Verified conversions across 205 color spaces: CSS strings, gamut checks, .cube LUTs
Nothing to run from here
DaVinci Resolve Lua is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
15
tools declared
local
runs on your machine
688
downloads
What it does
Control the free edition of DaVinci Resolve 21.1 from Claude through a Lua script inside Resolve.
Quickstart
This one is not published to a package registry, so there is no one-line install: it is built and started the way its own source says.
Publishernot claimed
SAAll 1 server
saadk4081 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts DaVinci Resolve Lua as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This one is not published to a package registry, so there is no one-line install: it is built and started the way its own source says.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Reports whether the in-Resolve Lua bridge is running and reachable, with the reason when it is not (never started, stopped, Resolve gone, no reply, lock held), the bridge session (pid, start time, state directory), the platform, the self-install outcome of the two Lua scripts, configuration…
No parameter schema on file.
Runs a Lua 5.1 chunk inside DaVinci Resolve with the live resolve object and returns its first return value as JSON together with captured print output, the execution time and any error. The chunk can call any scripting-API method and change the project, so it counts as destructive. Synchronous…
No parameter schema on file.
Returns an overview of the open project: name and unique id, current page, database (type and name), current Media Pool folder, frame rate and resolution, timeline count, root-bin clip and sub-bin counts, and the current timeline (name, unique id, start timecode, start and end frame) when one is…
No parameter schema on file.
Lists the projects in the current project-manager folder of the current database, with last-modified and creation dates and notes where Resolve provides them, and marks the open one. Read-only. It does not switch projects; use open_project for that.
No parameter schema on file.
Lists every timeline of the open project: index, name, unique id, start and end frame, and video, audio and subtitle track counts, with the current one marked. Read-only. Use set_current_timeline to switch and get_timeline_items to read clips.
No parameter schema on file.
Lists the clips in one Media Pool bin (default the root bin) with name, unique id, file path, duration, fps, resolution, type, frame count and clip colour, paginated with offset and limit. Read-only. An unknown bin path answers with the bins available at the last level that resolved. It does not…
No parameter schema on file.
Lists the items on one track of the current timeline: name, unique id, type (video, audio, generator, transition), start, end and duration in frames (fractional when Resolve reports subframes), source start and end frames, enabled state, and the source file path when the item has a Media Pool…
No parameter schema on file.
Adds a marker to the current timeline at a frame counted from the timeline start (frame 0 is the first frame, whatever the start timecode) and returns the marker Resolve stored. Fails when the frame already holds a marker or lies outside the timeline. Writes to the project; it does not save it.…
No parameter schema on file.
Deletes every marker of one colour, or all markers when no colour is given, from the current timeline, and returns how many were removed and how many remain. Destructive and not undoable through this server: it refuses unless confirm is true. It does not delete markers on clips or in the Media Pool.
No parameter schema on file.
Makes the timeline with the given name the current timeline of the open project and returns its name, unique id and index. An unknown name answers with the known timeline names. It does not create timelines.
No parameter schema on file.
Loads the named project from the current project-manager folder, saving the open project first by default (LoadProject on an unsaved project can raise a dialog the bridge cannot answer). Returns the loaded project, the previous one and whether it was saved. The switch is not undoable through this…
No parameter schema on file.
Queues a render of the current timeline into an existing output directory with the given file name, optionally after loading a named render preset, starts it without the interactive dialog, and returns the job id plus the queued job entry and the current format and codec. It returns as soon as…
No parameter schema on file.
Returns one render job's status (JobStatus such as Ready, Rendering, Complete, Cancelled or Failed; completion percentage; error text; time taken or remaining) and whether Resolve is rendering at all. Read-only. An unknown job id answers with the known job ids.
No parameter schema on file.
Asks the in-Resolve bridge loop to exit cleanly (it marks its session stopped and ends the script). Afterwards every Resolve tool reports "bridge not running" until the user relaunches the script from Workspace > Scripts. It does not quit Resolve and does not touch the project.
No parameter schema on file.
Searches Blackmagic's shipped scripting reference for DaVinci Resolve 21.1 (DaVinciResolveScript.pyi method signatures and docstrings tagged with their class and line, TypedDict shapes, the README's sections including the lists of deprecated and unsupported calls, and the CHANGELOG) and returns…
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install DaVinci Resolve Lua or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 0.2.0 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings4 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest406ef81acfd0a4b567208cb0a68693490a4f0e48f2280b121364d1349fa48bcf
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (15 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| resolve_status | no tags | |
| run_lua | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| get_project_info | no tags | |
| list_projects | no tags | |
| list_timelines | no tags | |
| list_media_pool_clips | no tags | |
| get_timeline_items | no tags | |
| add_marker | state-write | state-write: declares readOnlyHint: false |
| delete_markers | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| set_current_timeline | state-write | state-write: declares readOnlyHint: false |
| open_project | state-write | state-write: declares readOnlyHint: false |
| render_current_timeline | state-write | state-write: declares readOnlyHint: false |
| get_render_status | no tags | |
| stop_bridge | state-write | state-write: declares readOnlyHint: false |
| scripting_api_docs | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest406ef81acfd0a4b5
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 0.2.0.
0.2.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish DaVinci Resolve Lua can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.