Skip to main content

dcc-mcp-premiere

DCC-MCP · PREMIERE PRO

Typed DCC-MCP control for Adobe Premiere Pro through the shared adobepy broker and Adobe's UXP runtime. The adapter exposes bounded project, media, timeline, marker, save, frame-export, and AME queue operations. It deliberately does not expose raw JavaScript, evalJs, shell commands, or arbitrary UXP calls.

Premiere Pro typed project and timeline workflow

Illustrative workflow generated with OpenAI ImageGen from the retained source in docs/images/sources; it is not a Premiere Pro screenshot or host-validation artifact.

Install

python -m pip install dcc-mcp-premiere
adobepy install-bridge premiere --dest <plugin-dir> --token <non-default-token>

Load the generated bridge with Adobe UXP Developer Tool in Premiere Pro 25.6 or later. Set ADOBEPY_TOKEN to the same token, start the adapter, then verify the connected host through DCC-MCP discovery:

dcc-mcp-cli wait-ready --dcc-type premiere --timeout-secs 60
dcc-mcp-cli load-skill premiere-project --dcc-type premiere

Each adapter instance uses an OS-assigned port and registers with DCC-MCP discovery. Agents should connect through the stable local gateway at http://127.0.0.1:9765/mcp. Set DCC_MCP_PREMIERE_PORT only for a deliberately fixed direct endpoint.

Typed tools

Inspection:

  • get_status
  • inspect_project
  • list_sequences
  • inspect_sequence
  • list_project_items
  • list_selected_clips
  • list_encoder_presets

Project and timeline authoring:

  • create_bin
  • import_media
  • create_sequence
  • insert_project_item
  • overwrite_project_item
  • create_marker

Persistence and export:

  • save_project
  • save_project_as
  • queue_sequence_export
  • export_frame

List and scan operations are paginated and bounded. Imports accept at most 100 files, with per-file and aggregate byte limits. Track indices, marker text, frame dimensions, and output extensions are validated before invoking the host. AME export reports queued=true; completion must be verified separately.

Safe local paths

The adapter resolves paths before calling Premiere and confines them to:

  • DCC_MCP_PREMIERE_ALLOWED_INPUT_ROOTS for imported media
  • DCC_MCP_PREMIERE_ALLOWED_OUTPUT_ROOTS for .prproj and exported media
  • DCC_MCP_PREMIERE_ALLOWED_PRESET_ROOTS for .sqpreset and .epr files

Each variable uses the platform path separator and defaults to the current user's home directory. Existing outputs require overwrite=true; missing parent directories require create_parents=true. Verified synchronous outputs include byte count and SHA-256.

Real-host acceptance

Automated tests use contract-compatible facade fakes; they are not represented as live Premiere proof. With a disposable project open and the UXP bridge connected, configure the three allowlists and run:

set DCC_MCP_PREMIERE_SMOKE_MEDIA=C:\path\to\media.mp4
set DCC_MCP_PREMIERE_SMOKE_ROOT=C:\path\to\writable-evidence
python tools/live_premiere_smoke.py

The smoke script uses dcc-mcp-cli for readiness, skill loading, and every typed call. It imports media, authors and inspects a sequence, adds a marker, saves a verified project copy, exports a verified frame, and prints hashes. Set DCC_MCP_PREMIERE_SMOKE_EPR to an allowlisted .epr file to include an AME queue test.

Development

python -m pip install -e ".[dev]"
python -m pytest -q
python -m ruff check src tests tools
python -m ruff format --check src tests tools
python tools/lint_skills.py
python -m build
python -m twine check dist/*

See docs/architecture.md for ownership, readiness, and security boundaries.

Metadata

Release files for dcc-mcp-premiere 0.5.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for dcc-mcp-premiere 0.5.0
File Size Uploaded
dcc_mcp_premiere-0.5.0.tar.gz 27.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for dcc-mcp-premiere 0.5.0
File Interpreter ABI Platform
dcc_mcp_premiere-0.5.0-py3-none-any.whl Python 3 none any Details

Total release size: 54.8 kB

Release files / dcc_mcp_premiere-0.5.0.tar.gz

Download URL dcc_mcp_premiere-0.5.0.tar.gz
Size 27.0 kB
Tags Source
SHA-256 checksum
How to use checksums
420fbf02baf836895eed66e7f687bd3a3a449a634edca29c1a44eba2f60c68b3
BLAKE2b-256 checksum
How to use checksums
f859a5bed52834bb3fdba20330ddb0eee3aee8d0def863a022c61dd2f578304d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 12, 2026.

Transparency log

Release files / dcc_mcp_premiere-0.5.0-py3-none-any.whl

Download URL dcc_mcp_premiere-0.5.0-py3-none-any.whl
Size 27.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
e35061610b0aba182b2eec29f2dc111cffb9d92194f9321f43805213456c3252
BLAKE2b-256 checksum
How to use checksums
5ce1f7602fec72ded139a7a10bde8783cd5690b14f4377278e0ead284f2137e2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 12, 2026.

Transparency log

Release history Release notifications | RSS feed

0.6.1

2 release files

0.6.0

2 release files

This release

0.5.0 This release

2 release files

0.4.0

2 release files

0.3.0

2 release files

0.2.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page