Generate short videos from text or images, or edit existing videos with natural language instructions, using Gemini Omni Flash. Returns video synchronously without polling.
Apache 2.0
650,537 tools. Updated 2026-10-14 07:11
"Connecting to Gemini Flash Experimental" matching MCP tools:
- Run tasks on Google's Gemini models via local CLI, using your Google One AI Pro subscription. Use as a fallback when Claude limits are tight or for tasks benefiting from Gemini.MIT
- Send text prompts to Google Gemini to receive responses. Supports configurable models and multi-turn conversations with session context.AGPL 3.0
- Send detailed prompts to Gemini CLI, choose models by task complexity, and continue multi-turn sessions with session_id. Returns response text, model used, and session ID.MIT
- Flash firmware to Telink chips, read back flash content, or reset the chip using bdt.exe. Supports writing, reading, and erasing flash, core, analog, and OTP memory.MIT
- Generate images from text descriptions using Gemini models. Configure size, aspect ratio, and include reference images for custom results.Apache 2.0
Matching MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables AI clients to create spaced-repetition flashcards from material being learned, quiz users aloud, grade answers, and schedule reviews using the FSRS algorithm through a self-hosted MCP server.3AGPL 3.0
- AlicenseAqualityDmaintenanceEnables conversational image generation and editing with Google's Gemini 2.5 Flash Image Preview. Supports text-to-image generation, natural language image editing, multi-image composition, and style transfer with optional file saving.48 npm3MIT
Matching MCP Connectors
- FlashOAuth
Spaced-repetition flashcards your AI writes, quizzes you on by voice, and schedules with FSRS.
Gemini Exchange MCP (public endpoints).
- Batch-generate Google Gemini images from text prompts and save them to an absolute directory for use in websites or apps.MIT
- Verify the AGY CLI version, list available models, and confirm the default gemini-3.8-flash-high model is present to avoid runtime failures before starting tasks.MIT
- Retrieve accurate answers and verify facts by leveraging Gemini 2.0 Flash and Google Search integration. Ideal for general knowledge queries, fact-checking, and detailed information retrieval.MIT
- Generate images using Google Gemini and save to a specified file path. Automatically resolves filename conflicts by appending a numeric suffix.MIT
- Edit existing images with natural language prompts using Google Gemini. Supports multi-image input (up to 10) and saves the edited full-resolution image to disk.MIT
- Generate an image from a text prompt using Gemini 2.5 Flash Image. Returns the image in base64.MIT
- Send prompts to Google's Gemini AI through the command line. Specify a model and timeout to control the response.MIT
- Send self-contained routine tasks to Gemini Flash with selected files and acceptance criteria, then batch-check results via Jev for a preview and review verdict.MIT
- Generate images from text prompts using Gemini AI models, saving them to specified file paths with configurable aspect ratios and quality options.MIT
- Set the default Gemini model for generating app images, persisting across sessions. Choose faster or higher quality models.MIT
- Generate an image from a text prompt using Google Gemini or Imagen models. Supports multiple models; retry with a different model if quota limit is reached.MIT
- Generate an image from a text prompt using Google Gemini and save it to assets/images. Optionally override the model or set a custom filename for the saved output.MIT
- Launch any Claude, Codex, Gemini, Grok, or Pi CLI agent as a background process and get its PID instantly; then poll status and fetch results by PID.MIT
- Generate an image from a text prompt using Gemini 2.5 Flash, returning a file path to avoid token limit issues from base64 data.MIT
- Describe image content with Google Gemini. Answer specific questions about an image by providing a file path and optional question.MIT