Gemini MCP integration
Generates text, speech, images, and Veo video from a prompt, embeds text for semantic search, and counts tokens before a call is made.
7actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Generate content (gemini)
Lyro uses Gemini to create contextual, detailed responses to complex customer questions. Customers get accurate, thoughtful answers instead of canned templates.
Embed content (gemini)
Lyro understands semantic meaning to find similar past issues and solutions. Your team resolves customers faster by surfacing precedent conversations with similar problems.
Generate image (nano banana)
Lyro creates visual explanations, diagrams, or product mockups for customers. Customers understand complex concepts faster with AI-generated graphics tailored to their needs.
How businesses use Gemini + Lyro
Each card is one request a support team gets, and the Gemini actions Lyro runs to close it.
Draft text or speech audio from a prompt
Lyro checks which Flash and Pro models are currently available, counts the tokens in the input, then generates the text or text-to-speech output with the parameters the request calls for.
List Models (Gemini API)Count Tokens (Gemini)Generate Content (Gemini)Produce an image from a description
Lyro generates the image with the model that suits the job, from fast stable output to the 4K preview model that accepts reference images, and stores the returned URL immediately because those links expire.
Generate Image (Nano Banana)List Models (Gemini API)Run a Veo video job through to the file
Lyro starts the video generation, holds the returned operation name unaltered, and polls until the job completes, validating that a video URL actually came back before treating the render as finished.
Generate Videos (Veo)Wait And Download Video (Veo)List Models (Gemini API)Turn your own text into searchable vectors
Lyro converts text into embeddings for semantic search, similarity comparison, clustering, or classification, and counts the tokens first so a large corpus is costed before the run starts.
Embed Content (Gemini)Count Tokens (Gemini)List Models (Gemini API)
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Gemini actions it has and picks the ones a request needs.
Connect Gemini
Authorize the Gemini account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Gemini actions that close it and chains as many as the request needs.
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free
Gemini · Lyro
What can you do in Gemini without me setting anything up?
These, right away:
- Generate content (gemini)
- List models (gemini API)
- Count tokens (gemini)
Great, let's start with the first one.
FAQ
Everything else about Gemini
Setup, permissions, and the limits of what Lyro can do inside Gemini.
Because hard-coded model IDs go stale. List Models returns the Gemini and Veo models currently available with their capabilities and limits, and preview Veo models in particular can be unavailable or return no video URI, so Lyro verifies availability and prefers a stable model over a preview name someone wrote down last quarter.
Every action available in Gemini
All 7 actions your agent can call on Gemini, straight from the live MCP connection.
Count tokens (gemini)
Counts the number of tokens in text using Gemini tokenization.
Embed content (gemini)
Generates text embeddings using Gemini embedding models.
Generate content (gemini)
Generates text content or speech audio from prompts using Gemini models.
Generate image (nano banana)
Generates images from text prompts using Gemini models (Nano Banana).
Generate videos (veo)
Generates videos from text prompts using Google's Veo models.
List models (gemini API)
Lists available Gemini and Veo models with their capabilities and limits.
Wait and download video (veo)
Polls a Veo video generation operation until completion, then downloads and returns the video as a FileDownloadable.
The tools Gemini sits next to
Same connection, same setup. Pick the next one your team already uses.
Bigml
Inventories models, clusters, and anomaly detectors, reads their evaluations and predictions, and sets up projects and external data connectors.
DeepSeek
Sends prompts to deepseek-chat or deepseek-reasoner with tool calling and thinking mode, and checks balance and model availability first.
Jigsawstack
Reads text out of customer attachments, translates and voices replies, and screens submitted text and images before they reach the queue.
Ollama
Route a request to a self-hosted model, reuse OpenAI-format endpoints against it, and report which models the host currently has installed.
Scale.ai
Creates image, video, LiDAR, and text annotation tasks, batches and finalizes them, reports completion counts, and reassigns Studio projects.
Veo
Submits a prompt as a Veo generation job, tracks the operation until it finishes, and downloads the finished clip.
Ready to connect Gemini?
Authorize the account and your agent has all 7 actions from the first conversation.