MCP Gemini
Connects Claude to Google's Gemini AI with 39 tools spanning text generation, image creation via Imagen 4, video generation with Veo, document analysis, YouTube summarization, text-to-speech, and multi-step web research. You get structured output extraction, content caching for repeated queries, code execution, and Google Search grounding for queries. Notable for image editing sessions where you can iteratively refine generated images across multiple turns. Runs locally via stdio so your API key stays on your machine. Reach for this when you want Claude to tap Gemini's multimodal capabilities, especially for tasks like analyzing PDFs, generating videos, or running deep research operations that span multiple web sources.
- tools
- 8
- transport
- STDIO
- last updated
- Mar 2, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
GEMINI_COUNT_TOKENSCounts the number of tokens in text using Gemini tokenization. Useful for estimating costs, checking input limits, and optimizing prompts before making API calls.2 params
Counts the number of tokens in text using Gemini tokenization. Useful for estimating costs, checking input limits, and optimizing prompts before making API calls.
modelstringtextstringGEMINI_EMBED_CONTENTGenerates text embeddings using Gemini embedding models. Converts text into numerical vectors for semantic search, similarity comparison, clustering, and classification tasks.4 params
Generates text embeddings using Gemini embedding models. Converts text into numerical vectors for semantic search, similarity comparison, clustering, and classification tasks.
modelstringtask_typestringtextstringtitlestringGEMINI_GENERATE_CONTENTGenerates text content from prompts using Gemini models. Supports various models like Gemini Flash and Pro with configurable temperature, token limits, and safety settings for diverse text generation tasks.9 params
Generates text content from prompts using Gemini models. Supports various models like Gemini Flash and Pro with configurable temperature, token limits, and safety settings for diverse text generation tasks.
max_output_tokensintegermodelstringpromptstringsafety_settingsarraystop_sequencesarraysystem_instructionstringtemperaturenumbertop_kintegertop_pnumberGEMINI_GENERATE_IMAGEGenerates images from text prompts using Gemini 2.5 Flash Image Preview model (Nano Banana). Supports creative image generation with customizable parameters like aspect ratio, safety settings, and optional local file saving. Generated images are automatically uploaded to S3 an...9 params
Generates images from text prompts using Gemini 2.5 Flash Image Preview model (Nano Banana). Supports creative image generation with customizable parameters like aspect ratio, safety settings, and optional local file saving. Generated images are automatically uploaded to S3 an...
max_output_tokensintegermodelstringpromptstringsafety_settingsarraysave_pathstringsystem_instructionstringtemperaturenumbertop_kintegertop_pnumberGEMINI_GENERATE_VIDEOSGenerates videos from text prompts using Google's Veo models. Creates high-quality video content. Returns operation ID for tracking progress. After this, call GEMINI_WAIT_FOR_VIDEO to download the video using the operation ID.4 params
Generates videos from text prompts using Google's Veo models. Creates high-quality video content. Returns operation ID for tracking progress. After this, call GEMINI_WAIT_FOR_VIDEO to download the video using the operation ID.
extrasobjectmodelstringperson_generationstringpromptstringGEMINI_GET_VIDEOS_OPERATIONChecks the status of a Veo video generation operation. Use the operation name from GenerateVideos to track progress and get the download URL when complete.1 params
Checks the status of a Veo video generation operation. Use the operation name from GenerateVideos to track progress and get the download URL when complete.
operation_namestringGEMINI_LIST_MODELSLists available Gemini and Veo models with their capabilities and limits. Useful for discovering supported models and their features before making generation requests.1 params
Lists available Gemini and Veo models with their capabilities and limits. Useful for discovering supported models and their features before making generation requests.
filter_prefixstringGEMINI_WAIT_FOR_VIDEOPolls a Veo video generation operation until completion, then downloads and returns the video as a FileDownloadable with public URL.1 params
Polls a Veo video generation operation until completion, then downloads and returns the video as a FileDownloadable with public URL.
operation_namestringSponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
MCP Gemini CrunchTools
A secure MCP (Model Context Protocol) server for Google Gemini AI - text, image, video, research, and more.
Overview
This MCP server is designed to be:
- Secure by default - STRIDE threat model (see SECURITY.md), Pydantic input validation, and the API key held as a
SecretStrto prevent accidental logging - No third-party services - Runs locally via stdio, your API key never leaves your machine
- Cross-platform - Works on Linux, macOS, and Windows
- Automatically updated - GitHub Actions monitor for CVEs and update dependencies
- Containerized - Available at
quay.io/crunchtools/mcp-geminibuilt on Hummingbird Python base image
Naming Convention
| Component | Name |
|---|---|
| GitHub repo | crunchtools/mcp-gemini |
| Container | quay.io/crunchtools/mcp-gemini |
| Python package (PyPI) | mcp-gemini-crunchtools |
| CLI command | mcp-gemini-crunchtools |
| Module import | mcp_gemini_crunchtools |
Why Hummingbird?
Details
- Repository
- github.com/crunchtools/mcp-gemini
- Categories
- AI & LLM Tools, Media & Entertainment
- Package
mcp-gemini-crunchtools- Transport
- STDIO
- Registry
- MCP registry, active
More from crunchtools
Related AI & LLM Tools MCP servers
View all
Colour Memorydigbyo/colour-memory-apiColour meaning, history and evidence for AI: 45,000+ source-graded colour records and 91 tools.0stars
Forex-GPT MCP Serverio.github.hatgit/forex-gpt-mcpAI-powered forex and crypto trading analysis with real-time data across 127+ instruments.0stars
Djd Agent Scorejacobsd32-cpu/djd-agent-score-mcpReputation scoring for AI agent wallets on Base. Trust scores, fraud checks, x402.0stars
Agent Loop Detectorlazymac2x/agent-loop-detector-apiCloudflare Workers MCP server: agent-loop-detector0starsAgent Trace Auditorlazymac2x/agent-trace-auditor-apiCloudflare Workers MCP server: agent-trace-auditor0starsAgent Workflow Enginelazymac2x/agent-workflow-engine-apiCloudflare Workers MCP server: agent-workflow-engine0stars