Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

vmaf-mcp

DEPRECATED (ADR-1229). The MCP server is now the Go binary vmafx-mcp (cmd/vmafx-mcp/), installed at /usr/local/bin/vmafx-mcp in every container image. Attach with docker exec -i vmaf-dev-mcp vmafx-mcp. This Python package implements the same fifteen tools and is retained for one release as a reference implementation; it is no longer installed by dev/Containerfile and a follow-up removes it. Do not add tools here — add them to cmd/vmafx-mcp/.

MCP (Model Context Protocol) server that exposes the VMAFx fork's scoring CLI to LLM tooling via JSON-RPC over stdio.

Tools

Tool Description
vmaf_score Score a (ref, dis) raw YUV pair. Returns the full JSON report.
vmaf_score_encoded Score encoded video (MP4/MKV/Y4M/…) — decodes via ffmpeg, then scores. (ADR-0608)
list_models Enumerate models under model/ (.json, .pkl, .onnx).
list_backends Report which backends (cpu/cuda/sycl/hip/metal) are compiled in.
probe_backend Runtime health check: compiled-in vs driver-functional distinction. (ADR-0608)
vmaf_version Return binary path, version string, and build flags. (ADR-0608)
run_benchmark Run testdata/bench_all.sh on the built-in fixture pairs.
eval_model_on_split Evaluate an ONNX tiny-AI model on a parquet feature split.
compare_models Rank ONNX models on the same split by PLCC.
Tool Description
--------------- ------------------------------------------------------------
vmaf_score Score a (ref, dis) YUV pair. Returns the full JSON report.
list_models Enumerate models under model/ (.json, .pkl, .onnx).
list_backends Report which backends (cpu/cuda/sycl/hip) are live.
run_benchmark Run testdata/bench_all.sh on a pair.
eval_model_on_split Evaluate an ONNX tiny-AI model on a parquet feature split.
compare_models Rank ONNX models on the same split by PLCC.
describe_worst_frames Extract the lowest-VMAF frames and describe visible artefacts with local VLM extras.

Install

cd mcp-server/vmaf-mcp
pip install -e .

Requires a built libvmaf binary at build/tools/vmaf (override via VMAF_BIN=/abs/path/to/vmaf).

Run

# Stdio transport (default for Claude Desktop, Cursor, etc.)
vmaf-mcp

Path allowlisting

For safety, the server only reads files under testdata/, python/test/resource/, and model/. Extend via colon-separated VMAF_MCP_ALLOW:

VMAF_MCP_ALLOW=/data/my-corpus:/mnt/yuv vmaf-mcp

Claude Desktop config

{
  "mcpServers": {
    "vmaf": {
      "command": "vmaf-mcp",
      "env": {
        "VMAF_BIN": "/home/you/dev/vmaf/build/tools/vmaf",
        "VMAF_MCP_ALLOW": "/data/yuv-corpus"
      }
    }
  }
}

Release files for vmaf-mcp 1.0.0rc1

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

Source distribution (sdist)

Source distribution for vmaf-mcp 1.0.0rc1
File Size Uploaded
vmaf_mcp-1.0.0rc1.tar.gz 295.7 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for vmaf-mcp 1.0.0rc1
File Interpreter ABI Platform
vmaf_mcp-1.0.0rc1-py3-none-any.whl Python 3 none any Details

Total release size: 360.2 kB

Release files / vmaf_mcp-1.0.0rc1.tar.gz

Download URL vmaf_mcp-1.0.0rc1.tar.gz
Size 295.7 kB
Tags Source
SHA-256 checksum
How to use checksums
a222929bbb5ac18890e90d30700a4376c5ff0f62ad0251e2fa32d0468b8f0cd8
BLAKE2b-256 checksum
How to use checksums
e4db35382aeab1c86da507de9f42f95ba4abb9ef7b29a413fb43a64459e0a51e
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 Sep 27, 2026.

Transparency log

Release files / vmaf_mcp-1.0.0rc1-py3-none-any.whl

Download URL vmaf_mcp-1.0.0rc1-py3-none-any.whl
Size 64.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
2e711371dac4ebb1ee0a3d0068e05eb4b0f457d7864ca16ffc99cdc97bff15a8
BLAKE2b-256 checksum
How to use checksums
86ec695862af1ba559179a7ce75859a8e844e77833de045effbb39f84711ae8c
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 Sep 27, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

1.0.0rc1 This release

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