MCP.Market

MCP Gemini MCP server

by crunchtools·io.github.crunchtools/gemini·v0.3.0
No reviews yet

MCP server for Google Gemini AI - text, image, video, research, and more

A91/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A91/100

full report

Adoption
New

0 stars16 downloads/wk

Reviews

Write one

Nobody has reviewed MCP Gemini yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

MCP Gemini tools (39, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • gemini_analyze_code_tool

    Analyze code with Gemini.

  • gemini_analyze_document_tool

    Analyze a document (PDF, DOCX, TXT, etc.).

  • gemini_analyze_image_tool

    Analyze and describe a local image file.

  • gemini_analyze_text_tool

    Analyze text with Gemini.

  • gemini_analyze_url_tool

    Analyze one or more URLs.

  • gemini_brainstorm_tool

    Brainstorm ideas on a topic using Gemini.

  • gemini_check_research_tool

    Check the status of a deep research operation.

  • gemini_check_video_tool

    Check the status of a video generation operation.

  • gemini_compare_urls_tool

    Compare two URLs.

  • gemini_continue_image_edit_tool

    Continue editing in an active image session.

  • gemini_count_tokens_tool

    Count the number of tokens in content.

  • gemini_create_cache_toolwrite action

    Create a content cache for repeated queries.

  • gemini_deep_research_tool

    Start a deep research task using a specialized Gemini model.

  • gemini_delete_cache_toolwrite action

    Delete a content cache.

  • gemini_dialogue_tool

    Generate multi-voice dialogue audio.

  • gemini_end_image_edit_tool

    End an image editing session and free resources.

  • gemini_extract_from_url_tool

    Extract specific data from a URL.

  • gemini_extract_tables_tool

    Extract tables from a document.

  • gemini_extract_tool

    Extract structured data from text.

  • gemini_generate_image_tool

    Generate an image from a text prompt using Gemini's native image model.

  • gemini_generate_image_with_input_tool

    Generate/edit an image using a local image file as input.

  • gemini_generate_video_tool

    Generate a video using Veo. Returns an operation ID to poll.

  • gemini_image_prompt_tool

    Help craft an effective image generation prompt.

  • gemini_imagen_generate_tool

    Generate images using Google Imagen 4 models.

  • gemini_list_caches_tool

    List all active content caches.

  • gemini_list_image_sessions_tool

    List all active image editing sessions.

  • gemini_list_voices_tool

    List available voices for text-to-speech.

  • gemini_query_cache_tool

    Query content in a cache.

  • gemini_query_tool

    Query Gemini with a prompt. Supports Google Search grounding.

  • gemini_research_followup_tool

    Ask a follow-up question about completed research.

  • gemini_run_code_toolwrite action

    Execute code using Gemini's built-in code execution.

  • gemini_search_tool

    Search the web using Gemini with Google Search grounding.

  • gemini_speak_tool

    Convert text to speech.

  • gemini_start_image_edit_tool

    Start a multi-turn image editing session.

  • gemini_structured_tool

    Get structured JSON output from Gemini.

  • gemini_summarize_pdf_tool

    Summarize a PDF document.

  • gemini_summarize_tool

    Summarize content with Gemini.

  • gemini_youtube_summary_tool

    Summarize a YouTube video.

  • gemini_youtube_tool

    Analyze a YouTube video.

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

no findings
  • Code scan29 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How MCP Gemini compares

Against every graded Media MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 83% of 1,337 Media servers
Tools
39
the typical Media server has 7
Tools that change things
8%
typical: 4%. Fewer write tools means less an agent can break
Downloads a week
16
more than 5% of 365 Media servers with a package

What its tools let an agent do: 36 read · 3 change

Install MCP Gemini in Claude Code, Cursor or VS Code

claude mcp add gemini -- uvx mcp-gemini-crunchtools
Add to Cursor

What the publisher says

From the MCP Gemini repository's README, as published. We do not edit it. Read it on GitHub

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 SecretStr to 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-gemini built on Hummingbird Python base image

Naming Convention

Why Hummingbird?

The container image is built on the Hummingbird Python base image from Project Hummingbird, which provides:

  • Minimal CVE exposure - Hummingbird images are built with a minimal package set, dramatically reducing the attack surface compared to general-purpose images
  • Regular updates - Security patches are applied promptly, keeping CVE counts low
  • Optimized for Python - Pre-configured Python environment with uv package manager for fast, reproducible builds
  • Production-ready - Designed for production workloads with proper signal handling and non-root user defaults

This means your MCP server runs in a hardened environment with fewer vulnerabilities than typical Python container images.

Features

Query Tools (5 tools)

  • gemini_query - Query Gemini with optional Google Search grounding
  • gemini_brainstorm - Generate creative ideas on a topic
  • geminianalyzecode - Analyze code for security, performance, bugs
  • geminianalyzetext - Analyze text for sentiment, tone, content
  • gemini_summarize - Summarize content in various formats

Image Generation (4 tools)

  • geminigenerateimage - Generate images from text prompts (native Gemini)
  • geminigenerateimagewithinput - Edit/modify existing images
  • geminiimageprompt - Craft effective image generation prompts
  • geminiimagengenerate - Generate images using Google Imagen 4 models

Image Editing (4 tools)

  • geministartimage_edit - Start a multi-turn image editing session
  • geminicontinueimage_edit - Continue editing in an active session
  • geminiendimage_edit - End an image editing session
  • geminilistimage_sessions - List all active editing sessions

Image Analysis (1 tool)

  • geminianalyzeimage - Analyze and describe local image files

Search Tools (1 tool)

  • gemini_search - Web search using Gemini with Google Search grounding

Document Tools (3 tools)

  • geminianalyzedocument - Analyze PDFs, DOCX, TXT, etc.
  • geminisummarizepdf - Summarize PDF documents
  • geminiextracttables - Extract tables from documents

URL Tools (3 tools)

  • geminianalyzeurl - Analyze one or more URLs
  • geminicompareurls - Compare two URLs
  • geminiextractfrom_url - Extract specific data from a URL

Video Tools (2 tools)

  • geminigeneratevideo - Generate videos using Veo
  • geminicheckvideo - Check video generation status

YouTube Tools (2 tools)

  • gemini_youtube - Analyze YouTube videos
  • geminiyoutubesummary - Summarize YouTube videos

Voice Tools (3 tools)

  • gemini_speak - Convert text to speech
  • gemini_dialogue - Generate multi-voice dialogue audio
  • geminilistvoices - List available voices

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

MCP Gemini: common questions

Is MCP Gemini MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the MCP Gemini safety report
How do I install MCP Gemini?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does MCP Gemini need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is MCP Gemini maintained?
The last commit was 39 days ago (2026-09-26). The latest release is v0.3.0.
What can I use instead of MCP Gemini?
Servers from other publishers that do the same job: PopNow MCP server, Remove AI Watermarks MCP server and Transloadit Media Processing MCP server.
How does MCP Gemini compare with other Media MCP servers?
safety score 91/100 (higher than 83% of 1,337 Media servers); tools 39 (the typical Media server has 7); tools that change things 8% (typical: 4%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to MCP Gemini

Same job from other publishers: the closest match first, then the best rated.

  • PopNow
    AI image, video, music and speech generation: text-to-video, image-to-video, effects and upscaling.
    A
  • Remove AI Watermarks
    Identify and remove AI watermarks and provenance metadata from your own images and video.
    A
  • Transloadit Media Processing
    Process video, audio, images and documents with Transloadit Robots. Connect by URL with OAuth.
    A
  • SuperCMO
    Marketing media generation — image, video, voice — for AI agents. BYO keys.
    B
  • anymd
    Any file → clean Markdown for AI agents: PDF, Office, EPUB, HTML, images, audio/video. Local MCP.
    A

More from crunchtools →