MCP for Adobe Premiere Pro

Give compatible AI assistants structured control over supported Adobe Premiere Pro workflows.

327 core tools across 37 modules, 4 resources, and 11 guided workflows. A connected UXP host adds 61 capability-gated tools.

---

What is this?

An MCP (Model Context Protocol) server that lets AI assistants like Claude, Windsurf, Cursor, GitHub Copilot, or any MCP-compatible client directly control Adobe Premiere Pro — importing media, editing timelines, applying effects, managing keyframes, exporting, and more.

"Add the B-roll clips to V2, apply a cross dissolve between each, color correct them to match the A-roll, and export a 1080p ProRes."

The AI handles the entire workflow through 327 core tools spanning the supported ExtendScript, QE DOM, local media and interchange analysis, revisioned project-context retrieval, safe edit-planning, project-intake preview, review handoff, and connection-verification surfaces. A compatible, authenticated UXP panel adds 56 documented, capability-gated tools without replacing the production CEP bridge.

Latest release: 1.14.6

• Guarded UXP editing: compatible hosts can use verified sequence ranges, playhead, marker, transition, caption, silence-cut, and split-edit workflows.
• Review-first evidence: local delivery checks, sampled media analysis, and editorial context packs remain bounded and avoid unapproved provider writes.
• Narrowed host behavior: unsupported sequence pixel-aspect ratios and partial UXP transition writes fail closed; other mutations retain their documented verified or explicitly committed_unverified outcome.
• Explicit boundary: the hosted endpoint remains an operator-managed MCP service; unauthenticated callers are rejected and it does not pair users to local Premiere processes.

See the v1.14.6 release notes for complete details. Live installation in Premiere Pro still requires host verification.

Current MCP protocol support

The server uses the stable TypeScript SDK v2 and serves the 2026-07-28 stateless protocol over HTTP and stdio, while retaining legacy MCP compatibility through 2025-11-25. Modern clients receive discovery, validated routing headers, cache hints, subscription-stream support, and the formal Premiere extension capability. See the complete MCP capability and boundary report.

---

For editors evaluating an AI workflow

Before an assistant changes an active project, use the Premiere Pro AI workflow checklist to define the target and no-change boundaries, verify the local connection, request a bounded plan, and inspect the returned result. It is a practical starting point for assistant editors and post leads testing a repeatable workflow on a duplicate project or small test sequence.

For product context, see the Adobe Premiere AI Assistant and MCP comparison and the Claude Desktop setup guide.

If you are deciding between a single local project, an Adobe Production on shared storage, or a remote Team Project, use the Premiere Pro collaboration workflow guide before you evaluate an MCP path. It links the relevant Adobe guidance, makes no project inspection request, and ends with the same read-only connection check.

For a concrete first Project Intake preview, choose one of the three schema-checked, no-sensitive-data starter templates. They are evaluation samples only: a human policy owner must review and replace their bins, media rules, and organization rules before a facility uses one.

---

Quick Start

Easiest supported path: Claude Desktop

1. Download the current Claude Desktop bundle (.mcpb).
2. In Claude Desktop, open Settings > Extensions > Advanced settings > Install Extension, select the downloaded bundle, and restart Claude Desktop.
3. Download the separate signed Premiere connector (.zxp). Open it with your trusted ZXP installer. If your computer has no ZXP installer, use the npm connector installer in Advanced setup below.
4. Restart Premiere, open a project, then open Window > Extensions > MCP for Adobe Premiere Pro.
5. In Claude, enter: Safely check my Premiere connection with verify_premiere_connection. Make no changes.

The Claude bundle contains the local MCP server, so this route does not require Node.js. The Premiere connector is a separate required install. The first prompt is read-only and reports whether the server is installed, configured, connected, and live-verified.

First proof, before the first edit

This is an illustrated workflow, not a Premiere panel screenshot or licensed-host proof.

1. Open a copied test project and an active sequence in Premiere.
2. Open Window > Extensions > MCP for Adobe Premiere Pro. “Running” means the local panel bridge is available; it does not show that an edit completed.
3. Run premiere-pro-mcp --doctor to check only local package/configuration readiness.
4. Ask the AI client: Run verify_premiere_connection. Make no changes. The returned check is read-only and avoids project names, paths, and media details.

If a bridge, project, or active sequence is missing, fix that setup state before allowing a mutation. For a concise, translatable version of this path, see quick starts in English, Spanish, and Japanese. The translations are machine-assisted drafts and retain command names in English.

Other AI assistants

Cursor, VS Code/Copilot, Windsurf, and other MCP clients do not currently have a project-provided one-click installer. Use their MCP settings with the advanced npm route below. Keep the assistant, server, connector, and Premiere on the same computer.

Advanced setup: npm or source

Before you begin

• Node.js 20.19 or newer on Windows or macOS.
• Adobe Premiere Pro 2020–2026. Keep Premiere, the CEP bridge, and your MCP client on the same computer for the recommended local setup.
• Optional: ffmpeg on PATH for detect_silence (brew install ffmpeg on macOS or winget install Gyan.FFmpeg on Windows). The production Docker image already includes it.

1. Install

Option A — npm:

npm install -g premiere-pro-mcp

Option B — Clone from source:

git clone https://github.com/leancoderkavy/premiere-pro-mcp.git
cd premiere-pro-mcp
npm install
npm run build

2. Install the CEP plugin

If installed via npm:

premiere-pro-mcp --install-cep

If cloned from source:

npm run install-cep

This installs the plugin into Premiere Pro's per-user extensions folder and enables debug mode.

3. Check the setup

premiere-pro-mcp --doctor

Then ask your MCP client to run verify_premiere_connection. The check is read-only.

Update an existing installation

New releases update the local server and Premiere connector; a deployment of the hosted MCP service does not replace software on your computer. Fully quit Premiere before updating the connector.

Installed globally from npm:

premiere-pro-mcp --check-update
premiere-pro-mcp --update

--update only changes a global npm installation. It installs the published latest package, refreshes the bundled CEP connector, and leaves your MCP client configuration and projects untouched. Restart Premiere and your MCP client afterward, then run verify_premiere_connection before editing.

Installed from a Git clone:

npm run check-update:source
npm run update:source

The source updater refuses a checkout with uncommitted files or local commits, fast-forwards only to its configured upstream, runs npm ci and the production build, then refreshes the CEP connector. This avoids silently overwriting local code. If you installed the Claude Desktop .mcpb bundle, download and install the newer bundle from the GitHub release instead; Claude controls extension updates.

Remove the CEP connector

Fully quit Premiere, then remove only this connector:

premiere-pro-mcp --uninstall-cep

The uninstaller intentionally leaves Adobe's shared PlayerDebugMode setting in place so it does not disrupt other CEP extensions. Remove the MCP server from your AI client's configuration and uninstall the npm package separately if you no longer use it. On macOS, --uninstall-cep removes the per-user npm/source install; the signed system-wide .pkg route has a separate privileged removal command in distribution readiness.

---

Publishing to npm

The easiest repeatable path is the token-free GitHub Actions workflow:

1. In the npm package settings, configure GitHub Actions as the trusted publisher for leancoderkavy/premiere-pro-mcp and workflow file npm-publish.yml.
2. Allow the npm publish action.
3. Open Actions -> Publish npm -> Run workflow and keep the default latest tag.

The workflow installs dependencies, builds, runs tests, verifies the packed files, refuses to republish an existing version, then publishes through short-lived OIDC credentials with automatic provenance. No npm token or recurring OTP is required.

For local publishing, use the guided helper:

npm run publish:npm

Useful local variants:

npm run publish:npm:dry-run
NPM_OTP=123456 npm run publish:npm
NPM_TOKEN=npm_xxx npm run publish:npm

Manual installation (macOS)

mkdir -p ~/Library/Application\ Support/Adobe/CEP/extensions
ln -s "$(pwd)/cep-plugin" ~/Library/Application\ Support/Adobe/CEP/extensions/MCPBridgeCEP

# Enable unsigned extensions (CSXS 9–14)
for v in 9 10 11 12 13 14; do
  defaults write com.adobe.CSXS.$v PlayerDebugMode 1
done

Manual installation (Windows)

1. Copy the cep-plugin folder to %APPDATA%\Adobe\CEP\extensions\MCPBridgeCEP
2. Open Registry Editor and set these String (REG_SZ) values to 1 (not DWORD):
   • HKEY_CURRENT_USER\Software\Adobe\CSXS.12\PlayerDebugMode
   • (repeat for CSXS.9 through CSXS.14)

3. Configure your MCP client

If you installed from npm, configure the client to run the global command:

{
  "mcpServers": {
    "premiere-pro": {
      "command": "premiere-pro-mcp"
    }
  }
}

If you cloned the repository instead, use the source-build configuration shown below for your client.

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "premiere-pro": {
      "command": "node",
      "args": ["/absolute/path/to/premiere-pro-mcp/dist/index.js"]
    }
  }
}

Windsurf / Cascade

Add to your MCP server configuration:

{
  "premiere-pro": {
    "command": "node",
    "args": ["/absolute/path/to/premiere-pro-mcp/dist/index.js"]
  }
}

Cursor

Add to .cursor/mcp.json in your project or global config:

{
  "mcpServers": {
    "premiere-pro": {
      "command": "node",
      "args": ["/absolute/path/to/premiere-pro-mcp/dist/index.js"]
    }
  }
}

GitHub Copilot (VS Code)

Add to your VS Code MCP server configuration:

{
  "mcpServers": {
    "premiere-pro": {
      "command": "node",
      "args": ["/absolute/path/to/premiere-pro-mcp/dist/index.js"]
    }
  }
}

4. Verify the bridge in Premiere Pro

1. Open (or restart) Premiere Pro
2. The bridge starts automatically using the default temp directory (or its previously saved setting)
3. Optionally go to Window > Extensions > MCP for Adobe Premiere Pro to confirm the green "Running" status or change the Temp Directory to match your MCP client config
4. Ask your AI assistant to run get_capabilities, then ping, with Premiere open.
5. For a safe first request, ask: "What is my current Premiere Pro project and active sequence? Do not make changes."

The default bridge directory is derived from the operating system on both sides, so most local setups should not set PREMIERE_TEMP_DIR. On macOS, the server resolves the per-user system temporary directory even when a GUI-launched client strips TMPDIR, keeping it aligned with Premiere's CEP panel. If you override it, use the same absolute path in the MCP server and CEP panel; Windows and macOS paths are not interchangeable.

Codex plugin

This repository includes an installable Codex plugin that bundles the local MCP server with a safety-oriented Premiere editing skill.

From a clone of this repository:

codex plugin marketplace add .
codex plugin add premiere-pro@premiere-pro-mcp
npx -y premiere-pro-mcp@1.14.6 --install-cep

Restart Premiere Pro and start a new Codex session after installation. The plugin launches premiere-pro-mcp@1.14.6 through npx; the separate CEP installation is required because the MCP server communicates with the running Premiere host through the local bridge.

The plugin source lives in plugins/premiere-pro, and the repository marketplace manifest lives in .agents/plugins/marketplace.json.

Claude

For Claude Code, add this repository as a marketplace and install the plugin:

/plugin marketplace add leancoderkavy/premiere-pro-mcp
/plugin install premiere-pro@premiere-pro-mcp

Then install the Premiere bridge and start a new Claude Code session:

npx -y premiere-pro-mcp@1.14.6 --install-cep

The Claude Code package lives in claude-plugins/premiere-pro, with its marketplace at .claude-plugin/marketplace.json.

Claude Desktop uses the self-contained MCP Bundle (.mcpb) format. Build and validate the current bundle with:

npm run build:claude

Install the resulting file from artifacts/ through Settings > Extensions > Advanced settings > Install Extension. The Premiere CEP bridge must still be installed separately.

Windows and macOS capability coverage

Surface	Windows	macOS	Verification boundary
CEP production bridge	Premiere Pro 2020–2026	Premiere Pro 2020–2026	Run get_capabilities, then ping with Premiere open
UXP preview bridge	Premiere Pro 25.6+	Premiere Pro 25.6+	Live loopback WebSocket and host API verification required
npm CEP installer	Copies plugin and verifies REG_SZ debug keys	Copies plugin and verifies the installed manifest/debug settings	Restart Premiere after installation
CI build and unit tests	Node 20, 22, and 24	Node 20, 22, and 24	GitHub-hosted OS runners; no Adobe host is available in CI

get_capabilities reports the current operating system, temp directory, CEP/UXP coverage, enabled authority profile, and any live-host verification still required. It also includes the full tools catalog generated from the tools registered by the server, including tools disabled by the active profile. Every entry identifies:

• the execution backend (local, CEP/ExtendScript, QE, or orchestrator);
• static support status (supported, limited, experimental, or unsupported);
• the minimum Premiere version known to the server;
• the required authority and whether the current profile enables it;
• the verification boundary and whether a live Premiere host is required; and
• relevant operational notes.

QE-backed tools are reported as experimental because QE is undocumented and can vary between Premiere builds. Authority availability is reported separately from implementation support, so disabling edit, for example, does not incorrectly label editing tools as unsupported. Static metadata never claims that a Premiere operation succeeded; use ping and inspect each tool result for runtime evidence.

MCP tools/list is filtered to the active authority profile. The default inspect,edit,export,filesystem profile advertises 325 of the 327 registered tools and omits execute_extendscript and evaluate_expression, which require explicit unsafe-script authority. ping and get_capabilities remain visible under every profile so a restricted or misconfigured server can still explain its state. The call-time capability guard remains authoritative even if listing metadata is wrong.

Workflow-scoped discovery packs and structured outputs

By default, the full permitted catalog remains available. Set PREMIERE_MCP_TOOL_PACKS to essential, inspection, delivery, captions, or a comma-separated combination such as inspection,captions to reduce the tool discovery and registered session surface for a focused client. full is the explicit full-catalog mode and cannot be combined with another pack. ping and get_capabilities remain listed for diagnosis, and every registered call still passes through the same capability guard; a pack never grants authority.

Every listed tool now declares the same machine-readable result envelope through MCP outputSchema: ok, tool, plus data on success or error on failure. The tool-specific data shape remains versioned by the individual tool result, so clients can reliably distinguish transport success from a Premiere or local operation failure without parsing the text block.

inspect_sequence_review_report creates one read-only handoff report from Premiere timeline readback: sequence structure, primary-track gaps, disabled clips, muted tracks, marker timing, and offline-source evidence. It never returns media paths; marker comments are omitted unless explicitly requested. The report is not proof of rendered pixels, audio quality, caption accuracy, rights, or editorial approval.

The MCP handshake reads serverInfo.version from the installed package.json, so clients receive the package version that is actually running rather than a separately maintained literal.

Tools with mixed execution boundaries can provide explicit operational metadata at registration. This is used for local file verification, static feature-support reports, and hybrid local-plus-Premiere validation so the capability catalog does not infer a host dependency from naming alone.

Collaboration and AI feature boundaries

get_advanced_feature_support returns a machine-readable matrix for Productions, Team Projects, Frame.io, Media Intelligence, Generative Extend, Object Mask, caption translation, Speech-to-Text, Enhance Speech, Remix, editorial plans, Premiere AI Assistant, Generative Media, and a future local semantic index. Each entry includes an explicit access mode: direct, observable-only, artifact-import, external-provider, user-assisted, unavailable, or planned. Pass an optional Premiere version, intended backend, confirmed entitlements, and network state to evaluate prerequisites without conflating them with API availability. It distinguishes documented APIs from entitlements, network prerequisites, separate service APIs, and user-assisted operations without using menu automation or private APIs.

The report tool itself is local: it does not contact Premiere and is callable through the current MCP server. Each feature entry separately reports whether its operations are callable through the production CEP transport. Productions reports only static backend/version eligibility until a UXP host performs live capability negotiation.

• Productions exposes documented read-only state through UXP, but the production MCP transport is still CEP.
• Frame.io needs a separately authenticated Frame.io API integration; an account entitlement alone does not make it callable through Premiere's DOM.
• Transcript JSON import/export is documented in UXP. Starting Speech-to-Text is not.
• preview_transcript_edit_uxp and plan_transcript_rough_cut_uxp provide a revision-locked transcript-edit workflow. The planner maps selected transcript ranges to verified 1x placements in a duplicate sequence and emits descending split/remove instructions; it does not claim that Adobe exposes native transcript text deletion or perform an unverified destructive edit.
• The remaining AI operations are user-assisted or unsupported by documented public APIs. The tool explains what can be inspected after a user completes the operation and where artifact provenance cannot be established safely.
• The server never uses menu automation, private APIs, clip-name heuristics, or duration changes as proof that an AI operation occurred.

Reusable project context

For projects where repeatedly inspecting clips, transcripts, audio, and timeline placements is expensive, call manage_project_context with action: "capture". The local context engine indexes a bounded active-sequence snapshot, hashes native project/media paths before persistence, and returns independent source, timeline, and combined context revisions. Add transcript passages, shot descriptions, audio observations, or editor notes once with action: "enrich"; ordinary trims and moves update the timeline revision without discarding unchanged source analysis.

Use search_project_context to retrieve only evidence relevant to the current editing intent. create_context_edit_plan returns a non-mutating candidate scaffold and stale-state guards; create_editorial_plan adds reviewed organization, stringout, rough-cut, and caption-artifact routes without calling an LLM or changing Premiere. Exact identities must still be resolved and passed through the routed operation's preview/confirmation flow before any application. See the project context engine guide for storage controls, privacy boundaries, and invalidation behavior; see local-first AI editorial workflows for the complete review-and-route workflow.

Authenticated UXP connection

The MCP server can accept a local UXP panel connection and invoke the UXP commands that are currently implemented:

PREMIERE_UXP_TOKEN="replace-with-a-long-random-secret" premiere-pro-mcp

Enter the same token in the UXP panel. The listener binds only to 127.0.0.1:7777, authenticates the WebSocket upgrade, requires a versioned capability handshake, correlates concurrent requests, and fails pending work on timeout or disconnect. Set PREMIERE_UXP_PORT to use another loopback port.

When enabled, MCP discovery includes 61 capability-gated UXP additions. The first expansion covers effects, deterministic timeline selection, selection batches, scene detection, proxy/ingest, relink, metadata, color conformance, read-only Premiere/After Effects environment inspection, Source Monitor audition, storage, and least-privilege workspace access. The second adds Project-panel selection, marker CRUD, single-transaction undoable beat-grid marker application, bin organization, sequence settings, imports, typed effect parameters/keyframes, track-item transforms, atomic J/L split edits, SequenceEditor timeline edits, sequence lifecycle, and AME encoding. The third wave begins with a redacted event journal, conservative AME terminal receipts, explicit host-readiness gates, safe multi-project sessions, lease-based growing-media control, namespaced workflow checkpoints, bounded media-health maintenance, caption-aware track mute state, transactional source trim/framing, and guarded sequence-range updates documented in the third-wave workflow matrix. The bounded migration surface also includes a non-ripple selected-item lift plus native video-transition listing, target inspection, and guarded transactions; it does not claim direct empty-track create/delete or global redo support. A separate hybrid benchmark gate keeps native acceleration disabled until reproducible cross-platform evidence exists. See also the first stable workflow matrix and the next-ten workflow matrix. Commands are advertised only while the authenticated local UXP bridge is connected; the host capability handshake remains the authority for support in the running Premiere build. A failed UXP command is never silently retried through CEP because the first operation may have partially succeeded.

The panel now requests access to one operator-selected workspace instead of declaring full filesystem access. Choose the folder in the panel before invoking a path-based UXP workflow. Media, relink, preset, export, and Source Monitor file paths must remain inside it; the persistent capability token and native root path are never returned over MCP. Lexical containment alone cannot exclude symlink, junction, or reparse-point escapes, and Adobe's request-scoped UXP filesystem API does not document canonical-path resolution. Builds without a host-supplied canonical resolver therefore advertise path-based UXP commands as unsupported and fail closed at invocation; use the existing CEP fallback for those operations.

Native transcript editing starts with a read-only, revision-locked planning flow. Use get_clip_transcript_uxp to export the transcript Premiere generated for a source clip, select source-time ranges from that JSON, and pass its SHA-256 revision to preview_transcript_edit_uxp. The preview sorts and merges ranges and returns a confirmation token without changing the timeline. Premiere does not expose a documented operation that directly turns deleted transcript text into timeline cuts, so automatic application remains withheld until the source-to-sequence mapping and documented reconstruction path pass live-host validation. search_clip_transcript_uxp provides read-only discovery without substituting an external transcription engine.

Premiere 26.2-26.3 hosts also expose documented UXP workflows for revisioned project inspection, verified project saves, preset-based sequence creation, OTIO/FCP XML interchange, transcript-language discovery, Object Mask detection, Adobe Media Encoder control, track renaming, subclip creation, stable marker inspection, Source Monitor positioning, and clip transcript detection. Mutations accept optional idempotency keys and return explicit verification outcomes. See the Adobe UXP 26.3 coverage matrix and the UXP capability foundation for the command matrix and live-host validation boundary.

The Premiere surface registry separately tracks the Premiere DOM, general UXP JavaScript, HTML/CSS, Spectrum, plugin guides, UXP Hybrid C++, the standalone Premiere C++ PrSDK, CEP/ExtendScript, the CEP platform, QE, and pinned competitor sources. The exhaustive general UXP JavaScript inventory is generated from Adobe's pinned declarations, while the exhaustive Premiere documentation inventory tracks every page in Adobe's live sitemap. This keeps declaration and documentation inventory distinct from implementation and licensed-host coverage.

The stable workflow expansion adds native component-chain effects, deterministic timeline selection, compound selection batches, scene-edit detection, proxy/ingest control, guarded offline relink, transactional project/XMP metadata, color and footage-conformance preflight, full Source Monitor audition, and project/Production storage checks. See the stable UXP workflow matrix for exact argument, undo, confirmation, and live-host boundaries.

---

Architecture

Local (stdio):

┌───────────────┐   stdio (MCP)    ┌──────────────┐   File-based IPC   ┌───────────────┐
│  AI Client    │ ◄──────────────► │  MCP Server  │ ◄────────────────► │  CEP Plugin   │
│  (Claude,     │                  │  (Node.js /  │   .jsx commands    │  (runs inside │
│   Windsurf,   │                  │  TypeScript) │   .json responses  │  Premiere)    │
│   Cursor,     │                  └──────────────┘                    └──────┬────────┘
│   Copilot)    │                                                             │
└───────────────┘                                                             │ evalScript()
                                                                              ▼
                                                                       ┌───────────────┐
                                                                       │  Premiere Pro │
                                                                       │  ExtendScript │
                                                                       │  + QE DOM     │
                                                                       └───────────────┘

Remote (HTTP/SSE — Fly.io):

┌───────────────┐  HTTP+SSE (MCP)  ┌─────────────────────┐   File-based IPC   ┌──────────────┐
│  AI Client    │ ◄──────────────► │  MCP Server         │ ◄────────────────► │  CEP Plugin  │
│  (any MCP     │                  │  premiere-pro-mcp   │   .jsx / .json     │  (Premiere)  │
│   client)     │                  │  .fly.dev           │   shared volume    └──────────────┘
└───────────────┘                  └─────────────────────┘

1. AI client invokes an MCP tool (e.g., add_to_timeline)
2. MCP server generates ES3-compatible ExtendScript with helper functions prepended
3. Script is written to a .jsx command file in a shared temp directory
4. CEP plugin polls for command files, executes via CSInterface.evalScript()
5. Result JSON is written to a response file and returned to the AI

The file-based IPC bridge is simple, reliable, and works across macOS and Windows without network sockets.

---

Tools (327 core total; 325 under the default profile; 386 with a connected UXP bridge)

The complete supported-actions catalog lists every registered core tool, the two tools restricted behind explicit unsafe-script authority, and all 61 authenticated UXP additions with their current action or mode values. It is generated from the same MCP registration surface returned to clients; the tables below are a shorter workflow-oriented overview.

Discovery & Inspection (10 + 10)

Tool	Description
get_project_info	Current project name, path, sequences, items
get_active_sequence	Detailed active sequence with all clips
list_project_items	All items in the project panel
get_full_project_overview	Comprehensive snapshot: bin tree, sequences, media types
get_full_sequence_info	Exhaustive sequence data: tracks, clips, effects, markers
get_full_clip_info	Everything about a clip: effects, keyframes, metadata
get_timeline_summary	Human-readable overview: duration, coverage %, effects
search_project_items	Filter by name, extension, offline status, color label
get_premiere_state	Full snapshot: project, sequence, playhead, selection
inspect_dom_object	Explore any Premiere Pro DOM object interactively
get_advanced_feature_support	Collaboration/AI API support, prerequisites, entitlements, and user-assisted boundaries
create_editorial_plan	Create a review-only local editorial plan from captured project context
preview_editorial_plan	Revalidate a local editorial plan and return a review receipt without changing Premiere
apply_editorial_organization_plan	Apply a confirmed organization plan through guarded UXP bin transactions only

Project Management (26)

Tool	Description
save_project / save_project_as / open_project	File operations
create_project / close_project	Project lifecycle
import_media / import_folder / import_ae_comps	Import media and AE comps
create_bin / delete_bin / rename_bin / create_smart_bin	Bin management
import_sequences / import_fcp_xml	Import from other projects
create_bars_and_tone	Generate bars & tone media
set_scratch_disk_path	Configure scratch disks
consolidate_and_transfer	Project Manager consolidation

Timeline & Editing (10 + 27 advanced)

Tool	Description
add_to_timeline / overwrite_clip	Insert and overwrite edits
ripple_delete	Remove clip and close gap (QE)
roll_edit / slide_edit / slip_edit	Professional trim modes (QE)
move_clip_to_track	Move between tracks (QE)
reverse_clip / speed_change / set_clip_speed_qe	Unavailable: Premiere has no supported scripting API for changing a timeline clip's speed or direction
split_clip / trim_clip / move_clip	Basic edits; trim verifies source points and visible timeline edges
set_clip_properties	Opacity, scale, rotation, position (speed requests fail before mutation)
link_selection / unlink_selection	Link/unlink A/V

Premiere Pro 26.3 compatibility: some installations silently ignore QE structural edits (ripple_delete, razor/split) and existing effect-parameter writes. These tools now verify the resulting sequence state and return an error instead of a false success. For structural edits, rebuild the wanted source ranges into a new sequence with create_sequence and add_to_timeline. The legacy CEP transition path targets qeClip.addTransition (not the QE track) and reports success only after DOM transition-count readback. Prefer the connected UXP transition tools where available; overlay clips remain a workaround when a legacy QE write is rejected or not verified. See issue #21.

Speed, caption, and visual-keyframe boundaries: Premiere Pro 26.3 may reflect legacy QE speed/direction methods, but exposes no supported scripting setter or Time Remapping component for timeline-clip speed or direction. reverse_clip, speed_change, set_clip_speed_qe, and set_clip_properties with speed now stop before host mutation; use the Speed/Duration UI or pre-render retimed media. add_text_overlay likewise stops before mutation because a raw-text-to-caption API is not exposed; import an .srt/.vtt and use create_caption_track, or use a MOGRT/PNG overlay. Keyframe and caption-track responses can prove parameter/structure readback only—not rendered pixels—so verify playback or exported frames before delivery. On macOS, AME preset discovery scans each installed app bundle's Contents/MediaIO/systempresets; prefer a Match Source preset for vertical projects.

Verified track edits: add_track and add_tracks validate requested counts and return success only when the active sequence's track counts exactly match the request. overwrite_clip validates both selected track indices and confirms the requested source item appears at the requested frame on a target track. On a Premiere 26.x build that ignores any of these calls, the MCP response is an error with the observed state rather than a false success. These are automated CEP contracts, not proof of a particular licensed host configuration.

trim_clip accepts exactly one source-relative new_in_seconds or new_out_seconds per call. It refuses retimed clips because CEP cannot prove their source-to-timeline mapping, then reads both source points and visible timeline start/end/duration before reporting success. The default keyframe_policy: "reject" stops before a trim that would leave effect keyframes beyond the visible clip; keyframe_policy: "preserve" is an explicit opt-in and reports the remaining count. split_clip verifies a spanning clip, the expected count increase, and the left/right cut boundaries. Its QE path cannot prove effect-keyframe redistribution, so a successful result labels those semantics unverified. These are CEP contract checks, not validation in a licensed Premiere Pro 26.x host.

Effects & Color (8)

Tool	Description
apply_effect / apply_audio_effect	Apply by name (QE)
remove_effect / remove_all_effects	Remove effects
color_correct	Lumetri: exposure, contrast, temperature, etc.
apply_lut	Apply LUT files
stabilize_clip	Warp Stabilizer with configurable settings

Premiere 26.x component removal: remove_effect and remove_effect_by_name require the CEP Component.remove() method. Some 26.x components, including Essential Sound's Amplify, do not expose that method. The tools return an actionable capability error and leave the component unchanged; use Effect Controls to remove it manually. The QE DOM has no safe targeted-removal fallback.

Essential Sound audio automation: Essential Sound can write ducking or level automation to an Amplify component rather than the clip's Volume > Level. adjust_audio_levels, set_clip_volume, and get_clip_volume operate only on Volume > Level, so they do not read, change, or verify Amplify automation. Inspect the clip's components (or Effect Controls) before treating a Volume readback as the clip's final gain.

Keyframes (8)

Tool	Description
add_keyframe / get_keyframes	Create and read keyframes
remove_keyframe / remove_keyframe_range	Delete keyframes
set_keyframe_interpolation	Linear / Hold / Bezier
get_value_at_time	Query interpolated value at any time
set_color_value	Set color properties on effects

Export & Encoding (16)

Tool	Description
export_sequence	Export via Adobe Media Encoder
validate_export_preset	Validate an .epr file and resolve its output extension in Premiere
verify_delivery_file	Verify output size and calculate SHA-256/SHA-512 checksums
capture_frame	Export frame as PNG, return as base64 image
export_as_fcp_xml / export_aaf / export_omf	Interchange formats
encode_project_item / encode_file	Direct encoding
start_batch_encode	Start render queue

Premiere's documented automation surfaces do not currently expose OTIO or EDL interchange, Render and Replace, cloud publishing, or Content Credentials export configuration. get_capabilities reports these delivery gaps explicitly rather than presenting UI-only operations as available tools.

Source Monitor & Playback (7 + 4)

Tool	Description
open_in_source / close_source_monitor	Source monitor control
insert_from_source / overwrite_from_source	3-point editing
play_timeline / stop_playback	Playback control (QE)
play_source_monitor	Play in source monitor

Selection & Clipboard (7 + 6)

Tool	Description
select_clips_by_name / select_clips_in_range	Smart selection
copy_effects_between_clips	Copy effects via QE
batch_apply_effect	Apply effect to multiple clips
set_blend_mode	27 blend modes

Media Properties (16)

Tool	Description
set_offline / has_proxy / detach_proxy	Offline/proxy management
set_override_frame_rate	Override FPS
set_scale_to_frame_size	Auto-scale to sequence frame
get_xmp_metadata / set_xmp_metadata	Raw XMP access; writes merge a well-formed patch without removing unrelated fields
get_color_space	Color space info

Sequence Management (11)

Tool	Description
create_sequence / create_sequence_from_preset	Create sequences from .sqpreset files without opening Premiere's modal dialog
duplicate_sequence / delete_sequence	Manage sequences
auto_reframe_sequence	Auto-reframe for social media
attach_custom_property	FCP XML custom properties
unnest_sequence	Replace nested sequence with its clips

Workspace & Captions (2 + 1)

Tool	Description
get_workspaces / set_workspace	Switch workspace layouts
create_caption_track	Create caption/subtitle tracks

Scripting (2)

Tool	Description
execute_extendscript	Run arbitrary ExtendScript (ES3); requires explicit unsafe-script authority
evaluate_expression	Evaluate a one-line expression; requires explicit unsafe-script authority

...and 100+ more

Track targeting, batch operations, markers, audio levels, motion/transform, metadata, sequence settings, navigation, project analysis, and more. Run get_project_info to get started — the AI will discover what it needs.

---

MCP Resources

The server exposes fourteen LLM context resources and eleven workflow prompts:

Resource URI	Description
config://premiere-instructions	Best practices: workflow order, timeline rules, effect tips, error handling
config://extendscript-reference	Complete ExtendScript API reference for writing custom scripts
config://premiere-workflows	Machine-readable catalog for rough cuts, dialogue cleanup, captions, and delivery
config://premiere-project-context	Revisioned local project-context indexing and retrieval workflow
premiere://project/info	Fresh, path-redacted current-project and active-sequence summary
premiere://project/sequences	Bounded sequence inventory with stable Premiere IDs
premiere://project/media	Bounded, path-redacted project-media inventory
premiere://project/bins	Bounded, path-redacted project-bin inventory
premiere://timeline/active	Bounded active-timeline tracks, clips, and markers snapshot
premiere://effects/available	Bounded video/audio effect catalog for planning
premiere://effects/applied	Bounded active-timeline component inventory
premiere://transitions/available	Bounded video/audio transition catalog for planning
premiere://export/presets	Bounded export-preset names and formats, without native paths
premiere://project/metadata	Read-only project and active-timeline summary, without paths or timestamps

The ten premiere:// snapshots are read-only CEP bridge requests. They include a revision token for stale-state detection and omit native media, project-tree, preset, and output paths. A successful snapshot proves bridge readback only—not licensed-host feature coverage, playback, rendering, or editorial correctness.

---

Remote Deployment (Fly.io)

The server includes an HTTP/SSE transport (src/http-server.ts) for remote access via mcp-remote or any MCP client that supports Streamable HTTP.

A live operator-managed instance is running at https://premiere-pro-mcp.fly.dev. It is not a public desktop relay: it cannot connect an authenticated user to Premiere on that user's computer. Public users should use the local stdio setup until the separate device-pairing relay is available.

Connect to an operator-managed instance

{
  "mcpServers": {
    "premiere-pro": {
      "command": "npx",
      "args": ["mcp-remote", "https://your-authorized-instance.example/mcp"]
    }
  }
}

The instance must either provision an operator bearer token or use the OAuth resource-server configuration below. The production endpoint intentionally returns 401 to callers who have not been authorized.

Self-host on Fly.io

# Clone and deploy your own instance
git clone https://github.com/leancoderkavy/premiere-pro-mcp.git
cd premiere-pro-mcp
fly apps create your-app-name
# Required: add bearer token auth. Use a unique, high-entropy secret per deployment.
fly secrets set MCP_AUTH_TOKEN=your-secret-token
fly deploy --remote-only

Then connect with:

{
  "mcpServers": {
    "premiere-pro": {
      "command": "npx",
      "args": ["mcp-remote", "https://your-app-name.fly.dev/mcp",
               "--header", "Authorization: Bearer your-secret-token"]
    }
  }
}

Trusted-operator OAuth resource-server mode

For an identity-aware operator deployment, configure a real OAuth/OIDC authorization server rather than distributing MCP_AUTH_TOKEN. The authorization server must support the MCP client's registration model and issue signed access tokens with an exact audience for this MCP resource.

fly secrets set \
  MCP_OAUTH_ISSUER=https://identity.example.com \
  MCP_OAUTH_JWKS_URI=https://identity.example.com/.well-known/jwks.json \
  MCP_OAUTH_AUDIENCE=https://your-app-name.fly.dev/mcp \
  MCP_PUBLIC_URL=https://your-app-name.fly.dev \
  MCP_OAUTH_REQUIRED_SCOPES=premiere:mcp \
  MCP_OAUTH_ALLOWED_SUBJECTS=your-provider-user-subject

OAuth mode validates the token signature, algorithm, issuer, exact audience, expiry, issued-at time, subject, and required scopes. It publishes protected resource metadata at /.well-known/oauth-protected-resource/mcp and includes that URL in the WWW-Authenticate challenge. Configuration is fail-closed: partial OAuth settings, non-HTTPS production URLs, ambiguous OAuth/shared-token settings, and missing credentials all prevent startup.

MCP_OAUTH_ALLOWED_SUBJECTS is mandatory and restricts this single-bridge deployment to explicitly trusted operator identities. This is an enforcement boundary, not a public-user device model.

This mode authenticates trusted operators but does not yet implement device ownership, desktop pairing, or per-user Premiere routing. Do not expose editor mutations as a public multi-user service until an outbound desktop relay and durable user/device authorization are implemented.

Note: The file bridge still requires the CEP plugin to share the same PREMIERE_TEMP_DIR. For cloud deployments this means running a sync agent or using fly proxy / WireGuard to reach your local machine. detect_silence can analyze only media paths available inside the server filesystem; a desktop-only path is not automatically available to a remote Fly machine. For a shared or multi-user remote deployment, put a managed identity-aware edge in front of the server and replace the shared bearer secret with per-user authorization. The built-in limiter is intentionally process-local defense in depth, not a substitute for an edge/WAF or account system.

---

Environment Variables

Variable	Description	Default
PREMIERE_TEMP_DIR	Shared temp directory for MCP ↔ CEP communication	OS user temp dir + /premiere-mcp-bridge (macOS fallback is independent of TMPDIR)
PREMIERE_TIMEOUT_MS	Command timeout in milliseconds	30000
PREMIERE_DEFAULT_SEQUENCE_PRESET	Override the auto-discovered .sqpreset used by create_sequence	auto-discovered
PREMIERE_MCP_CAPABILITIES	Comma-separated authority profile; add unsafe-script only when raw scripting is required	inspect,edit,export,filesystem
PREMIERE_MCP_DEBUG	Set to 1 (or true) to emit verbose server diagnostics to stderr	unset
PREMIERE_CONTEXT_BACKEND	Local project-context store: auto, sqlite, json, or memory	auto
PREMIERE_CONTEXT_DIR	Override the local project-context storage directory	OS application-data directory
PORT	HTTP port (HTTP/SSE transport only)	3000
MCP_AUTH_TOKEN	Operator bearer token for controlled HTTP deployments; mutually exclusive with OAuth mode	unset
MCP_OAUTH_ISSUER	Exact trusted OAuth/OIDC token issuer URL	unset
MCP_OAUTH_JWKS_URI	HTTPS JWKS URL used to verify access-token signatures	unset
MCP_OAUTH_AUDIENCE	Exact MCP resource audience, normally the public /mcp URL	unset
MCP_PUBLIC_URL	Canonical HTTPS origin used in protected-resource discovery	unset
MCP_OAUTH_REQUIRED_SCOPES	Space- or comma-separated scopes required for /mcp	premiere:mcp
MCP_OAUTH_ALLOWED_SUBJECTS	Mandatory comma-separated token-subject allowlist for the single operator bridge	unset
ALLOW_UNAUTHENTICATED	Set to 1 only for local/test HTTP harnesses; it is rejected when NODE_ENV=production	unset
MCP_MAX_REQUEST_BYTES	Maximum HTTP MCP request body size	1048576
MCP_HEADERS_TIMEOUT_MS	Maximum time to receive request headers	10000
MCP_REQUEST_TIMEOUT_MS	Maximum time to receive an HTTP request	60000
MCP_KEEP_ALIVE_TIMEOUT_MS	Idle keep-alive socket timeout	5000
MCP_MAX_REQUESTS_PER_SOCKET	Requests permitted on one keep-alive socket	100
MCP_MAX_CONCURRENT_REQUESTS	In-flight authenticated MCP request ceiling	8
MCP_RATE_LIMIT_PER_MINUTE	Per-credential token-bucket refill rate	120
MCP_RATE_LIMIT_BURST	Per-credential short burst allowance	30
MCP_MAX_RATE_LIMIT_KEYS	In-memory rate-limit identity ceiling	2048
MCP_TRUST_PROXY	Set to 1 only behind a proxy that overwrites X-Forwarded-For	unset
POSTHOG_API_KEY	PostHog project token; enables privacy-safe MCP usage telemetry	unset
POSTHOG_HOST	PostHog ingestion host	https://us.i.posthog.com
POSTHOG_ENVIRONMENT	Environment property attached to telemetry events	production
POSTHOG_DISTINCT_ID	Optional stable anonymous server identifier	Fly machine ID or random boot ID

When PostHog is enabled, the server records mcp_connection_attempt, mcp_request, mcp_request_rejected, and mcp_tool_call. It also records premiere_mcp_activation_completed only after the read-only verify_premiere_connection check confirms the selected bridge, an open project, and an active sequence. Events contain bounded operational fields such as method, tool name, outcome, status code, duration, and selected bridge. Authentication tokens, IP addresses, MCP arguments, project paths, media names, and tool results are never sent. Person profiles are disabled for these events.

This signal is an aggregate emission, not proof that an analytics provider received it, a count of unique people or editors, or evidence that an editing workflow succeeded. It does not carry a person or editor identifier, so it cannot safely infer "first value."

---

Project Structure

premiere-pro-mcp/
├── src/
│   ├── index.ts                 # Entry point — stdio transport setup
│   ├── http-server.ts           # Entry point — HTTP/SSE transport (Fly.io / remote)
│   ├── server.ts                # MCP server — registers 327 tools, filtered by authority profile
│   ├── bridge/
│   │   ├── file-bridge.ts       # File-based IPC (write .jsx, poll .json)
│   │   └── script-builder.ts    # ExtendScript generator with ES3 helpers
│   ├── tools/                   # 31 tool modules
│   │   ├── discovery.ts         # Project discovery and queries
│   │   ├── recovery.ts          # Read-only autosave discovery and private bridge telemetry
│   │   ├── project.ts           # Project management and import
│   │   ├── media.ts             # Media and proxy management
│   │   ├── sequence.ts          # Sequence creation and settings
│   │   ├── timeline.ts          # Timeline clip operations
│   │   ├── effects.ts           # Effect application and color correction
│   │   ├── transitions.ts       # Transition management (QE DOM)
│   │   ├── audio.ts             # Audio levels, keyframes, and ffmpeg silence analysis
│   │   ├── av-settings.ts       # Documented AV inspection, mapping, and capability boundaries
│   │   ├── text.ts              # Text overlays and MOGRTs
│   │   ├── markers.ts           # Sequence and clip markers
│   │   ├── tracks.ts            # Track add/delete/lock/visibility
│   │   ├── playhead.ts          # Playhead, work area, in/out points
│   │   ├── metadata.ts          # Metadata, XMP, color labels
│   │   ├── export.ts            # Export, frame capture, encoding
│   │   ├── advanced.ts          # QE DOM: ripple, roll, slide, slip, speed
│   │   ├── keyframes.ts         # Keyframe CRUD and interpolation
│   │   ├── scripting.ts         # Execute arbitrary ExtendScript
│   │   ├── inspection.ts        # Deep project/sequence/clip inspection
│   │   ├── selection.ts         # Clip selection utilities
│   │   ├── clipboard.ts         # Copy effects, batch operations
│   │   ├── source-monitor.ts    # Source monitor control
│   │   ├── track-targeting.ts   # Track targeting, motion, audio props
│   │   ├── utility.ts           # Batch ops, analysis, navigation
│   │   ├── health.ts            # Connectivity ping
│   │   ├── workspace.ts         # Workspace layout switching
│   │   ├── captions.ts          # Caption track creation
│   │   ├── playback.ts          # Timeline/source playback control
│   │   └── project-manager.ts   # Project consolidation/transfer
│   └── resources/
│       └── extendscript-reference.ts  # API reference for LLM context
├── cep-plugin/                  # CEP panel that runs inside Premiere Pro
│   ├── CSXS/manifest.xml        # Extension manifest (PPRO 14.0+)
│   ├── index.html               # Panel UI
│   ├── main.js                  # Bridge polling and script execution
│   ├── host.jsx                 # ExtendScript entry point
│   └── CSInterface.js           # Adobe CEP interface library
├── scripts/
│   ├── install-cep.sh           # macOS CEP installer (symlink + debug mode)
│   └── install-cep.ps1          # Windows CEP installer (copy + REG_SZ debug mode)
├── Dockerfile                   # Multi-stage Docker build for Fly.io
├── fly.toml                     # Fly.io deployment config
├── RESEARCH.md                  # API research and implementation status
├── CONTRIBUTING.md              # Contribution guidelines
├── CHANGELOG.md                 # Version history
└── LICENSE                      # MIT License

---

Technical Details

CEP and UXP backends

CEP remains the production backend because it provides broad ExtendScript access and the undocumented QE DOM used for effects, ripple deletes, and advanced trims across Premiere Pro 2020–2026. The packaged uxp-plugin is a Premiere 25.6+ preview backend for supported frame export, capability discovery, and state events. It does not silently retry failed UXP mutations through CEP.

ExtendScript Compatibility

All generated scripts use ES3 syntax (var, manual for loops, no arrow functions, no let/const) since ExtendScript is based on ECMAScript 3. The bridge writes a versioned helper library to the shared temp directory and loads it once per ExtendScript engine via $.evalFile; each command then sends only its tool-specific script.

Security

Understand the trust model before deploying this: any client that can reach the MCP server can control Premiere Pro. execute_extendscript and evaluate_expression are arbitrary-code-execution tools by design and are omitted from discovery and denied at call time by default. Enable them only by setting PREMIERE_MCP_CAPABILITIES=inspect,edit,export,filesystem,unsafe-script.

• Run it locally over stdio unless you have a specific reason not to. That's the safe default.
• The HTTP transport (http-server) requires MCP_AUTH_TOKEN and refuses to start without it in production. It binds 0.0.0.0 and is remotely reachable, so never expose it publicly without a strong token and edge controls. ALLOW_UNAUTHENTICATED=1 is limited to non-production local/test use.
• The HTTP transport admits only exact /mcp Streamable HTTP requests, enforces body/socket/request limits, and applies a bounded in-process per-credential rate and concurrency limit before MCP request parsing or Premiere bridge work begins. It returns 413, 429, or 503 on containment failures. Configure an upstream rate limit and request-size limit too; process-local counters do not protect a multi-machine deployment.
• The landing CSP uses a per-response nonce for scripts, and its static assets use explicit cache policies. Keep the server in front of the exported landing so those controls are not bypassed by a separate static host.
• The bridge temp directory is created private to your user (mode 0700), and the server refuses to use one owned by another user — relevant on shared machines, where the CEP panel would otherwise execute any cmd_*.jsx staged there.
• There is a 500 KB script size limit, and a small regex check that rejects eval(), new Function(), and System.callSystem() in tool-generated scripts. This is a guard rail, not a sandbox — it is trivially bypassable and is not a security boundary. Do not rely on it to contain untrusted input; the real boundary is who can reach the server.

QE DOM

Many tools use the undocumented QE DOM (enabled via app.enableQE()). These tools are marked with "Uses QE DOM" in their descriptions. The QE DOM provides capabilities unavailable through the standard ExtendScript API:

• Apply effects and transitions by name
• Ripple delete, roll/slide/slip edits
• Set clip speed and reverse
• Frame blending and time interpolation
• Remove all effects from a clip

---

Troubleshooting

CEP plugin doesn't appear in Premiere Pro

1. Verify debug mode:
   • macOS: defaults read com.adobe.CSXS.12 PlayerDebugMode should return 1
   • Windows: reg query "HKCU\SOFTWARE\Adobe\CSXS.12" /v PlayerDebugMode should report REG_SZ 1 (a REG_DWORD value is not valid for unsigned CEP discovery)
2. Check the plugin exists:
   • macOS: ls ~/Library/Application\ Support/Adobe/CEP/extensions/MCPBridgeCEP
   • Windows: dir "%APPDATA%\Adobe\CEP\extensions\MCPBridgeCEP"
3. Completely restart Premiere Pro (not just close/reopen the project)
4. Check the CSXS version matches your Premiere Pro version
5. Run premiere-pro-mcp --diagnose-cep to check installation metadata and recent Premiere logs.

Version 1.3.0 and newer installs the signed artifacts/MCPBridgeCEP.zxp included in the npm package on Windows. If diagnostics report Signature verification failed, reinstall the latest npm version, fully quit every Premiere process, run premiere-pro-mcp --install-cep, and relaunch.

Commands timeout or hang

1. Open the CEP panel and verify it shows "Running" with a green dot (the bridge normally starts automatically)
2. Ensure temp directories match between MCP client config and CEP panel
3. Read the timeout error: if it reports an in-flight heartbeat, dismiss any open Premiere modal dialog; without a heartbeat, verify the bridge is running and using the same temp directory
4. Increase timeout: set PREMIERE_TIMEOUT_MS to 60000 or higher
5. Try ping tool to test basic connectivity

AI client can't see tools

1. Restart the AI client after editing config
2. Verify the path to dist/index.js is absolute and correct
3. Run node dist/index.js in a terminal to check for startup errors
4. Ensure npm run build completed without errors

QE DOM tools fail

1. QE tools require an active sequence — open one first
2. Some QE operations are index-based and can fail if clips have been reordered
3. Re-query the sequence structure after QE operations

---

Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

The evidence-backed next improvement pull-request roadmap breaks the proposed feature, protocol, reliability, and performance work into ten reviewable changes with explicit dependencies and live-host acceptance gates.

---

License

MIT — free for personal and commercial use.