davinci-resolve-mcp 2.28.1 → 2.30.0

package/CHANGELOG.md

@@ -2,6 +2,81 @@
 
 Release history for the DaVinci Resolve MCP Server. The latest release is summarized in the root README; older entries live here to keep the README focused.
 
+## What's New in v2.30.0
+
+Adds the **Resolve 21 AI-ops ledger** — usage/time/file accounting for the
+Resolve-local AI operations added in v2.29.0 (audio classification, IntelliSearch,
+slate, motion-deblur, speech generation). These run on Resolve's own GPU/AI engine
+and do **not** consume the Claude-side analysis token budget, so they get their
+own ledger instead of being metered by the analysis-caps layer.
+
+**What's tracked.** Every run of the five 21.0 ops records: op name, op class
+(`analysis` vs `render`), clip id, success/failure, wall-clock time, and — for the
+two media-creating ops (`remove_motion_blur`, `generate_speech`) — the output
+file path and byte size. The reliable signal is invocation counts + the
+file/disk accounting for the creators; durations for the bool-returning analysis
+ops reflect the script-call time (some queue work inside Resolve).
+
+- **New table** `resolve_ai_op_usage` (timeline_brain DB schema v7).
+- **New module** `src/utils/resolve_ai_ledger.py` — `timed()` context manager +
+  `record_op` / `get_usage` / `get_summary`. All writes are best-effort and never
+  block or mask the underlying Resolve op.
+- **Instrumentation** wraps the consolidated `folder` / `media_pool_item`
+  `perform_audio_classification` / `clear_audio_classification` /
+  `analyze_for_intellisearch` / `analyze_for_slate` / `remove_motion_blur`
+  handlers and `project_settings.generate_speech`.
+- **New MCP action** `media_analysis(action="get_resolve_ai_usage", session_only?, op?, limit?)`
+  returns the per-op summary + recent runs.
+- **Control panel**: a read-only "Resolve 21 AI ops" card (`/api/resolve_ai_usage`)
+  shows runs, success/fail, total time, and files/bytes created.
+
+Phase 1 of a staged build (ledger → interactive console → governance). Granular
+`--full` server instrumentation is deferred — the ledger covers the consolidated
+server, which is the default surface. Validated live against Resolve Studio 21.0.0.47.
+
+## What's New in v2.29.0
+
+Adds the **DaVinci Resolve 21.0** scripting-API additions. Every new method is
+runtime-detected (`_requires_method`/capability flags), so the tools stay inert
+on older Resolve builds and activate automatically on Resolve 21+.
+
+**New AI analysis actions** on the `folder` and `media_pool_item` compound tools
+(and mirrored as granular `--full` tools):
+
+- `perform_audio_classification` / `clear_audio_classification` — classify clip
+  audio into categories and subcategories.
+- `analyze_for_intellisearch(identify_faces?, is_better_mode?)` — IntelliSearch
+  analysis with optional face identification. Requires the *AI IntelliSearch* Extra.
+- `analyze_for_slate(marker_color?)` — slate/clapboard detection that drops a
+  marker of the chosen color (validated against the 16 Resolve marker colors).
+  Requires the *AI Slate ID* Extra.
+- `remove_motion_blur(deblur_option?)` — renders motion-deblurred copies. This
+  **creates new media files** (source media is never modified) and is therefore
+  **confirm-token gated**: the first call returns a preview + token, the second
+  call (with the token) runs.
+
+**Speaker-detection transcription.** `transcribe_audio` now accepts an optional
+`use_speaker_detection` boolean (Resolve 21+); omit it to use the project's
+Speech Recognition setting.
+
+**Speech generation.** `project_settings(action="generate_speech", ...)` wraps
+`Project.GenerateSpeech` (AI text-to-speech). It creates a new audio item and
+optionally places it on the timeline, so it is also confirm-token gated.
+Requires the *AI Speech Generator* Extra. Granular `--full` tool: `generate_speech`.
+
+**Session control.** `resolve_control(action="disable_background_tasks_for_current_session")`
+wraps `Resolve.DisableBackgroundTasksForCurrentResolveSession()` to quiet
+background work during heavy scripted runs.
+
+**Capability surface.** The `media_analysis` transcription-capability report and
+the control panel's boot payload (`resolve.ai_features`) now list which 21.0 AI
+methods are available and which Extras each gated method needs.
+
+Notes: these are Resolve-local GPU/AI operations and do not consume the
+Claude-side analysis token budget, so they are not metered by the analysis-caps
+layer; the derivative-creating ones are protected by the confirm-token gate
+instead. The granular `--full` server grew from 329 to 341 tools.
+
 ## What's New in v2.28.1
 
 Bug-fix release.

package/README.md

@@ -1,9 +1,9 @@
 # DaVinci Resolve MCP Server
 
-[![Version](https://img.shields.io/badge/version-2.28.1-blue.svg)](https://github.com/samuelgursky/davinci-resolve-mcp/releases)
+[![Version](https://img.shields.io/badge/version-2.30.0-blue.svg)](https://github.com/samuelgursky/davinci-resolve-mcp/releases)
 [![npm](https://img.shields.io/npm/v/davinci-resolve-mcp.svg?label=npm&color=CB3837)](https://www.npmjs.com/package/davinci-resolve-mcp)
 [![API Coverage](https://img.shields.io/badge/API%20Coverage-100%25-brightgreen.svg)](docs/reference/api-coverage.md)
-[![Tools](https://img.shields.io/badge/MCP%20Tools-32%20(329%20full)-blue.svg)](#server-modes)
+[![Tools](https://img.shields.io/badge/MCP%20Tools-32%20(341%20full)-blue.svg)](#server-modes)
 [![Tested](https://img.shields.io/badge/Live%20Tested-98.5%25-green.svg)](docs/reference/api-coverage.md#test-results)
 [![DaVinci Resolve](https://img.shields.io/badge/DaVinci%20Resolve-18.5+-darkred.svg)](https://www.blackmagicdesign.com/products/davinciresolve)
 [![Python](https://img.shields.io/badge/python-3.10+-green.svg)](https://www.python.org/downloads/)
@@ -50,7 +50,7 @@ The command starts a localhost server and opens the control panel in your browse
 | Mode | Entry point | Tools | Best for |
 |------|-------------|-------|----------|
 | Compound | `src/server.py` | 32 | Default mode for most assistants. Related Resolve operations are grouped behind action parameters to keep context usage low. |
-| Full / granular | `src/server.py --full` or `src/resolve_mcp_server.py` | 329 | Power users who want one MCP tool per Resolve API method. |
+| Full / granular | `src/server.py --full` or `src/resolve_mcp_server.py` | 341 | Power users who want one MCP tool per Resolve API method. |
 
 The compound server is recommended unless you specifically need the granular one-tool-per-method surface.
 
@@ -99,7 +99,7 @@ The default server is a local stdio process launched by your MCP client; it does
 
 | Metric | Value |
 |--------|-------|
-| MCP Tools | **32** compound / **329** granular |
+| MCP Tools | **32** compound / **341** granular |
 | Kernel Actions | **136** guarded workflow actions across 9 compound tools |
 | API Methods Covered | **336/336** (100%) |
 | Methods Live Tested | **331/336** (98.5%) |
@@ -136,7 +136,7 @@ Extension authoring references live in [docs/authoring](docs/authoring/). Resolv
 - Python 3.10+ (3.10-3.12 is the lowest-risk range). Python 3.13/3.14 also work on recent Resolve builds (verified on Studio 20.3.2); older builds may fail to connect on 3.13+, in which case use 3.10-3.12.
 - Resolve external scripting set to **Local**.
 
-Resolve 19.1.3 remains the compatibility baseline. Resolve 20.x scripting calls are additive, version-guarded, and live-tested on 20.3.2. Resolve 21 beta APIs are intentionally deferred until stable.
+Resolve 19.1.3 remains the compatibility baseline. Resolve 20.x scripting calls are additive, version-guarded, and live-tested on 20.3.2. Resolve 21.0 scripting additions (audio classification, speaker-detection transcription, IntelliSearch, slate analysis, motion-deblur, speech generation, session background-task control) are exposed behind runtime capability detection, so they stay inert on older builds and activate automatically on Resolve 21+.
 
 ## Development
 

package/docs/SKILL.md

@@ -101,7 +101,7 @@ before mutating Resolve state.
 | Mode | Entry point | Tool count | Use when |
 |---|---|---|---|
 | Compound (default) | `src/server.py` | 32 tools | Most workflows — keeps context lean |
-| Granular (full) | `src/server.py --full` | 329 tools | Power users needing one tool per API method |
+| Granular (full) | `src/server.py --full` | 341 tools | Power users needing one tool per API method |
 
 This skill document covers the **compound server** (the default). Each compound
 tool accepts an `action` string and an optional `params` object.
@@ -442,7 +442,10 @@ Note: `folder path` arguments use slash notation like `"Master/SubFolder"`.
 **`folder`** — Operations on a specific Media Pool folder.
 
 Key actions: `get_clips(path?)`, `get_subfolders(path?)`, `export(path?, export_path)`,
-`transcribe_audio(path?)`, `clear_transcription(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()`).
@@ -452,7 +455,10 @@ Key actions: `get_name`, `get_metadata(key?)`, `set_metadata(key, value)`,
 `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`, `get_audio_mapping`, `get_mark_in_out`, `set_mark_in_out`
+`transcribe_audio(use_speaker_detection?)`, `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`.
@@ -662,6 +668,15 @@ effective values + a usage rollup (clip / job / day) with percent-consumed.
 counts for one scope. Usage is tracked in
 `<project>/_soul/timeline_brain.sqlite` (`analysis_token_usage` table).
 
+Resolve 21's local AI ops (audio classification, IntelliSearch, slate,
+motion-deblur, speech generation) run on Resolve's own GPU/AI engine and do NOT
+spend the Claude analysis token budget — they are tracked separately in the
+`resolve_ai_op_usage` table. Inspect with
+`media_analysis(action="get_resolve_ai_usage", session_only?, op?, limit?)` →
+`{summary, recent}` (invocation counts, wall-clock, and files/bytes created by
+`remove_motion_blur` / `generate_speech`). The control panel shows the same as a
+read-only "Resolve 21 AI ops" card.
+
 The caps layer:
 - Slices `frame_paths` to `frames_per_clip` before the host LLM sees them.
 - Downscales each sampled frame in place to `max_frame_dim_pixels` (Pillow;

package/docs/contributing.md

@@ -64,7 +64,7 @@ davinci-resolve-mcp/
 ├── install.py                    # Universal installer (macOS/Windows/Linux)
 ├── src/
 │   ├── server.py                # Compound MCP server — 32 tools (default)
-│   ├── resolve_mcp_server.py    # Thin full-server entrypoint — 329 tools
+│   ├── resolve_mcp_server.py    # Thin full-server entrypoint — 341 tools
 │   ├── granular/                # Modular full-server implementation
 │   └── utils/                   # Platform detection, Resolve connection helpers
 ├── tests/                       # 5-phase live API test suite + Resolve 20 delta (331/331 pass)

package/docs/install.md

@@ -87,7 +87,7 @@ The MCP server comes in two modes:
 | Mode | File | Tools | Best For |
 |------|------|-------|----------|
 | **Compound** (default) | `src/server.py` | 32 | Most users — fast, clean, low context usage |
-| **Full** | `src/resolve_mcp_server.py` | 329 | Power users who want one tool per API method |
+| **Full** | `src/resolve_mcp_server.py` | 341 | Power users who want one tool per API method |
 
 The compound server's `timeline_item` tool includes dedicated actions for common workflows:
 
@@ -102,7 +102,7 @@ The compound server's `timeline_item` tool includes dedicated actions for common
 
 The installer uses the compound server by default. To use the full server:
 ```bash
-python src/server.py --full    # Launch full 329-tool server
+python src/server.py --full    # Launch full 341-tool server
 # Or point your MCP config directly at src/resolve_mcp_server.py
 ```
 

package/docs/reference/api-coverage.md

@@ -6,7 +6,7 @@ Complete Resolve scripting API coverage, live-test status, and method-by-method
 
 | Metric | Value |
 |--------|-------|
-| MCP Tools | **33** compound (default) / **329** granular |
+| MCP Tools | **33** compound (default) / **341** granular |
 | Kernel Actions | **136** guarded MCP workflow actions across 9 compound tools |
 | API Methods Covered | **336/336** (100%) |
 | Methods Live Tested | **331/336** (98.5%) |
@@ -17,7 +17,7 @@ Complete Resolve scripting API coverage, live-test status, and method-by-method
 
 ## API Coverage
 
-Every non-deprecated method in the DaVinci Resolve Scripting API is covered. The default compound server exposes **33 tools** that group related operations by action parameter, keeping LLM context windows lean. The full granular server provides **329 individual tools** for power users. Both modes cover all 13 API object classes. MCP-level kernel actions are tracked separately in [Kernel Action Coverage](../kernels/README.md).
+Every non-deprecated method in the DaVinci Resolve Scripting API is covered. The default compound server exposes **33 tools** that group related operations by action parameter, keeping LLM context windows lean. The full granular server provides **341 individual tools** for power users. Both modes cover all 13 API object classes. MCP-level kernel actions are tracked separately in [Kernel Action Coverage](../kernels/README.md).
 
 The 33rd compound tool is `timeline_versioning` (C6) — an MCP-level workflow
 tool, not a wrapper around a Resolve API method. It surfaces the

package/docs/reference/resolve_scripting_api.txt

@@ -1,4 +1,4 @@
-Last Updated: 7 Oct 2025
+Last Updated: 5 May 2026
 -------------------------
 In this package, you will find a brief introduction to the Scripting API for DaVinci Resolve Studio. Apart from this README.txt file, this package contains folders containing the basic import
 modules for scripting access (DaVinciResolve.py) and some representative examples.
@@ -105,6 +105,7 @@ Resolve
   GetKeyframeMode()                               --> keyframeMode       # Returns the currently set keyframe mode (int). Refer to section 'Keyframe Mode information' below for details.
   SetKeyframeMode(keyframeMode)                   --> Bool               # Returns True when 'keyframeMode'(enum) is successfully set. Refer to section 'Keyframe Mode information' below for details.
   GetFairlightPresets()                           --> [presetNames...].  # Returns a list of Fairlight presets by name
+  DisableBackgroundTasksForCurrentResolveSession()--> None               # Disables all background tasks for current Resolve session.
 
 ProjectManager
   ArchiveProject(projectName,
@@ -199,6 +200,7 @@ Project
   AddColorGroup(groupName)                        --> ColorGroup         # Creates a new ColorGroup. groupName must be a unique string.
   DeleteColorGroup(colorGroup)                    --> Bool               # Deletes the given color group and sets clips to ungrouped.
   ApplyFairlightPresetToCurrentTimeline(name)     --> Bool               # Apply Fairlight Preset of given name to the current timeline, returns True if successful, False otherwise.
+  GenerateSpeech({speechGenerationSettings}, timecode) --> MediaPoolItem # Generates an audio MediaPoolItem based on the given speechGenerationSettings and adds it to the timeline at the stated timecode if "AddToTimeline" is True. Returns the newly generated MediaPoolItem.
 
 MediaStorage
   GetMountedVolumeList()                          --> [paths...]         # Returns list of folder paths corresponding to mounted volumes displayed in Resolve’s Media Storage.
@@ -263,8 +265,13 @@ Folder
   GetIsFolderStale()                              --> bool               # Returns true if folder is stale in collaboration mode, false otherwise
   GetUniqueId()                                   --> string             # Returns a unique ID for the media pool folder
   Export(filePath)                                --> bool               # Returns true if export of DRB folder to filePath is successful, false otherwise
-  TranscribeAudio()                               --> Bool               # Transcribes audio of the MediaPoolItems within the folder and nested folders. Returns True if successful; False otherwise
+  TranscribeAudio(useSpeakerDetection=None)       --> Bool               # Transcribes audio of the MediaPoolItems within the folder and nested folders. Returns True if successful; False otherwise
   ClearTranscription()                            --> Bool               # Clears audio transcription of the MediaPoolItems within the folder and nested folders. Returns True if successful; False otherwise.
+  PerformAudioClassification()                    --> Bool               # Analyzes and classifies the audio of the MediaPoolItems within the folder and nested folders into categories and subcategories.
+  ClearAudioClassification()                      --> Bool               # Clears audio classification of the MediaPoolItems within the folder and nested folders.
+  RemoveMotionBlur({deblurOption})                --> [[MediaPoolItem, MediaPoolItem]...]   # Applies motion deblur on MediaPoolItems in the folder. Returns a list of pairs mapping original to newly created MediaPoolItems.
+  AnalyzeForIntellisearch(identifyFaces, isBetterMode) --> Bool          # Performs Intellisearch analysis on all MediaPoolItems in the folder. identifyFaces specifies whether to identify faces; isBetterMode specifies whether to use Better mode. Returns True if required packages are installed and analysis is successful.
+  AnalyzeForSlate(markerColor)                    --> Bool               # Performs Slate analysis on all MediaPoolItems in the folder using the current settings and specified markerColor. Returns True if required packages are installed and analysis is successful.
 
 MediaPoolItem
   GetName()                                       --> string             # Returns the clip name.
@@ -304,8 +311,13 @@ MediaPoolItem
   ReplaceClip(filePath)                           --> Bool               # Replaces the underlying asset and metadata of MediaPoolItem with the specified absolute clip path.
   ReplaceClipPreserveSubClip(filePath)            --> Bool               # Replaces the underlying asset and metadata of a video or audio clip with the specified absolute clip path, preserving original sub clip extents.
   GetUniqueId()                                   --> string             # Returns a unique ID for the media pool item
-  TranscribeAudio()                               --> Bool               # Transcribes audio of the MediaPoolItem. Returns True if successful; False otherwise
+  TranscribeAudio(useSpeakerDetection=None)       --> Bool               # Transcribes audio of the MediaPoolItem. Returns True if successful; False otherwise
   ClearTranscription()                            --> Bool               # Clears audio transcription of the MediaPoolItem. Returns True if successful; False otherwise.
+  PerformAudioClassification()                    --> Bool               # Analyzes and classifies the audio of a MediaPoolItem into categories and subcategories.
+  ClearAudioClassification()                      --> Bool               # Clears audio classification of the MediaPoolItem.
+  RemoveMotionBlur({deblurOption})                --> MediaPoolItem      # Applies motion deblur on the MediaPoolItem. Returns the newly created MediaPoolItem.
+  AnalyzeForIntellisearch(identifyFaces, isBetterMode) --> Bool          # Performs Intellisearch analysis on the MediaPoolItem. identifyFaces specifies whether to identify faces; isBetterMode specifies whether to use Better mode. Returns True if required packages are installed and analysis is successful.
+  AnalyzeForSlate(markerColor)                    --> Bool               # Performs Slate analysis on the MediaPoolItem using the current settings and specified markerColor. Returns True if required packages are installed and analysis is successful.
   GetAudioMapping()                               --> json formatted string # Returns a string with MediaPoolItem's audio mapping information. Check 'Audio Mapping' section below for more information.
   GetMarkInOut()                                  --> {mark}             # Returns dict of in/out marks set (keys omitted if not set), example:
                                                                          # {'video': {'in': 0, 'out': 134}, 'audio': {'in': 0, 'out': 134}}

package/install.py

@@ -35,7 +35,7 @@ from src.utils.update_check import (
 
 # ─── Version ──────────────────────────────────────────────────────────────────
 
-VERSION = "2.28.1"
+VERSION = "2.30.0"
 # Only hard floor: mcp[cli] requires Python 3.10+. There is no upper bound —
 # Resolve's scripting bridge loads into newer interpreters on recent builds
 # (Python 3.14 verified against Resolve Studio 20.3.2). Older Resolve builds

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "davinci-resolve-mcp",
-  "version": "2.28.1",
+  "version": "2.30.0",
   "description": "NPM bootstrapper for the DaVinci Resolve MCP Server.",
   "license": "MIT",
   "author": "Samuel Gursky <samgursky@gmail.com>",

package/src/analysis_dashboard.py

@@ -4370,6 +4370,24 @@ HTML = r"""<!doctype html>
           </div>
         </div>
 
+        <div class="caps-section">
+          <div class="caps-section-head">
+            <div class="caps-section-title">Resolve 21 AI ops</div>
+            <div class="caps-section-hint">Local Resolve AI operations (audio classification, IntelliSearch, slate, motion-deblur, speech). These run on Resolve's GPU/AI engine and do <strong>not</strong> consume the Claude analysis token budget above — tracked here for invocations, time, and files created.</div>
+          </div>
+          <div id="resolveAiOpsBlock" class="caps-usage-block">
+            <div id="resolveAiOpsSummary" class="caps-section-hint">loading…</div>
+            <table id="resolveAiOpsTable" class="resolve-ai-ops-table" style="display:none; width:100%; border-collapse:collapse; margin-top:8px; font-size:12px;">
+              <thead><tr style="text-align:left; opacity:0.7;">
+                <th style="padding:4px 6px;">Op</th><th style="padding:4px 6px;">Runs</th>
+                <th style="padding:4px 6px;">OK</th><th style="padding:4px 6px;">Time</th>
+                <th style="padding:4px 6px;">Files</th><th style="padding:4px 6px;">Created</th>
+              </tr></thead>
+              <tbody id="resolveAiOpsRows"></tbody>
+            </table>
+          </div>
+        </div>
+
         <div class="caps-section">
           <div class="caps-section-head">
             <div class="caps-section-title">Safety</div>
@@ -7040,6 +7058,59 @@ HTML = r"""<!doctype html>
         </svg>`;
     }
 
+    // ─── Resolve 21 AI ops ledger (read-only) ───────────────────────
+    function fmtMs(ms) {
+      ms = ms || 0;
+      if (ms < 1000) return ms + 'ms';
+      const s = ms / 1000;
+      return s < 60 ? s.toFixed(1) + 's' : (s / 60).toFixed(1) + 'm';
+    }
+    function fmtBytes(n) {
+      n = n || 0;
+      if (!n) return '—';
+      const u = ['B', 'KB', 'MB', 'GB', 'TB'];
+      let i = 0; let v = n;
+      while (v >= 1024 && i < u.length - 1) { v /= 1024; i++; }
+      return v.toFixed(v < 10 && i > 0 ? 1 : 0) + ' ' + u[i];
+    }
+    async function refreshResolveAiOps() {
+      const summaryEl = $('resolveAiOpsSummary');
+      const tableEl = $('resolveAiOpsTable');
+      const rowsEl = $('resolveAiOpsRows');
+      if (!summaryEl || !tableEl || !rowsEl) return;
+      const data = await api('/api/resolve_ai_usage').catch(() => ({ success: false }));
+      if (!data || !data.success) {
+        summaryEl.textContent = 'ledger unavailable';
+        tableEl.style.display = 'none';
+        return;
+      }
+      const totals = (data.summary && data.summary.totals) || {};
+      const byOp = (data.summary && data.summary.by_op) || {};
+      const ops = Object.keys(byOp).sort();
+      if (!ops.length) {
+        summaryEl.textContent = 'No Resolve AI ops recorded yet for this project.';
+        tableEl.style.display = 'none';
+        return;
+      }
+      summaryEl.innerHTML = `<strong>${totals.runs || 0}</strong> runs · `
+        + `<strong>${totals.successes || 0}</strong> ok / ${totals.failures || 0} failed · `
+        + `${fmtMs(totals.wall_clock_ms)} total · `
+        + `<strong>${totals.files_created || 0}</strong> files (${fmtBytes(totals.bytes_created)}) created`;
+      rowsEl.innerHTML = ops.map(op => {
+        const b = byOp[op];
+        const isRender = b.op_class === 'render';
+        return `<tr style="border-top:1px solid rgba(255,255,255,0.06);">
+          <td style="padding:4px 6px;">${escapeHtml(op)}${isRender ? ' <span style="opacity:0.6;">(media)</span>' : ''}</td>
+          <td style="padding:4px 6px;">${b.runs}</td>
+          <td style="padding:4px 6px;">${b.successes}</td>
+          <td style="padding:4px 6px;">${fmtMs(b.wall_clock_ms)}</td>
+          <td style="padding:4px 6px;">${b.files_created || '—'}</td>
+          <td style="padding:4px 6px;">${b.bytes_created ? fmtBytes(b.bytes_created) : '—'}</td>
+        </tr>`;
+      }).join('');
+      tableEl.style.display = '';
+    }
+
     // ─── Caps inspector + refusals + reset ──────────────────────────
     async function inspectCapsFromUI() {
       const clipId = ($('capsInspectClipId')?.value || '').trim();
@@ -9916,6 +9987,7 @@ HTML = r"""<!doctype html>
     refreshCapsWidget().catch(() => {});
     refreshCapsHistory().catch(() => {});
     refreshCapsRefusals().catch(() => {});
+    refreshResolveAiOps().catch(() => {});
 
     // Caps inspector + reset
     $('capsInspectBtn')?.addEventListener('click', () => inspectCapsFromUI().catch(alertError));
@@ -10654,6 +10726,45 @@ def _current_resolve_project_id() -> Tuple[Optional[str], Optional[str]]:
 
 
 @_serialize_resolve
+def _resolve_ai_features(resolve: Any) -> Dict[str, Any]:
+    """Report which Resolve 21.0 AI scripting methods are available on the
+    connected build, plus the Extra each AI-gated method requires. Presence is
+    detected via getattr (no Resolve round-trips beyond fetching the handles),
+    so this stays cheap enough for the boot handshake.
+    """
+    def has(obj: Any, name: str) -> bool:
+        return bool(obj) and callable(getattr(obj, name, None))
+
+    project = folder = None
+    try:
+        pm = resolve.GetProjectManager()
+        project = pm.GetCurrentProject() if pm else None
+        mp = project.GetMediaPool() if project else None
+        folder = mp.GetRootFolder() if mp else None
+    except Exception:
+        pass
+
+    features = {
+        "disable_background_tasks": has(resolve, "DisableBackgroundTasksForCurrentResolveSession"),
+        "generate_speech": has(project, "GenerateSpeech"),
+        "perform_audio_classification": has(folder, "PerformAudioClassification"),
+        "clear_audio_classification": has(folder, "ClearAudioClassification"),
+        "analyze_for_intellisearch": has(folder, "AnalyzeForIntellisearch"),
+        "analyze_for_slate": has(folder, "AnalyzeForSlate"),
+        "remove_motion_blur": has(folder, "RemoveMotionBlur"),
+    }
+    return {
+        "features": features,
+        "available_count": sum(1 for v in features.values() if v),
+        # Methods that additionally need an Extras download to actually run.
+        "requires_extra": {
+            "analyze_for_intellisearch": "AI IntelliSearch",
+            "analyze_for_slate": "AI Slate ID",
+            "generate_speech": "AI Speech Generator",
+        },
+    }
+
+
 def _resolve_identity() -> Dict[str, Any]:
     resolve, error = _connect_resolve_read_only()
     if not resolve:
@@ -10668,6 +10779,7 @@ def _resolve_identity() -> Dict[str, Any]:
         "version_string": str(version_string) if version_string else None,
         "version": list(version_tuple) if isinstance(version_tuple, (list, tuple)) else None,
         "page": str(page) if page else None,
+        "ai_features": _resolve_ai_features(resolve),
     }
 
 
@@ -13573,6 +13685,20 @@ class Handler(BaseHTTPRequestHandler):
             except Exception as exc:
                 self._json({"success": False, "error": f"{type(exc).__name__}: {exc}"})
             return
+        if path == "/api/resolve_ai_usage":
+            # Ledger of Resolve-local 21.0 AI ops (read straight from this
+            # project's brain DB — no Resolve round-trip needed).
+            try:
+                from src.utils import resolve_ai_ledger as _ledger
+                root = self.state.project_root
+                self._json({
+                    "success": True,
+                    "summary": _ledger.get_summary(project_root=root),
+                    "recent": _ledger.get_usage(project_root=root, limit=50),
+                })
+            except Exception as exc:
+                self._json({"success": False, "error": f"{type(exc).__name__}: {exc}"})
+            return
         if path.startswith("/api/timeline_thumbnail/"):
             rel = unquote(path[len("/api/timeline_thumbnail/"):])
             # Path is <slug>/<vNN.png>; constrain it to live under _soul/timeline_versions

package/src/granular/common.py

@@ -80,7 +80,7 @@ if not logging.getLogger().handlers:
         handlers=[logging.StreamHandler()],
     )
 
-VERSION = "2.28.1"
+VERSION = "2.30.0"
 logger = logging.getLogger("davinci-resolve-mcp")
 logger.info(f"Starting DaVinci Resolve MCP Server v{VERSION}")
 logger.info(f"Detected platform: {get_platform()}")

package/src/granular/folder.py

@@ -294,3 +294,127 @@ def folder_clear_transcription(folder_path: str = "") -> Dict[str, Any]:
         folder = mp.GetCurrentFolder()
     result = folder.ClearTranscription()
     return {"success": bool(result)}
+
+
+def _resolve_folder(mp, folder_path):
+    """Return (folder, error). Empty path -> current folder."""
+    if folder_path:
+        folder = _navigate_to_folder(mp, folder_path)
+        if not folder:
+            return None, {"error": f"Folder '{folder_path}' not found"}
+        return folder, None
+    return mp.GetCurrentFolder(), None
+
+
+_MARKER_COLORS = [
+    "Blue", "Cyan", "Green", "Yellow", "Red", "Pink", "Purple", "Fuchsia",
+    "Rose", "Lavender", "Sky", "Mint", "Lemon", "Sand", "Cocoa", "Cream",
+]
+
+
+@mcp.tool()
+def folder_perform_audio_classification(folder_path: str = "") -> Dict[str, Any]:
+    """Classify audio of all clips in a Media Pool folder into categories (Resolve 21+).
+
+    Args:
+        folder_path: Path from root. Empty for current folder.
+    """
+    _, mp, err = _get_mp()
+    if err:
+        return err
+    folder, err = _resolve_folder(mp, folder_path)
+    if err:
+        return err
+    if not hasattr(folder, "PerformAudioClassification"):
+        return {"error": "PerformAudioClassification requires DaVinci Resolve 21+"}
+    return {"success": bool(folder.PerformAudioClassification())}
+
+
+@mcp.tool()
+def folder_clear_audio_classification(folder_path: str = "") -> Dict[str, Any]:
+    """Clear audio classification for all clips in a Media Pool folder (Resolve 21+).
+
+    Args:
+        folder_path: Path from root. Empty for current folder.
+    """
+    _, mp, err = _get_mp()
+    if err:
+        return err
+    folder, err = _resolve_folder(mp, folder_path)
+    if err:
+        return err
+    if not hasattr(folder, "ClearAudioClassification"):
+        return {"error": "ClearAudioClassification requires DaVinci Resolve 21+"}
+    return {"success": bool(folder.ClearAudioClassification())}
+
+
+@mcp.tool()
+def folder_analyze_for_intellisearch(folder_path: str = "", identify_faces: bool = False, is_better_mode: bool = False) -> Dict[str, Any]:
+    """Run IntelliSearch analysis on all clips in a folder (Resolve 21+, requires AI IntelliSearch Extra).
+
+    Args:
+        folder_path: Path from root. Empty for current folder.
+        identify_faces: Whether to identify faces.
+        is_better_mode: Use Better mode (vs Faster).
+    """
+    _, mp, err = _get_mp()
+    if err:
+        return err
+    folder, err = _resolve_folder(mp, folder_path)
+    if err:
+        return err
+    if not hasattr(folder, "AnalyzeForIntellisearch"):
+        return {"error": "AnalyzeForIntellisearch requires DaVinci Resolve 21+"}
+    return {"success": bool(folder.AnalyzeForIntellisearch(bool(identify_faces), bool(is_better_mode)))}
+
+
+@mcp.tool()
+def folder_analyze_for_slate(folder_path: str = "", marker_color: str = "Blue") -> Dict[str, Any]:
+    """Run Slate analysis on all clips in a folder (Resolve 21+, requires AI Slate ID Extra).
+
+    Args:
+        folder_path: Path from root. Empty for current folder.
+        marker_color: Marker color for detected slates (Blue, Cyan, Green, Yellow, Red, Pink,
+            Purple, Fuchsia, Rose, Lavender, Sky, Mint, Lemon, Sand, Cocoa, Cream).
+    """
+    _, mp, err = _get_mp()
+    if err:
+        return err
+    folder, err = _resolve_folder(mp, folder_path)
+    if err:
+        return err
+    if not hasattr(folder, "AnalyzeForSlate"):
+        return {"error": "AnalyzeForSlate requires DaVinci Resolve 21+"}
+    if marker_color not in _MARKER_COLORS:
+        return {"error": f"Invalid marker_color '{marker_color}'. Valid: {', '.join(_MARKER_COLORS)}"}
+    return {"success": bool(folder.AnalyzeForSlate(marker_color))}
+
+
+@mcp.tool()
+def folder_remove_motion_blur(folder_path: str = "", deblur_option: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
+    """Render motion-deblurred copies of all clips in a folder (Resolve 21+).
+
+    Creates NEW media files; source media is not modified.
+
+    Args:
+        folder_path: Path from root. Empty for current folder.
+        deblur_option: Settings dict (FileName, Format, Codec, EncodingProfile,
+            UseExtremeMode, UseMarkInMarkOut, RenderAtSourceRes, UseMoreGpuMemory).
+    """
+    _, mp, err = _get_mp()
+    if err:
+        return err
+    folder, err = _resolve_folder(mp, folder_path)
+    if err:
+        return err
+    if not hasattr(folder, "RemoveMotionBlur"):
+        return {"error": "RemoveMotionBlur requires DaVinci Resolve 21+"}
+    result = folder.RemoveMotionBlur(deblur_option or {})
+    created = []
+    for pair in (result or []):
+        try:
+            orig, new = pair
+            created.append({"original": orig.GetName(), "new": new.GetName(), "new_id": new.GetUniqueId()})
+        except Exception:
+            continue
+    return {"success": bool(result), "created": created}