Davinci Resolve MCP

DaVinci Resolve MCP Server — AI Skill Reference

This document gives AI assistants the context needed to use the DaVinci Resolve MCP server effectively. It covers the tool landscape, page prerequisites, common workflow patterns, error recovery, and known gotchas.

What This Server Does

The DaVinci Resolve MCP server bridges AI assistants to DaVinci Resolve Studio via its official Scripting API. You can control every aspect of a post-production session — projects, timelines, clips, color grading, Fusion compositions, audio, render queues, and more — through natural language.

DaVinci Resolve must be running with Preferences > General > "External scripting using" set to Local. The server auto-launches Resolve if it is not running, but that first connection can take up to 60 seconds.

Workflow Integration plugins/scripts are a separate Resolve-hosted UI mechanism. They are not required for this MCP server, but docs/integrations/workflow-integrations.md summarizes when they are useful for optional in-Resolve panels, UIManager scripts, and render callback companions.

OpenFX plugins are native C++ image-effect plugins, not an MCP control surface. Use docs/notes/openfx-notes.md when diagnosing insert_ofx_generator failures or discussing optional OFX plugin development.

LUT files are directly relevant to Color-page graph actions. Use docs/notes/lut-notes.md when diagnosing graph.set_lut failures, validating .cube files, or explaining project_settings.refresh_luts.

Fusion templates are relevant to Edit/Cut page insertion actions. Use docs/notes/fusion-template-notes.md when diagnosing insert_fusion_generator or insert_fusion_title failures, template paths, .setting files, or .drfx bundles.

DCTL files are programmable color transforms/effects adjacent to LUT and OpenFX workflows. Use docs/notes/dctl-notes.md when diagnosing .dctl/.dctle discovery, ResolveFX DCTL plugin behavior, ACES DCTL IDT/ODT setup, or DCTL-as-LUT usage.

Codec plugins are native IO encode plugins that extend Deliver-page render formats/codecs. Use docs/notes/codec-plugin-notes.md when diagnosing missing custom render formats/codecs, .dvcp.bundle packaging, or IOPlugins install paths.

The fuse_plugin, dctl, and script_plugin compound tools (v2.5.0+) write Fuse plugin source, DCTL files, and Lua/Python scripts into Resolve's install directories. They are authoring tools — every other tool in this server wraps Resolve's scripting API, while these three emit and install plugin/script source. Status: lifecycle-verified in DaVinci Resolve Studio 20.3.2.9 for MCP-marked install/read/list/remove, regular DCTL refresh_luts, ACES/Fuse restart-required classification, Python installed-script execution, and Python/Lua run_inline. Use docs/kernels/extension-authoring-kernel.md for the kernel boundary map, docs/authoring/fuse-dctl-authoring.md for the Fuse + DCTL coverage matrix, and docs/authoring/script-plugin-authoring.md for the script DSL spec and the conversational-execution model. For hand-authoring .setting template files (Edit effects/transitions/titles/generators and Fusion macros) — the format, control catalog, thumbnail conventions, install paths, and gotchas, plus copyable starter templates — see docs/authoring/setting-files/.

Extension Authoring kernel actions (v2.16.0+) are exposed through script_plugin:

• extension_capabilities
• probe_fuse_lifecycle(name?, kind?, install?, cleanup?)
• probe_dctl_lifecycle(name?, kind?, category?, install?, refresh_luts?, cleanup?)
• probe_script_lifecycle(name?, language?, category?, install?, execute?, cleanup?)
• safe_install_extension(extension_type, name, source?|kind?, dry_run?)
• safe_remove_extension(extension_type, name, dry_run?)
• refresh_or_restart_required(extension_type, category?)
• extension_boundary_report(include_template_matrix?)

Key behavioral notes for script_plugin:

• run_inline(source, language) runs ad-hoc Lua/Python in Resolve and returns stdout + result — use this for one-off conversational queries against the Resolve API instead of building+installing a script.
• language accepts lua, py, or the human-facing aliases python and python3.
• execute(name, category, language) runs an installed script; Python stdout and stderr are captured, while installed Lua execution can return false from the Python bridge even when install/read/list/remove worked.
• Lua scripts: fusion.Execute() from the Python bridge is a no-op in Resolve 20.x — _run_inline_lua works around this with RunScript against a temp file plus completion-sentinel polling on app:SetData/GetData.
• Fuse install path on macOS is …/DaVinci Resolve/Fusion/Fuses/ (NOT Support/Fusion/Fuses/ as the SDK doc lists). The MCP path helpers handle this; if you're staging files manually, use the path the implementation emits.
• Resolve picks up new scripts without a restart; new Fuses need a restart to register; new DCTLs need project_settings(action='refresh_luts') (regular LUT category) or a restart (ACES IDT/ODT category).

Tool metadata (v2.17.1+) includes MCP ToolAnnotations for read-only, destructive, idempotent, and external-resource hints. Treat compound tool annotations as conservative because a single compound tool may expose both probe and mutation actions behind its action parameter. Continue to prefer safe_*, dry_run, probe_*, capabilities, and boundary_report actions before mutating Resolve state.

Two Server Modes

This skill document covers the compound server (the default). Each compound tool accepts an action string and an optional params object.

The compound server also registers MCP prompts. Use davinci_resolve_workflow as the compact operating brief, and use analyze_media as a slash-command style entry point for source-safe project, selected-clip, bin, file, or sequence analysis. The Analyze Media prompt executes directly by default, persists inspectable reports/artifacts under the project analysis root, requests host_chat_paths visual analysis (frames are extracted to disk and the host chat finalizes each clip via media_analysis(action="commit_vision", ...)), runs local transcription through the configured backend, and writes metadata plus source-time Media Pool markers back to the Resolve project unless the user opts out.

Anti-regression rule: do not silently downgrade media analysis. Source-safe means source media stays untouched; it does not mean no visuals, no transcript, no persisted report, no metadata writeback, or no Media Pool markers. Do not add include_visuals=false, include_transcription=false, publish_metadata=false, timed_markers=no, session_only=true, or dry_run=true unless the user explicitly asks for that opt-out, the target is a raw file path that cannot receive Resolve project writeback. The host_chat_paths vision protocol is: analyze_* returns a deferred payload with absolute frame_paths and a JSON schema; you must read those frames as images (Claude Code's Read tool handles JPG/PNG natively), produce the JSON, and call commit_vision for each clip. Skipping commit_vision leaves the run in pending_host_vision_analysis — surface that explicitly; do not call the analysis complete.

The deferred payload also includes a host_tool_choice_hint block. Hosts that respect this hint pass it as tool_choice={type:"tool", name:"media_analysis"} on the next API turn, hard-locking the agent into the correct next call. Hosts that don't recognize the field ignore it — the flow is unchanged for them.

Local Control Panel

If the user asks to open, launch, or inspect the Resolve MCP control panel, run this from the repository root:

venv/bin/python -m src.control_panel

The command starts the local control panel and opens the default browser. Use --no-open when running in a headless context, then give the user the printed localhost URL. The panel is local and single-user; it is an operational surface for server status, Resolve clips, source-safe analysis jobs, preferences, and diagnostics as those sections are added.

The Review tab → History button opens the timeline-history surface: per-timeline version chain, brain-edit deltas, manual archive, and rollback. Backed by timeline_versioning MCP actions; see that tool's section below for the underlying primitives.

Editorial Memory And Decision-Making

When the user asks for cutting, pacing, story shape, suspense, comedy timing, or tonal reframing, operate like an editor, not just a metadata scanner. Use docs/guides/editorial-decision-guide.md as the project-owned craft reference. The short version: emotion and story come first, then clarity, rhythm, eye trace, screen geography, continuity, and coverage variety.

Before analyzing or rebuilding anything, check whether the active project already contains useful evidence:

• media_analysis(action="coverage_report", params={"target": {...}}) — the pre-flight contract. Pure read; never triggers analysis. Returns per-clip state (analyzed / stale / missing / reuse_blocked / superseded_by_relink), layer presence, source_trust tier, and a recommended_action. The response carries an evidence_base summary string — lead any editorial or color recommendation with that line, before the creative answer.
• media_analysis(action="summarize") for project-wide rollup of warnings, motion distribution, and signed-report counts.
• media_analysis(action="get_report") when a manifest or report path is known.
• timeline(action="list")
• timeline(action="get_current")
• timeline(action="probe_timeline_structure")
• timeline(action="source_range_report")
• timeline_markers(action="get_all")
• media_analysis(action="review_timeline_markers") when marker imagery matters

Reuse prior analysis unless it is stale, incomplete, missing a modality, or flagged superseded_by_relink because Resolve's source clip was replaced after analysis ran. Coverage_report surfaces all of these in one read. Do not re-run visual analysis just because the edit task is new if a current report already has keyframes, motion variance, and usable visual descriptions. Add transcription, host_chat_paths vision (followed by commit_vision), marker review, or source range checks only when that missing evidence changes the decision. Use force_refresh=true only when the user asks for a fresh read or when cache signatures show the source, prompt, depth, or requested modality has changed.

Source-trust filtering: coverage_report accepts min_source_trust (one of auto, filename, low, medium, high). Clips below the threshold appear in summary.clips_needs_higher_trust and are reported with below_min_source_trust=true. Use medium for routine work, high for shot-matching or look-development passes where confident scene/identity reads matter.

For finished-video editorial work, scene detection and motion variance are guardrails, not story. Use them to avoid black frames, flash frames, corrupt ranges, and accidental cut points. Let transcript, sound events, complete thoughts, reactions, and decisive visual frames drive the actual edit.

After creating or modifying a timeline variant, do a second pass before calling the work done:

• timeline(action="detect_gaps_overlaps")
• timeline(action="source_range_report")
• timeline_markers(action="get_thumbnail_image") at important markers and cuts
• Compare each marker name against the Resolve-rendered frame; revise the marker or edit if the image contradicts the plan.

Do not depend on personal, external, or workstation-specific editorial context. For this project, keep the editorial craft reference self-contained in docs/guides/editorial-decision-guide.md and keep this SKILL.md focused on operational use of the MCP.

Color Memory And Decision-Making

When the user asks for color correction, shot matching, look development, LUTs, DCTLs, DRX grades, Gallery stills, or color-group workflows, use docs/guides/color-decision-guide.md as the project-owned color reference.

Be explicit about the API boundary:

• Directly creatable/control surfaces: CDL values on an existing node, grade versions, color-group assignment, LUT assignment on existing nodes, node enable/cache state, LUT/DCTL assets, Gallery still import/export, and grade copy/export helpers.
• Opaque full-grade surfaces: copied grades, imported/exported .drx stills, and manually built Resolve node graphs. These can carry full grades, but the MCP applies or copies them as packages.
• Not directly creatable from structured params: new node trees, Lift/Gamma/Gain wheel values, log/HDR palette values, curves, qualifiers, power windows, tracking, Color Warper, and detailed ResolveFX/OFX parameter edits.

Before any color recommendation, run media_analysis(action="coverage_report", params={"target": {...}, "min_source_trust": "medium"}) (use "high" for shot-matching or look-development passes). Lead the response with the returned evidence_base line before the grade plan. Coverage_report surfaces relink-superseded clips that must be re-analyzed before being graded from prior visual descriptions.

For safe color work, start with timeline_item_color(action="grade_boundary_report"), timeline_item_color(action="grade_version_snapshot"), timeline_item_color(action="probe_node_graph"), and a Resolve-rendered frame reference for the target shot or shots. Use thumbnails, contact sheets, Gallery stills, marker frames, or existing visual analysis reports before writing a grade, and cite the inspected frames in the response. When the API can safely provide them, compare matched untreated/bypass, current, and after frames at the same timecodes, then restore the previous active version or node-enabled state after any temporary bypass capture. Treat untreated frames as diagnostic evidence, not as permission to discard an existing creative grade.

Prefer safe_set_cdl for small reversible primary corrections. Use DRX/stills or grade copy only when the user accepts whole-grade replacement/transfer semantics. Use DCTL/LUT authoring only for reusable mathematical transforms, not as a substitute for hand-built windows, qualifiers, or tracked secondaries. Do not apply blind/global grades unless the user explicitly asks for that. When the user asks to build on or adjust an existing grade, preserve the current grade/version as the starting point, create or switch to a recoverable adjustment version, and apply only incremental changes through supported controls. Do not reset grades, replace graphs, or apply DRX/copy-grade whole-grade artifacts unless replacement or transfer semantics are explicitly accepted. Distinguish Resolve's default one-node graph from an existing creative grade; only describe a creative grade when active tools, LUTs, or other grade state are present.

For sequence-wide looks, prefer a duplicated timeline, batch creation of reference/current/look versions across all target clips, and one bulk Resolve script for repeated version, group, or CDL operations. Use color groups for shared scene-level intent only when they fit the work: group pre-clip for shared normalization, clip versions for shot-specific matching, and group post-clip for the creative look. Sampling can guide a first pass, but final handoff should state the reviewed scope; short sequences should be checked shot by shot.

Page Context Requirements

DaVinci Resolve is a page-based application. Certain operations only work on specific pages. Always confirm or switch pages before calling page-sensitive tools.

When a tool returns an unexpected False or an error about context, check whether you are on the correct page first.

Tool Map

App Control

resolve_control — App-level operations.

Key actions:

• launch — connect to or start Resolve; call this first if any tool returns a "Not connected" error
• get_version — returns {product, version, version_string}
• api_truth(query?) — look up behaviorally-verified facts about quirky/unreliable Resolve API behavior (no connection needed); filter by substring
• verification_stats — readback-verification tally (verified/contradicted/ unverified) since server start (no connection needed)
• get_page / open_page(page) — read or switch the active page
• get_keyframe_mode / set_keyframe_mode(mode)
• get_fairlight_presets — Resolve 20.2.2+; returns available Fairlight preset names
• quit — terminates Resolve (destructive; confirm with user first)

layout_presets — Save, load, export, import, delete UI layout presets.

render_presets — Import and export render and burn-in presets.

Project Management

project_manager — CRUD on projects.

Key actions: list, get_current, create(name, media_location_path?), load(name), save, close, delete(name), import_project(path), export_project(name, path), archive, restore

Project / Database / Archive kernel actions (v2.15.0+) add guarded project lifecycle, settings, database, preset, and archive boundary helpers:

• project_capabilities
• probe_project_lifecycle
• probe_project_settings(keys?, try_write?, dry_run?)
• safe_project_create(name, media_location_path?, dry_run?)
• safe_project_export(name, path, with_stills_and_luts?, dry_run?)
• safe_project_import(path, name, dry_run?)
• safe_project_archive(name, path, src_media=false, render_cache=false, proxy_media=false, dry_run?)
• safe_project_restore(path, name, dry_run?)
• safe_project_delete(name, close_current?, dry_run?)
• safe_set_project_settings(settings, restore?, dry_run?)
• project_settings_snapshot(name?)
• database_capabilities
• safe_set_current_database(db_info, dry_run?, allow_switch?)
• preset_lifecycle_probe
• project_boundary_report

Health check and declarative spec (v2.28.0+):

• lint — graded project health pre-flight returning {ok, counts, issues}. Issues (error / warning / info) cover: no project, no current timeline, mixed frame rates across timelines, empty timeline, render format unset, color science unmanaged, offline media, and unanalyzed clips. Composed from existing probes; safe read-only.
• diff_to_spec(spec_path | spec) — preview drift between a declarative spec and the live project WITHOUT mutating. Returns {actions, diff, change_count}.
• plan_spec(spec_path | spec) — the ordered action list as a dry run.
• apply_spec(spec_path | spec, dry_run?, run_hooks?, continue_on_error?) — reconcile the project toward the spec. Idempotent (re-runs are no-ops); color/ HDR settings apply in dependency order; markers added only when absent; explicit settings override a named color_preset; before/after shell hooks run only with run_hooks=true. The spec is YAML or JSON: {project, color_preset?, settings?, timelines:[{name, fps?, settings?, markers?}], hooks?}. Note: apply_spec reconciles the currently open or already-existing project; creating a brand-new project from a spec depends on Resolve's CreateProject succeeding (it can return None when an unsaved project blocks the switch).

Safe project actions require _mcp_ names and temp paths by default. Database switching dry-runs by default because Resolve closes open projects when switching databases. Archive source media/cache/proxy flags are rejected unless explicitly opted in.

project_manager_folders — Navigate project folders.

Key actions: list, get_current, create(name), open(name), goto_root, goto_parent

project_manager_database — Switch databases.

Key actions: get_current, list, set_current(db_info)

project_manager_cloud — Cloud projects (requires Resolve cloud infrastructure; most users will not have this).

project_settings — Project metadata, settings, color groups, and misc operations on the open project.

Key actions: get_name, set_name(name), get_setting(name?), set_setting(name, value), get_color_groups, add_color_group(name), delete_color_group(name), export_frame_as_still(path), load_burnin_preset(name), insert_audio(media_path, ...), apply_fairlight_preset(preset_name), project_summary(include_clips?, clip_limit?) — live structural readout (current page, timeline count, media-pool inventory by type)

Media

media_storage — Browse mounted volumes and import files.

Key actions: get_volumes, get_subfolders(path), get_files(path), import_to_pool(items) — items is a list of file path strings

media_pool — Full Media Pool management.

Key actions: get_root_folder, get_current_folder, set_current_folder(path), add_subfolder(name), create_timeline(name), import_timeline(path, options?), import_media(paths), delete_clips(clip_ids), move_clips(clip_ids, target_path), setup_multicam_timeline(name, clip_ids|angles, sync_mode?, include_audio?, dry_run?), get_selected, set_selected(clip_id), export_metadata(path, clip_ids?)

Media Pool / Ingest kernel actions (v2.8.0+) add safer agent-facing workflows: ingest_capabilities, probe_media_pool, probe_ingest_item, safe_import_media, safe_import_sequence, safe_import_folder, organize_clips, copy_metadata, normalize_metadata, probe_clip_properties, metadata_field_inventory, safe_relink, safe_unlink, link_proxy_checked, link_full_resolution_checked, set_clip_marks, clear_clip_marks, copy_clip_annotations, setup_multicam_timeline, and media_pool_boundary_report. See docs/kernels/media-pool-ingest-kernel.md for the live-tested support map.

setup_multicam_timeline is a helper, not a native multicam API wrapper. It creates a source-safe stacked prep timeline with one angle per video track, optional matching audio tracks, and stack_start, source_timecode, or explicit record_frame placement. Native multicam clip creation, angle switching, and flattening remain Resolve UI workflows; see docs/guides/multicam-setup-guide.md.

Note: folder path arguments use slash notation like "Master/SubFolder". "Master" or "/" refers to the root folder.

folder — Operations on a specific Media Pool folder.

Key actions: get_clips(path?), get_subfolders(path?), export(path?, export_path), transcribe_audio(path?, use_speaker_detection?), clear_transcription(path?), perform_audio_classification(path?), analyze_for_intellisearch(path?, identify_faces?, is_better_mode?), analyze_for_slate(path?, marker_color?), remove_motion_blur(path?, deblur_option?) (Resolve 21+; the last three need AI Extras, and remove_motion_blur is confirm-token gated)

media_pool_item — Read/write clip metadata and properties. All actions require a clip_id (the UUID returned by GetUniqueId()).

Key actions: get_name, get_metadata(key?), set_metadata(key, value), get_clip_property(key?), set_clip_property(key, value), get_clip_color, set_clip_color(color), link_proxy(proxy_path), replace_clip(path), set_name(name), link_full_resolution_media(path), replace_clip_preserve_sub_clip(path), monitor_growing_file, transcribe_audio(use_speaker_detection?), clear_transcription, get_transcription (read back {text, truncated, status, has_transcription}; truncated flags when Resolve's preview cut the text off), perform_audio_classification, analyze_for_intellisearch(identify_faces?, is_better_mode?), analyze_for_slate(marker_color?), remove_motion_blur(deblur_option?) (Resolve 21+; AI Extras / confirm-token gated as noted above), get_audio_mapping, get_mark_in_out, set_mark_in_out

media_pool_item_markers — Markers and flags on clips in the Media Pool. All actions require a clip_id.

Key actions: add(frame, color, name, note, duration), get_all, delete_by_color(color), delete_at_frame(frame), add_flag(color), get_flags, set_name(name)

media_analysis — Project-scoped media intelligence and guarded metadata publishing.

Media Analysis and editorial-assist actions (v2.17.0+) add source-safe planning, report reuse, persisted analysis execution, host_chat_paths visual review (finalized per clip via commit_vision), transcription, default Resolve metadata/marker writeback, and timeline-level editorial helpers.

Key actions: capabilities, install_guidance, resolve_output_root, plan, coverage_report, analyze_file, analyze_clip, analyze_bin, analyze_project, detect_sync_events, add_sync_event_markers, publish_clip_metadata, commit_vision, summarize, get_report, build_index, index_status, query_index, start_batch_job, run_batch_job_slice, batch_job_status, list_batch_jobs, cancel_batch_job, resume_batch_job, review_timeline_markers, cleanup_artifacts, db_status, db_ingest, get_panel_state, set_panel_state, session_start_context, update_clip_field, update_shot_field, get_field_history, revert_field, list_corrections, deepen, commit_shot_vision, vision_pending_sweep, build_embeddings, find_similar, detect_entities, commit_entities, list_entities, prepare_bin_briefing, commit_bin_summary, detect_shot_relationships, commit_shot_relationships, and list_shot_relationships.

Cross-clip entities + bin briefing v2 (v2.44.0+). Recurring people/places/props across a project's media, found cheaply and confirmed with ONE vision call per cluster:

• detect_entities(threshold?, min_cluster_size?) clusters the v10 CLIP frame vectors (build visual embeddings first), writes provisional entity rows + appearances, and returns a deferred payload with one representative frame per cluster (caps pre-checked, estimate inlined). The host chat reads those frames and calls commit_entities(entities=[{entity_index, kind, label, description, confidence, merge_with?}], vision_token) — conservative labels only (describe what's visible; never guess names). merge_with collapses clusters that show the same entity.
• list_entities returns labeled entities with per-clip/shot appearances; the panel's Review page shows a "Recurring across this bin" card.
• prepare_bin_briefing returns entities + per-clip summaries (text-only, no vision cost); the host writes a colleague-style markdown briefing and calls commit_bin_summary(briefing, briefing_token), which lands in memory/bin_summary.md above the v2.0 aggregate.

Cross-shot relationships (v2.49.0+). Pattern recognition only (spec §4 — no editorial suggestions): same_setup_as / alt_take_of (symmetric) and continues_from (directional; the source shot continues from the target).

• detect_shot_relationships(setup_threshold?, alt_take_threshold?, continues_band?, max_candidates?) — pairwise cosine over the per-shot visual vectors (build visual embeddings first; raise max_frames_per_clip if shot coverage is partial), plus transcript continuity as a second signal for continues_from. Returns a deferred payload with a representative frame PAIR per candidate (caps pre-checked, two frames per candidate). Candidates live only in the detection-state stash until committed — re-detect replaces them.
• The host chat reads BOTH frames of each pair and calls commit_shot_relationships(relationships=[{candidate_index, verdict: confirm|reject, relationship_type?, confidence?}], vision_token). Confirm only what the frames show; reject lookalikes. Overriding the suggested type is allowed. Committed rows supersede prior machine rows for the same pair.
• list_shot_relationships(clip_id?, shot_uuid?, relationship_type?) — current rows with clip/shot context on both ends. The shot page's Relationships group fills from these rows, and plan_swap prefers confirmed alt_take_of alternates over raw cosine (the rationale states which basis ranked each alternate).

Embeddings + similarity (v2.43.0+). Local-compute semantic search; no vendor tokens, so nothing here touches the caps ledger. Backends are detected, never installed (capabilities lists them with install guidance): text = ollama serving nomic-embed-text or sentence-transformers; visual = open_clip (ViT-B-32, needs torch); audio (v2.51.0+) = CLAP via transformers (laion/clap-htsat-unfused, preferred) or the laion_clap package — needs torch + ffmpeg.

• build_embeddings(kinds=["text","visual","audio"]?, clip_id?) — idempotent; embeds clip summaries, shot descriptions (+ deep field groups), transcript segments, and sampled frames (per-shot visual vector = mean of its frames'). kinds=["audio"] embeds one CLAP window per shot (center-cropped to ~10s, piped from the source media as raw PCM — read-only, no temp files) plus a clip-level mean vector; clips whose media is offline are reported in skipped_missing_media. Only re-embeds entities whose content changed.
• find_similar(text=… | clip_id=… | clip_id+shot_index, kind="text"|"visual"|"audio", entity_types?, limit?) — brute-force cosine over the project's vectors. Free-text visual queries use the CLIP text encoder ("cracked windshield" finds the frame); free-text audio queries use the CLAP text encoder ("engine revving" finds the shot). Results carry scores plus clip/shot/segment context. The panel search box gains a Semantic toggle when a text backend is detected. Vectors live in the per-project DB (schema v10).

Deep shot-level vision tier (v2.42.0+). Opt-in, estimate-first. Two entry points share one per-shot schema (Visual / Content / Production / Editorial / Cuttability / description / confidence):

• depth="deep" on any analyze action extends the deferred host-vision payload with deep_shot_schema; each shot_descriptions entry must carry the field groups. The first deep run returns confirmation_required with a token-cost estimate — re-call with confirm_deep=true. Caps still apply.
• deepen(clip_id|clip_dir, shot_index?|shot_indices?) runs the pass post-hoc on an already-analyzed clip. First call returns the estimate + confirm_token; re-call with the token to get the deferred payload, read its frame_paths, and commit via commit_shot_vision(clip_id, shots=[{shot_index, ...groups...}], vision_token). Deep fields land as vision_deep_v1 provenance rows; human corrections always survive. Shots with no sampled frames on disk get 1–2 frames re-extracted via ffmpeg (read-only on source media). vision_pending_sweep(expire?, max_age_days?, reoffer?) lists clips stuck in pending_host_analysis; reoffer=true returns each clip's stored deferred payload to finish the run, expire=true stamps them expired_host_analysis so pendings never linger silently.

DB-canonical analysis store (v2.41.0+). The per-project SQLite DB (_soul/timeline_brain.sqlite, schema v9+) is the source of truth for clip analysis; analysis.json is a derived export written in lockstep. Analysis runs write rows first (clips, shots, per-field subjective provenance, transcript segments, sampled frames, QC observations) and then export the JSON. Human corrections recorded via update_clip_field / update_shot_field live as row-level provenance and always survive re-analysis. Readers (panel API, exports) load DB-first and fall back to analysis.json for reports that predate v9. db_status reports schema version + row counts; db_ingest migrates an existing project's JSON reports (and corrections.json sidecars) into the DB — run it once on older analysis roots. The tool never installs dependencies and validates that outputs stay under davinci-resolve-mcp-analysis project roots rather than beside source media. Executed Resolve-target analysis defaults to running, persisting inspectable artifacts, and publishing metadata plus Media Pool clip markers. Use dry_run=true, publish_metadata=false, timed_markers=no, or session_only=true with keep_artifacts=false to disable those defaults for a run. Persisted analysis refreshes the local SQLite search index automatically unless auto_build_index=false is set; build_index remains the manual rebuild action for existing reports. quick uses ffprobe metadata; standard adds ffmpeg read-through checks, cut-boundary analysis from full-stream scene detection, flash-frame candidates, motion/variance scoring, analysis keyframes, and sidecar reports. depth controls which layers run; a separate sampling_mode controls how many frames each clip gets for visual analysis (and thus token cost): fixed (Economy, flat content-blind frames), per_minute (Balanced, frames scale with duration), adaptive_capped (Thorough, content-aware bounded to [frame_floor, frame_ceiling] — recommended/default), or adaptive (Thorough uncapped). When no default is saved, the first analyze returns confirmation_required with a sampling_mode_prompt; choosing a mode saves it as the default. Pass sampling_mode per call for a one-off. The mode owns frame count — analysis_caps.frames_per_clip is a safety ceiling above it, not the primary dial. By default, planning checks the active project's analysis root and bounded related project-version roots for existing reports, then marks matching clips skip_execution=true when those reports already contain the requested technical, motion, transcription, and vision layers. Resolve clip records also carry the published third-party davinci_resolve_mcp.analysis_report_path when metadata writeback has run; use that provenance as a first-class reuse hint even if the report lives under a previous project-version analysis root. The planner also maintains an analysis_registry.json under the analysis base root. This registry indexes report paths by source path, clip id, media id, and signature so project renames and versioned Resolve projects can still find prior work quickly. Reports include cache signatures with source stat, depth, frame budget, prompt hash, and requested modalities. Use force_refresh=true for a fresh read, max_report_age_days for freshness limits, and reuse_policy="fresh" when unsigned older reports should not be reused. Pass reuse_existing=false only when the user explicitly wants to ignore memory; pass search_related_project_roots=false only for intentionally isolated runs. If Resolve metadata shows prior MCP analysis but the planner cannot validate a matching report, execution returns status="reuse_blocked" instead of silently reanalyzing. Treat that as a project-memory integrity warning; restore the report or pass force_refresh=true only when the user explicitly wants fresh analysis. Transcription, visual analysis, metadata writeback, and Media Pool marker writeback are default-on. Vision uses vision.provider="host_chat_paths": analyze actions extract representative frames to disk under the project analysis root and return a deferred payload containing absolute frame_paths, a shot_table mapping each detected shot range to its in-shot frame_indices, the JSON schema, and a commit_action. The host chat must read those frames as local images, produce JSON per the schema (including one shot_descriptions entry per shot_index in the shot_table, grounded only in the frames listed for that shot), and call media_analysis(action="commit_vision", params={clip_id, visual, vision_token}) per clip to merge the visual report, rebuild Media Pool clip markers, and publish vision-dependent metadata to Resolve. Each Resolve shot marker inherits its description from shot_descriptions[shot_index]; missing entries fall back to an in-range analysis_keyframe and finally to a clip-summary-tagged fallback — never to a neighbour shot's description. The manifest exposes vision_pending=True and pending_action so callers know what is incomplete. Pass include_visuals=false, include_transcription=false, publish_metadata=false, or timed_markers=no to opt out. Agents must not add those opt-out flags preemptively; use them only when requested or when a target boundary requires it. Standard/deep runs prioritize first/last usable frames plus before/after cut-boundary frames as the sampled set. Skipping commit_vision leaves the run in pending_host_vision_analysis — that is a failure mode to surface, not a silent downgrade. The local mock providers are for tests and do not send frames off-machine.

When creating timelines through media_pool, use if_exists="reuse" for idempotent reruns, if_exists="version" for deliberate alternate cuts, and if_exists="fail" when duplicate names indicate a workflow error. Use detect_sync_events before multicam setup, deliverable QC, or single-camera sync review when the user needs likely 2-pop or slate-clap locations. It reads source audio through FFmpeg/FFprobe only, returns advisory frames/timecodes and per-file record_offset suggestions, and never installs FFmpeg automatically. It also returns marker suggestions; add_sync_event_markers remains an explicit marker-write action for standalone sync detections. Use publish_clip_metadata when the user wants analysis to become searchable inside Resolve. It analyzes or reuses reports, proposes field-specific merges for Description, Comments, Keywords, People, and optional slate-derived fields, stores provenance in third-party metadata, and writes metadata plus source-time markers by default for executed Resolve-target analysis. Disable a write run with dry_run=true, publish_metadata=false, or timed_markers=no. review_timeline_markers creates a labeled Resolve-rendered marker contact sheet plus JSON sidecar; with vision.enabled=true it returns a host_chat_paths review payload (image_path + prompt) so the host chat can read the sheet and answer inline — no commit step required for marker review.

Before calling analyze_*, prefer summarize and get_report to discover existing reports for the active project. If reports exist, use them as the working memory for edit decisions and only request fresh analysis when a missing layer changes the decision. If a user is making story or audio-spine decisions and transcription is available but disabled, tell them that transcript analysis may materially improve the edit instead of silently skipping it. Resolve-native transcription changes project state; use it only when that mutation is intentional.

Timelines

edit_engine — Evidence-driven edit loops (v2.45.0+): selects assembly, tighten, swap.

Every loop is plan → confirm → execute. plan_* actions are dry-run by construction: they query the DB-canonical analysis store and return a per-decision rationale plus a stored plan_id (plans persist under memory/edit_plans/ with a content fingerprint, so a stale

…(truncated)