bit, ≤ UHD 3840×2160, ≤ 60 fps. Applying a Studio-only effect watermarks the export.
Credits
Architecture and Studio-edition tool designs informed by samuelgursky/davinci-resolve-mcp (MIT). This project is a from-scratch Free-edition rework using the bridge approach.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.