mcp.film

mcp.film / Video Generation / Google GenMedia MCP

Google GenMedia MCP

Officialby Google Cloudpaidverified Oct 19, 2026

Google Cloud's MCP servers for Veo, Gemini Omni, Lyria, Chirp TTS and ffmpeg compositing.

What it does

A suite of Go-based MCP servers from Google Cloud's GenMedia Creative Studio repo: Veo text/image-to-video plus extension, first/last-frame, reference and ingredients tools, a Gemini Omni video server, Nano Banana and Gemini stills, Gemini transcription, Lyria music, Chirp 3 TTS, and an AVTool server wrapping ffmpeg for compositing. The closest thing to an official Veo MCP, and a full agentic production toolchain on Vertex AI.

Connect

Connection is set up through the vendor's flow — follow the official connect instructions.

Local install: One binary per model. Install them all with the repo's script — curl -sL https://raw.githubusercontent.com/GoogleCloudPlatform/genmedia-creative-studio/main/experiments/mcp-genmedia/mcp-genmedia-go/install-online.sh | bash — or build from source with go work sync && go install ./mcp-avtool-go ./mcp-chirp3-go ./mcp-gemini-go ./mcp-gemini-transcribe-go ./mcp-nanobanana-go ./mcp-lyria-go ./mcp-veo-go ./mcp-omni-go, then point your client at each binary (mcp-veo-go for Veo) with GOOGLE_CLOUD_PROJECT set

Auth: api_key · env GOOGLE_CLOUD_PROJECT — Google Cloud project with Vertex AI enabled; uses Application Default Credentials (gcloud auth application-default login)

Sample tools

veo_t2vveo_i2vveo_extend_videoveo_first_last_to_videoveo_ingredients_to_videoomni_video_generationlyria_generate_musicgemini_transcribechirp_ttslist_chirp_voices

Field notes

Official Google Cloud code but explicitly experimental (lives in /experiments). The repo has been renamed: GoogleCloudPlatform/vertex-ai-creative-studio now redirects to GoogleCloudPlatform/genmedia-creative-studio, and the README's install-online.sh URL uses the new path — GitHub redirects old clone URLs, but update pinned raw links. Very active as of 19 Oct 2026: 1,223 stars, pushed 2026-10-18, VERSION 3.21.0 released 2026-10-17. Nine servers now: mcp-gemini-transcribe-go (gemini_transcribe on Gemini 3.5 Transcribe, global location only) joined, and the README's go install line finally includes mcp-omni-go. Veo exposes veo_t2v, veo_i2v, veo_extend_video, veo_first_last_to_video, veo_reference_to_video and veo_ingredients_to_video and defaults to veo-3.1-fast-generate-001; residual Veo 2.0 references were stripped on 2026-10-17. gemini_audio_tts gained Gemini 3.8 TTS. Imagen is on the way out: mcp-imagen-go carries a deprecation banner, is excluded from the default install line, and the README says Imagen models were deprecated as of June 30, 2026 — use mcp-nanobanana-go (defaults to gemini-nano-banana-2.1) for stills. Install is still the rough edge — no npx one-liner, no published claude mcp add, so you pipe install-online.sh to bash or go install per directory and wire each binary in yourself. Omni is preview-gated and calls the global-only Interactions endpoint, ignoring regional overrides. Supports stdio/HTTP/SSE and GCS or local output; ships agent skills for storyboarding. With Sora leaving the API on 2026-09-24, this is the most direct official route to Veo 3.1 for an agent.

Also in Video Generation

Used in

AI Commercial Sprint · Model Shootout · Compare video and image models before spending the budget · Generate voice, score, and sound assets

Pairs well with