dvr MCP server
Commit Oct 21, 2026Automate DaVinci Resolve editing, color grading, and rendering using a command-line tool, Python library, or MCP server for AI agents.
Also known as mhadifilms/dvr
- Stars
- 15
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Oct 21, 2026
- License
- MIT
What is dvr MCP?
dvr automates DaVinci Resolve editing, color grading, and rendering using a command-line tool, Python library, or MCP server for AI agents.
Summary generated from the project's README
About dvr MCP server
Video editors and developers can automate DaVinci Resolve workflows including editing, color grading, and rendering through this tool. It provides a structured way to interact with the software, replacing the fragile and silent failure patterns of the native Python scripting API with idempotent operations and decoded errors. The system works as a command-line interface, a typed Python library, or an MCP server for AI agents like Claude and Cursor.
Users can connect to DaVinci Resolve Studio 18.5 or higher on macOS, Windows, or Linux. The MCP server exposes over 39 typed tools, allowing LLM clients to drive the application without manual shell parsing. While the full automation requires the Studio version, certain inspection and schema tools function even when the software is not running. Setup is simplified through dedicated commands for Claude Desktop and Cursor, making it easy to integrate video production tasks into an AI-driven development environment.
What you can do with it
- 1Automate video rendering tasksA developer can trigger a render job using a specific preset and monitor the progress via the command line.
- 2Apply declarative project configurationsUsers can reconcile project settings by applying a YAML specification to ensure the environment matches a desired state.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablemhadifilms/dvr is public and reachablegithub.com/mhadifilms/dvr ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-21github.com/mhadifilms/dvr ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubdvr
The missing CLI, Python library, and MCP server for DaVinci Resolve.
Declarative. Scriptable. LLM-friendly. No more silent None returns.
dvr is a command-line tool, a typed Python library, and a Model Context Protocol (MCP) server for automating DaVinci Resolve — editing, color grading, rendering, and delivery. It turns Resolve's fragile scripting API into clean, idempotent operations with structured JSON output, so humans, scripts, and AI agents (Claude, Cursor, and any MCP-compatible client) can drive Resolve reliably.
pip install dvr
$ dvr timeline inspect
{
"name": "Edit_v2",
"fps": 24.0,
"duration_frames": 86400,
"tracks": {
"video": [{"index": 1, "name": "V1", "clips": 1, "enabled": true}, ...],
"audio": [{"index": 1, "name": "A1", "clips": 4, "subtype": "stereo"}, ...]
},
"markers": [...],
"color": {"science": "DaVinci YRGB Color Managed v2", "input": "Rec.2020", ...}
}
Why dvr exists
DaVinci Resolve has a powerful Python scripting API. It's also painful:
- Silent failures everywhere.
AddRenderJob()returnsNoneon success or failure — good luck. - String-keyed settings with undocumented valid values.
- No batch operators. You loop everything.
- macOS connection footguns. Resolve binds to LAN IP; vanilla
scriptapp('Resolve')returnsNone. - Chain navigation. Every
.Get*()can returnNone. One typo and you're traversing nothing. - 20+ export formats behind magic enum constants.
dvr wraps the API with a clean object model, idempotent operations, decoded errors, structured I/O, and a CLI that's pleasant for humans and parseable by LLM agents.
Three ways to use it: Python library, CLI, and MCP server
1. Python library
from dvr import Resolve
r = Resolve() # auto-connects, handles macOS LAN-IP quirk
with r.project.use("MyShow"):
tl = r.timeline.current
print(tl.inspect()) # one call, full state
# Query language operates on inspected state
bad = tl.clips.where(lambda c: c.duration < 12)
for clip in bad:
clip.add_marker(color="red", note="too short")
job = r.render.submit(preset="delivery")
job.wait() # blocks with progress
print(job.output_path)
2. CLI
$ dvr project ensure MyShow --color rec2020_pq_4000 --fps 24
$ dvr timeline inspect | jq '.tracks.video[].clips'
$ dvr render submit --preset delivery --wait --stream
{"job_id": "abc", "status": "rendering", "pct": 12, "eta_s": 240}
{"job_id": "abc", "status": "rendering", "pct": 24, "eta_s": 210}
{"job_id": "abc", "status": "complete", "output": "/path/out.mov"}
3. MCP server (for LLM agents)
$ pip install dvr
$ dvr mcp install-claude # one-shot Claude Desktop setup
$ dvr mcp serve # or run the server yourself
$ dvr mcp tools # introspect the 39+ typed tools
LLM agents call typed tools directly — no shell parsing, no silent failures. Tools that don't need a live Resolve (version, doctor, static schema topics) work even when Resolve isn't running, so first-time setup is instant. See docs/mcp.md.
Five things that make it fundamentally better than the raw DaVinci Resolve scripting API
- One
inspect()call replaces ten API calls. Full structured state in a single round-trip. - Idempotent operations.
project.ensure(),timeline.ensure(),bin.ensure()— re-run anything safely. - Decoded errors. Every failure carries
cause,fix, andstate. No moreNone. - Declarative specs.
dvr apply project.dvr.yamlreconciles state.kubectl applyfor DaVinci. - Persistent connection.
dvr servekeeps Resolve warm — sequential commands run in <100ms.
Install
| Channel | Command |
|---|---|
| Homebrew (macOS / Linux) | brew install mhadifilms/tap/dvr |
| PyPI | pip install dvr |
| pipx | pipx install dvr |
| uv | uv tool install dvr |
| From source | git clone https://github.com/mhadifilms/dvr && cd dvr && pip install -e ".[dev]" |
Optional extras
pip install "dvr[docs]" # docs site dependencies
pip install "dvr[dev]" # dev (ruff, mypy, pytest)
MCP support is included in the default install.
Homebrew details
dvr ships via my personal tap at mhadifilms/homebrew-tap. The recommended pattern is to tap once, then use the bare command:
brew tap mhadifilms/tap
brew install dvr # works after the tap is installed
Or, if you only ever want to install once and don't care about updates:
brew install mhadifilms/tap/dvr
brew install dvrsays "no formula"? That's expected if you haven't tapped yet. Homebrew only searcheshomebrew/coreby default; our formula lives in our personal tap. Runbrew tap mhadifilms/tapand try again.
Requirements
- Python 3.10+ (matches Resolve's embedded Python on current versions)
- DaVinci Resolve Studio 18.5+ — external scripting is a Studio-only feature. Blackmagic Design sells Studio as a one-time $295 perpetual license or via Blackmagic Cloud at $30/month per seat.
- macOS, Windows, or Linux
dvr auto-discovers Resolve's scripting library on each platform. No environment variables needed for typical installs.
The free edition of DaVinci Resolve cannot be scripted from outside the app (Blackmagic restricted this in v19.1+). If you're evaluating
dvrwithout Studio, use--dry-runflags onapplyand explore the schema/inspection commands — they work without a live connection.
FAQ
How do I script DaVinci Resolve from Python?
Install dvr (pip install dvr) and use the typed from dvr import Resolve library, or run the dvr CLI. It auto-connects to Resolve, handles the macOS LAN-IP quirk, and returns structured objects instead of None.
Is there a DaVinci Resolve MCP server?
Yes. dvr mcp serve runs a Model Context Protocol (MCP) server that exposes 39+ typed tools, so LLM agents can automate DaVinci Resolve without parsing shell output. See docs/mcp.md.
Does dvr work with Claude and Cursor?
Yes. Run dvr mcp install-claude or dvr mcp install-cursor for one-shot setup. Any MCP-compatible AI agent or LLM client can drive Resolve through the same typed tools.
Can I automate DaVinci Resolve rendering and exports from the command line?
Yes. dvr render submit --preset delivery --wait --stream renders from the CLI with streaming JSON progress, and dvr exports EDL / AAF / FCPXML / OTIO interchange formats.
How is dvr different from the raw DaVinci Resolve scripting API?
It adds a clean object model, idempotent operations (ensure), decoded errors with cause/fix/state, declarative YAML specs (dvr apply), a persistent connection daemon, and an MCP server — replacing dozens of fragile Get*() calls that silently return None.
Status
Stable from 1.0. Breaking changes ship with a deprecation cycle and a major version bump; new features land as minor releases. See CHANGELOG.md.
License
MIT — see LICENSE.
Contributing
Issues and pull requests welcome. The project's API surface is large; contributions covering edge cases on Windows / Linux are especially valuable. See CONTRIBUTING.md for setup and conventions.
dvris an independent open-source project. It is not affiliated with, endorsed by, or sponsored by Blackmagic Design. "DaVinci" and "DaVinci Resolve" are trademarks of Blackmagic Design Pty Ltd.
dvr MCP questions
Is there a DaVinci Resolve MCP server?
Yes, running dvr mcp serve starts an MCP server that provides over 39 typed tools for LLM agents to automate Resolve.
Does dvr work with Claude and Cursor?
Yes, you can use one-shot setup commands like dvr mcp install-claude or dvr mcp install-cursor to enable these clients.
Can I automate DaVinci Resolve rendering and exports from the command line?
Yes, you can submit render jobs via the CLI with streaming JSON progress and export various interchange formats like EDL, AAF, FCPXML, and OTIO.
What are the requirements for using dvr?
You need Python 3.10+ and DaVinci Resolve Studio 18.5 or newer, as external scripting is a Studio-only feature.