Explain Image MCP Server
Allows AI agents to analyze images using Google's Gemini vision models, providing tools to describe images, extract text, or return structured data based on prompts.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Explain Image MCP Server Describe what's in this image: /screenshots/bug.png"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Explain Image MCP Server
A zero-dependency MCP (Model Context Protocol) server that lets any AI agent — including text-only models — "see" images.
The agent passes an image (local path, URL, or data URL) plus a prompt to the describe_image tool. The server forwards both to a Gemini vision model through the OpenAI-compatible REST endpoint and returns the model's text interpretation. Because the agent supplies the prompt, it controls exactly what the model returns: a description, OCR of visible text, an object list, structured JSON, and so on.
No external libraries are used — the MCP JSON-RPC protocol is implemented by hand over stdio, and the Gemini request is a plain fetch().
AI agent ── describe_image(image, prompt) ──► MCP server (stdio, JSON-RPC 2.0)
│
▼
POST /chat/completions (OpenAI-compatible)
│
▼
Gemini vision modelRequirements
Node.js >= 18.17 (global
fetchrequired)
Related MCP server: mcp-see
Configuration
Env var | Default | Description |
| (required) | Google AI Studio API key |
|
| Default model id; override per call with the |
|
| OpenAI-compatible base URL (swap to add another provider later) |
Install with an MCP client
san:
san mcp add -e GEMINI_API_KEY=your-key explain-image -- node /path/to/explain-image-mcp-server/src/index.jsClaude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"explain-image": {
"command": "node",
"args": ["/path/to/explain-image-mcp-server/src/index.js"],
"env": { "GEMINI_API_KEY": "your-key" }
}
}
}Tools
describe_image
Analyze one or more images with a Gemini vision model. The agent supplies the prompt.
Argument | Type | Required | Description |
| string | string[] | yes | Local file path, |
| string | no | What the model should return. Defaults to a detailed description |
| string | no | Gemini model id, overrides |
| integer | no | Maximum response length |
Example agent call:
describe_image(
image: "/screenshots/bug.png",
prompt: "Describe this UI bug precisely: what is shown, and what looks wrong?"
)list_models
List the model ids available on the configured OpenAI-compatible endpoint.
Default model & cost
The default is gemini-2.5-flash — a cost-efficient GA Flash model with image
input (Google pricing, July 2026): $0.30 / 1M input tokens, $2.50 / 1M output
tokens (vs $1.50 / $7.50 for gemini-3.6-flash). For 2.5 Flash/Flash-Lite
models the server sends reasoning_effort: "none", disabling thinking so no
output tokens are spent on reasoning. Set GEMINI_MODEL (or pass model per
call) to use a different model, e.g. gemini-3.6-flash for higher quality at a
higher price.
Development
npm test # end-to-end smoke test (protocol handshake + request formatting, no real key needed)The smoke test runs the full MCP handshake against a fake OpenAI-compatible upstream and validates the request shape (auth header, message body, base64 data URL) plus error paths.
Security note
The API key is stored in plaintext wherever the MCP client saves env vars. Keep it out of version control — .san/ is git-ignored in this repo for that reason.
Available Tools
2 toolsdescribe_imageA
Look at an image and return a text interpretation from the Gemini vision model. The calling agent supplies the prompt, so it controls exactly what the model should return (a description, OCR of visible text, a list of objects, structured JSON, etc.). Pass image as a local file path, an http(s) URL, or a data: URL (or an array of these for multiple images). This is how a text-only model can 'see' an image.
Inputs: image (required), model, prompt, max_tokens.
list_modelsA
List the Gemini model ids available on the configured OpenAI-compatible endpoint.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: describe_image processes images, while list_models enumerates available models. There is no overlap or ambiguity in their roles.
Both tools follow the identical verb_noun naming pattern (describe_image and list_models), creating a clear and predictable convention. This consistency makes the tool set easy to navigate.
With only 2 tools, the server is lean but appropriately scoped for its narrow purpose of explaining images. The core describe_image tool is supported by list_models, giving just enough functionality without bloat.
For the stated purpose of image explanation, the server fully covers the domain. describe_image is flexible via custom prompts, supporting descriptions, OCR, object listing, and more, with no obvious gaps for a single-purpose MCP server.
Maintenance
Related MCP Connectors
AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.
Analyze images and videos with Gemini to get fast, reliable visual insights. Handle content from U…
Image & PDF tools for AI agents: compress, convert, resize, PDF, AI vision, pipeline.
Run AI-powered analysis on images including moderation, captioning, tagging, and more.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables image analysis and understanding using Vision Language Models through OpenAI-compatible APIs. Supports analyzing images from URLs or local files with custom prompts.12MIT
- FlicenseAqualityNot gradedmaintenanceEnables AI agents to analyze images through vision AI providers (Gemini, OpenAI, Claude), performing tasks like image description, object detection with bounding boxes, region-specific analysis, and precise color extraction without consuming context window with raw pixels.4-
- AlicenseAqualityDmaintenanceEnables image analysis using any OpenAI-compatible vision API, supporting URLs, local files, or base64 input with custom prompts.1MIT
- AlicenseAqualityDmaintenanceEnables AI agents to analyze images, extract text, compare images, and analyze video through any OpenAI-compatible vision model.4488 npm20MIT