DaVinci Resolve
PYPI · DAVINCI-MCP
Typed, safe MCP server for DaVinci Resolve: every write verified, deletes confirmed, snapshots.
Available components
Last scanned (7 hours ago)
Scores higher than 66% of PyPI servers
Category Design and Media
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs uv_build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 16 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 3 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability71
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 13172 tokens (~248/item across 53 items; 52 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 99% of tool parameters carry a description.Partial
- Structured output schemas are declared (98% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 12 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 54 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 1 Nov 26 70
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/davinci-mcp@1.0.4
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | uv_build |
Background: Why install scripts are a supply-chain risk →
Dependencies 16 packages
| Packages resolved | 16 |
|---|---|
| Stale | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
ui_delete Ui (destructive) ~169
Remove ui objects. op.action (params; * = required): - ripple_delete_selection(keyboard_preset): Ripple delete the selected timeline clips via the UI (selection not API-readable). First call returns a plan + confirm_token; repeat it with confirm_token to apply. Calls known in advance (a sequence, the same change on several items): ONE batch_run.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm_token | string|null | – | From the first call's plan; repeat that call with it to apply. |
| dry_run | boolean | – | true: return the planned effect, change nothing. |
| op | object | yes | {action, ...params}. Parameters per action: see the description or this server's describe_action tool. |
| snapshot | boolean|null | – | true: back up the timeline/project first; omitted: server policy. |
| Name | Type | Req | Description |
|---|---|---|---|
| job | object|null | – | – |
| plan | object|null | – | – |
| receipt | object|null | – | – |
| status | string | yes | – |
No examples provided.
ui_read Ui (read) ~84
Read ui state, no side effects: use it to find ids and check results. op.action (params; * = required): - list_menu_items(path): List the items of a Resolve menu (top-level menu bar when path is empty).
| Name | Type | Req | Description |
|---|---|---|---|
| op | object | yes | {action, ...params}. Parameters per action: see the description or this server's describe_action tool. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| channel | string | yes | – |
| result | object | yes | – |
No examples provided.
ui_write Ui (write) ~230
Change ui state; may overwrite current values. Every change is read back from Resolve (receipt.verified=false means it did not take). op.action (params; * = required): - blade_at_playhead(keyboard_preset): Split the clips under the playhead on the Edit page (default Cmd+B). - invoke_menu(path*, validate_path): Click a Resolve menu item by its path (brings Resolve to front). - open_gallery_panel(keyboard_preset): Open the Color page and show the Gallery (needed for GalleryStillAlbum.ExportStills). - send_shortcut(command*, keyboard_preset): Run a named Resolve command via its default shortcut or menu (default preset only). Calls known in advance (a sequence, the same change on several items): ONE batch_run.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | true: return the planned effect, change nothing. |
| op | object | yes | {action, ...params}. Parameters per action: see the description or this server's describe_action tool. |
| snapshot | boolean|null | – | true: back up the timeline/project first; omitted: server policy. |
| Name | Type | Req | Description |
|---|---|---|---|
| job | object|null | – | – |
| plan | object|null | – | – |
| receipt | object|null | – | – |
| status | string | yes | – |
No examples provided.
vision_read Vision (read) ~200
Read vision state, no side effects: use it to find ids and check results. op.action (params; * = required): - contact_sheet(count, timecodes, from_markers, columns, thumb_width, labels): Tile frames sampled across the timeline (or at timecodes / markers) into one JPEG. - export_frame(timecode, max_width): Capture the timeline frame at a timecode as a JPEG (playhead is restored). - probe_media(path, clip): ffprobe summary of a file or Media Pool clip: codecs, fps, audio, color metadata. - screenshot_resolve(max_width): Screenshot of the DaVinci Resolve window (macOS, needs Screen Recording permission). - source_frames(path*, seconds*, max_width): Extract frames straight from a media file with ffmpeg (Resolve not needed).
| Name | Type | Req | Description |
|---|---|---|---|
| op | object | yes | {action, ...params}. Parameters per action: see the description or this server's describe_action tool. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| channel | string | yes | – |
| result | object | yes | – |
No examples provided.
workflow_write Workflow (write) ~223
Change workflow state; may overwrite current values. Every change is read back from Resolve (receipt.verified=false means it did not take). op.action (params; * = required): - apply_look: Apply a LUT to every video item, group them in a color group and grab a still. - build_vertical_reel: Build a vertical timeline from clips, add subtitles and optionally render it. - conform_from_edl: Import media + EDL as a timeline, fix offline events via Start TC, report linkage. - deliver: Render one or more outputs (preset/format/size) and report the real files produced. - title_overlay: Add an animated Text+ title (and Merge over the clip) to a timeline item's Fusion comp. Calls known in advance (a sequence, the same change on several items): ONE batch_run.
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | true: return the planned effect, change nothing. |
| op | – | yes | The action and its parameters. |
| snapshot | – | – | true: back up the timeline/project first; omitted: server policy. |
| Name | Type | Req | Description |
|---|---|---|---|
| job | object|null | – | – |
| plan | object|null | – | – |
| receipt | object|null | – | – |
| status | string | yes | – |
No examples provided.
How do I install the DaVinci Resolve MCP server?
DaVinci Resolve runs locally as a PyPI package, launched with uvx davinci-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · davinci-mcp
claude mcp add aedelon-davinci-mcp -- uvx davinci-mcp
What is the DaVinci Resolve MCP server?
DaVinci Resolve is an MCP server listed in the public MCP registry as io.github.Aedelon/davinci-mcp. Typed, safe MCP server for DaVinci Resolve: every write verified, deletes confirmed, snapshots. This page covers its PyPI package (davinci-mcp).
Is the DaVinci Resolve MCP server safe to use?
DaVinci Resolve scores 70 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the DaVinci Resolve MCP server expose?
DaVinci Resolve exposes 52 tools: ai_delete, ai_read, ai_write, app_delete, app_read, and 47 more. Their descriptions and schemas cost roughly 12,712 tokens of context every time the server is loaded.
Is the DaVinci Resolve MCP server still maintained?
DaVinci Resolve is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the DaVinci Resolve MCP server under?
DaVinci Resolve declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.