Skip to main content
Glama
nikships

Gemini Omni MCP

by nikships
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

Gemini Omni MCP Banner

Gemini Omni MCP

MCP server for Google's Gemini Omni Flash video model — text-to-video, image-to-video, reference-guided video, and conversational video editing with native audio, straight from your AI agent.

PyPI version Python 3.11+ License: MIT

Setup

Get a Gemini API key from Google AI Studio, then add the server to your MCP config.

Claude Desktop / Claude Code / Cursor

Add to your MCP config (mcp.json / .claude.json / claude_desktop_config.json):

{
  "mcpServers": {
    "gemini-omni": {
      "command": "uvx",
      "args": ["gemini-omni-mcp@latest"],
      "env": {
        "GEMINI_API_KEY": "your-api-key-here"
      }
    }
  }
}

Droid CLI

droid mcp add gemini-omni "uvx gemini-omni-mcp@latest" --env GEMINI_API_KEY=your-api-key-here

Generated MP4s are saved to ~/gemini_omni_videos by default (set OUTPUT_DIR to change).

Related MCP server: veo-mcp-server

Features

  • Text-to-video: prompt-only MP4 generation with generated audio (music, ambience, SFX)

  • Image-to-video: animate a single reference image with motion and camera direction

  • Reference-to-video: up to 6 reference images to lock subjects, style, or props

  • Conversational editing: iterate on a generated video via previous_interaction_id, or upload your own MP4 and edit it

  • Prompt role tags: <FIRST_FRAME> and <IMAGE_REF_N> bind reference images to roles

  • Timing cues: [0-3s], [3-6s], [6-10s] direct the action beat by beat

  • Batch generation: run multiple prompts in conservative parallel batches (max 4)

  • URI or inline delivery: robust Files API polling and download built in

Output is 720p 24fps MP4 with SynthID watermarking (preview-quality model).

Showcase

All videos below were generated by this server with gemini-omni-flash-preview, sound on.

Corgi on a hoverboard

A corgi wearing tiny goggles rides a glowing hoverboard through a neon-lit Tokyo street at night, rain reflections on the pavement, camera tracking alongside, single continuous shot, cinematic lighting, upbeat synthwave music.

https://github.com/user-attachments/assets/4b9a8e87-7db0-469d-a261-3c354f7fe9b8

Astronaut latte art

An astronaut in a white spacesuit pours latte art into a floating cup inside a cozy moon-base cafe, Earth visible through a large window, steam swirling in low gravity, slow dolly-in, warm lighting, gentle ambient cafe sounds.

https://github.com/user-attachments/assets/88072ef8-1ce4-4c80-a05a-bfb5531d1271

Origami ocean

An origami paper whale swims gracefully through a stylized paper-craft ocean, paper waves folding and unfolding, paper seagulls gliding above, soft sunlight, camera slowly orbiting, calm orchestral score.

https://github.com/user-attachments/assets/c1e31341-e53c-4a55-af12-d6bb9432dcf5

Tools

generate_video

Generates or edits one MP4 and returns JSON with video.path, interaction_id, and metadata.

Argument

Type

Description

prompt

string

Scene, motion, camera, lighting, mood, and audio direction

task

string?

text_to_video, image_to_video, reference_to_video, or edit. Inferred if omitted

aspect_ratio

string?

16:9 (default) or 9:16

duration_seconds

int?

Optional preview field, 3 to 10

reference_image_paths

list?

Up to 6 local image paths

input_video_path

string?

Local MP4 to upload and edit

delivery

string?

uri (default, recommended) or inline

previous_interaction_id

string?

Continue editing a generated video

enhance_prompt

bool?

Optional LLM prompt enhancement, default false

batch_generate

Runs multiple prompts in parallel batches, capped at 4.

Argument

Type

Description

prompts

list

One prompt per video

task, aspect_ratio, duration_seconds, reference_image_paths, delivery, enhance_prompt

—

Shared across the batch, same semantics as generate_video

batch_size

int?

Parallelism, capped at MAX_BATCH_SIZE

Configuration

Everything is configured through environment variables (or a local .env):

Variable

Default

Description

GEMINI_API_KEY

—

Required. GOOGLE_API_KEY also accepted

OUTPUT_DIR

~/gemini_omni_videos

Where generated MP4s are saved

DEFAULT_ASPECT_RATIO

16:9

16:9 or 9:16

DEFAULT_DELIVERY

uri

uri or inline

DEFAULT_DURATION_SECONDS

unset

Optional 3-10s target

REQUEST_TIMEOUT

300

Generation timeout in seconds

FILE_POLL_INTERVAL

5.0

Seconds between Files API polls

FILE_POLL_TIMEOUT

600

Max seconds waiting for file activation

MAX_BATCH_SIZE

4

Max parallel generations

ENABLE_PROMPT_ENHANCEMENT

false

LLM-enhance prompts before generation

LOG_LEVEL

INFO

Logging level

Prompting tips

  • Ask for a "single continuous shot" and "no scene cuts" for one-scene outputs.

  • Always include audio direction, for example "gentle ambient sound, no dialogue".

  • For edits, keep the prompt short and add "Keep everything else the same".

  • Use <FIRST_FRAME> and <IMAGE_REF_N> tags to bind reference-image roles.

  • Timing cues like [0-3s], [3-6s], and [6-10s] work well.

Limitations

  • Preview model: 720p, 24fps, MP4 only, SynthID-watermarked.

  • System instructions, temperature, negative prompts, voice edits, YouTube sources, and multi-video reasoning are unsupported.

  • Uploaded-video editing is unavailable in some regions.

Development

git clone https://github.com/nikships/gemini-omni-mcp
cd gemini-omni-mcp
uv sync --all-extras
uv run ruff format .
uv run ruff check .
uv run mypy gemini_omni_mcp/
uv run pytest
uv build

Releases are automated: every push to main bumps the version and publishes to PyPI (see PUBLISHING.md).

License

Gemini Omni MCP is licensed under the MIT license. See LICENSE for details.

Available Tools

2 tools
batch_generateA

Generate multiple Gemini Omni Flash videos in conservative parallel batches.

Use for storyboards, aspect-ratio comparisons, or reference-guided variations. Batch size defaults to configuration and is capped at 4 because video jobs are long. The JSON response includes per-prompt video.path, interaction_id, metadata, and errors.

ParametersJSON Schema
NameRequiredDescriptionDefault
taskNo
promptsYes
deliveryNo
batch_sizeNo
aspect_ratioNo
enhance_promptNo
duration_secondsNo
reference_image_pathsNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description discloses key behaviors: conservative parallel batching, batch size cap at 4, and response structure (video.path, interaction_id, etc.). It does not discuss authentication or rate limits, but the tool is a generator so destructive effects are minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is brief, with the primary action in the first sentence, followed by use cases and key constraints. Every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 8 parameters and no schema descriptions, the description is incomplete for parameter semantics. It does mention the output format (JSON with specific fields) and batch behavior, but more detail on each parameter's role is needed for full contextual completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain parameters. It only covers batch_size, aspect_ratio, and reference_image_paths implicitly. Other parameters like task, delivery, enhance_prompt, and duration_seconds are not mentioned, leaving the agent underinformed for 8 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool generates multiple Gemini Omni Flash videos in parallel batches. It explicitly mentions use cases like storyboards and aspect-ratio comparisons, distinguishing it from the sibling tool 'generate_video' which likely handles single video generation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides specific usage scenarios (storyboards, comparisons, variations) and a rationale for batch size cap ('because video jobs are long'), guiding when to use. It implicitly excludes single-video use, but could be more explicit about when to prefer the sibling tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

generate_videoA

Generate or edit MP4 videos with Gemini Omni Flash.

Capabilities:

  • text_to_video: prompt-only video with generated audio.

  • image_to_video: one reference image plus motion and camera direction.

  • reference_to_video: multiple reference images for subjects, style, or props.

  • edit: use previous_interaction_id or input_video_path to edit existing video.

Parameters:

  • prompt: Describe the scene, motion, camera movement, lighting, mood, and audio.

  • task: text_to_video, image_to_video, reference_to_video, or edit. If omitted, inferred.

  • aspect_ratio: 16:9 landscape or 9:16 portrait.

  • duration_seconds: Optional 3 to 10 second target. If the API rejects this preview field, retry without it.

  • reference_image_paths: Up to 6 local images. Use or tags in the prompt for control.

  • input_video_path: Local MP4 to upload and edit through the Files API.

  • delivery: uri is recommended for generated MP4 files; inline is supported for smaller payloads.

  • previous_interaction_id: Continue editing a prior generated video.

  • enhance_prompt: Optional, default false. For edits, simple prompts usually work better.

Prompt tips:

  • Ask for "single continuous shot" and "no scene cuts" when you want one scene.

  • Include explicit audio direction such as "gentle ambient room tone, no dialogue".

  • For edits, say "Keep everything else the same".

  • Timing cues like [0-3s], [3-6s], [6-10s] are supported.

Limitations:

  • Output is MP4, currently 720p at 24fps, SynthID-watermarked, and preview quality.

  • System instructions, temperature, top_p, stop sequences, negative_prompt, voice edits, YouTube sources, and multi-video reasoning are unsupported.

  • Uploaded-video editing is unavailable in some regions.

Returns JSON including video.path, interaction_id, task, aspect_ratio, delivery, size, and URI metadata. After success, open video.path with the native OS video viewer.

ParametersJSON Schema
NameRequiredDescriptionDefault
taskNo
promptYes
deliveryNo
aspect_ratioNo
enhance_promptNo
duration_secondsNo
input_video_pathNo
reference_image_pathsNo
previous_interaction_idNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses limitations (720p, 24fps, watermark, preview quality), unsupported features, region restrictions, and post-success behavior (open video.path). Annotations absent, so description carries full burden and does well.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with sections and bullets, but lengthy. Front-loads purpose. Every sentence adds value, but slight redundancy in parameter listing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers capabilities, parameters, prompt tips, limitations, return values. Output schema exists, but description adds detailed return structure. Complete for a complex tool with 9 parameters and a sibling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 9 parameters are individually described with context, defaults, and usage nuances (e.g., duration_seconds retry, reference tags). Compensates fully for 0% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Generate or edit MP4 videos' and enumerates four specific capabilities (text_to_video, etc.). Distinguishes from sibling 'batch_generate' by focusing on single generation/editing tasks, though not explicitly contrasted.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides task categories and prompt tips, but lacks explicit guidance on when to use vs. batch_generate or when to avoid. Usage context is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.2/5.0
Disambiguation5/5

The two tools serve completely distinct purposes: batch_generate for parallel multi-video generation and generate_video for single video creation/editing. There is no overlap in functionality, ensuring clear differentiation.

Naming Consistency5/5

Both tool names follow a consistent verb_noun pattern in snake_case (generate_video, batch_generate). The naming style is uniform, making it predictable for agents.

Tool Count4/5

With only two tools, the server is narrowly scoped but appropriate for its focused purpose of video generation. The tools cover both single and batch workflows without unnecessary bloat.

Completeness4/5

The tool surface covers the core generation lifecycle (text-to-video, image-to-video, reference-to-video, editing) and batch processing. Minor gaps exist (no listing of previous interactions or deletion), but these are not essential for the domain.

Maintenance

ActivityMaintained
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nikships/gemini-omni-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server