$git clone https://github.com/samuelgursky/davinci-resolve-mcpA Model Context Protocol (MCP) server that lets AI assistants control DaVinci Resolve Studio through the official Scripting API. It provides full API coverage plus guarded workflow helpers for editing, media pool organization, render setup, review markers, grading, Fusion, Fairli
| 1 | # DaVinci Resolve MCP Server |
| 2 | |
| 3 | [](https://github.com/samuelgursky/davinci-resolve-mcp/releases) |
| 4 | [](https://www.npmjs.com/package/davinci-resolve-mcp) |
| 5 | [](docs/reference/api-coverage.md) |
| 6 | [-blue.svg)](#server-modes) |
| 7 | [-18%20tools-blueviolet.svg)](#server-modes) |
| 8 | [](docs/reference/api-coverage.md#test-results) |
| 9 | [](https://www.blackmagicdesign.com/products/davinciresolve) |
| 10 | [](https://www.python.org/downloads/) |
| 11 | [](https://opensource.org/licenses/MIT) |
| 12 | |
| 13 | A Model Context Protocol (MCP) server that lets AI assistants control DaVinci Resolve Studio through the official Scripting API. It provides full API coverage plus guarded workflow helpers for editing, media pool organization, render setup, review markers, grading, Fusion, Fairlight, project lifecycle tasks, extension authoring, and source-safe media analysis. |
| 14 | |
| 15 | [](docs/guides/control-panel.md) |
| 16 | |
| 17 | A local browser control panel ships with the server for inspecting Resolve state, running source-safe analysis, drilling into analyzed clips and shots, and editing analysis output inline. See the [Control Panel Guide](docs/guides/control-panel.md) for the full tour. |
| 18 | |
| 19 | ## Quick Start |
| 20 | |
| 21 | ```bash |
| 22 | npx davinci-resolve-mcp setup |
| 23 | ``` |
| 24 | |
| 25 | Before connecting, open DaVinci Resolve Studio and set **Preferences > General > External scripting using** to **Local**. The npm launcher installs a managed copy under your user application-data directory, then runs the universal Python installer. The installer creates a virtual environment, detects Resolve paths, and can configure Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, Continue, Cline, Roo Code, OpenCode, and JetBrains IDEs. |
| 26 | |
| 27 | For source installs: |
| 28 | |
| 29 | ```bash |
| 30 | git clone https://github.com/samuelgursky/davinci-resolve-mcp.git |
| 31 | cd davinci-resolve-mcp |
| 32 | python install.py |
| 33 | ``` |
| 34 | |
| 35 | For platform paths, client-specific config, and manual setup, see [Installation and Configuration](docs/install.md). |
| 36 | |
| 37 | The installer and server check the latest GitHub release for MCP updates. Checks are best-effort and throttled; the server never blocks MCP startup for a prompt. The installer can prompt, snooze, ignore a release, disable checks, or apply an opt-in safe auto-update for clean git checkouts. |
| 38 | |
| 39 | ## Local Control Panel |
| 40 | |
| 41 | Launch the single-user local control panel from the repository root: |
| 42 | |
| 43 | ```bash |
| 44 | venv/bin/python -m src.control_panel |
| 45 | ``` |
| 46 | |
| 47 | The command starts a localhost server and opens the control panel in your browser. To have an AI coding agent do this, ask: **"Open the Resolve MCP control panel for this repo."** Agents should use `venv/bin/python -m src.control_panel` unless your Python environment is already active. Persisted analysis jobs refresh the local search index automatically after successful slices; the manual Build Index action is for rebuilding from existing reports. |
| 48 | |
| 49 | ## Server Modes |
| 50 | |
| 51 | | Mode | Entry point | Tools | Best for | |
| 52 | |------|-------------|-------|----------| |
| 53 | | Compound | `src/server.py` | 34 | Default mode for most assistants. Related Resolve operations are grouped behind action parameters to keep context usage low. | |
| 54 | | Full / granular | `src/server.py --full` or `src/resolve_mcp_server.py` | 341 | Power users who want one MCP tool per Resolve API method. | |
| 55 | |
| 56 | The compound server is recommended unless you s |