Schema | gemini-vision-mcp-safe

gemini-vision-mcp-safe

Describes the environment variables required to run the server.

Name	Required	Description	Default
`HTTP_PROXY`	No	HTTP proxy URL.
`HTTPS_PROXY`	No	HTTPS proxy URL (e.g., http://127.0.0.1:7890).
`GEMINI_API_KEY`	Yes	Your key from Google AI Studio.
`GEMINI_VISION_MODEL`	No	Default model for vision requests.	gemini-2.5-flash
`GEMINI_VISION_ALLOW_URL`	No	Allow URL inputs.	true
`GEMINI_VISION_MAX_IMAGE_MB`	No	Maximum image size in MB.	10
`GEMINI_VISION_ALLOW_LOCAL_FILE`	No	Allow local file inputs.	true
`GEMINI_VISION_BLOCK_LOCAL_URLS`	No	Block private/loopback IPs for URLs.	true
`GEMINI_VISION_GEMINI_TIMEOUT_MS`	No	Timeout for Gemini API call in milliseconds.	60000
`GEMINI_VISION_REQUEST_TIMEOUT_MS`	No	Timeout for URL fetch in milliseconds.	20000

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
analyze_image_with_geminiA	Analyze a local image file or image URL using Google Gemini Vision. PRIVACY RULES: Use this tool ONLY when the current main model cannot natively understand images. If the current main model has native vision capability, do NOT use this tool unless the user explicitly asks to use Gemini. Before calling this tool with confirm_send_to_gemini=true, you MUST ask the user for consent. The image bytes and prompt will be sent to Google Gemini API. If image_source is a URL, this MCP downloads the image from your machine first, then sends bytes to Gemini. If the user has not explicitly agreed, omit confirm_send_to_gemini or set it to false to show a confirmation notice only. Supported inputs: Local file path, e.g. C:/Users/me/Desktop/image.png HTTP/HTTPS image URL, e.g. https://example.com/image.png
analyze_images_batchA	Batch analyze multiple images (2-5) using Google Gemini Vision. Same privacy rules as analyze_image_with_gemini apply. Useful for comparing screenshots, before/after views, or multi-page documents. Supported inputs: local file paths or HTTP/HTTPS image URLs (can mix).

Name

Description

Analyze a local image file or image URL using Google Gemini Vision.

PRIVACY RULES:

Use this tool ONLY when the current main model cannot natively understand images.
If the current main model has native vision capability, do NOT use this tool unless the user explicitly asks to use Gemini.
Before calling this tool with confirm_send_to_gemini=true, you MUST ask the user for consent.
The image bytes and prompt will be sent to Google Gemini API.
If image_source is a URL, this MCP downloads the image from your machine first, then sends bytes to Gemini.
If the user has not explicitly agreed, omit confirm_send_to_gemini or set it to false to show a confirmation notice only.

Supported inputs:

Batch analyze multiple images (2-5) using Google Gemini Vision.

Same privacy rules as analyze_image_with_gemini apply. Useful for comparing screenshots, before/after views, or multi-page documents.

Supported inputs: local file paths or HTTP/HTTPS image URLs (can mix).

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources