MCP server for image analysis using GPT-4o-mini
Connect Image Gemini to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server for image analysis using GPT-4o-mini. The image gemini mcp server is what makes that connection.
An MCP server that receives image/video URLs or local file paths and analyzes their content using the Gemini 2.0 Flash model.(forked from github.com/champierre/image-mcp-server)
@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
analyze_image — Receives one or more image URLs and analyzes their contentArguments — imageUrls (array of strings, required), prompt (string, optional)analyze_image_from_path — Receives one or more local image file paths and analyzes their contentanalyze_video — Receives one or more video URLs and analyzes their content. Best for smaller videos (see Video Notes)analyze_video_from_path — Receives one or more local video file paths and analyzes their content. Best for smaller videos (see Video Notes)analyze_youtube_video — Receives a single YouTube video URL and analyzes its contentConfiguration is passed through the environment: GEMINI_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Image Gemini's toolset — analyze_image, Arguments, analyze_image_from_path and 3 more — is a fair guide to whether it matches your workflow. It is maintained by rentapad; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| analyze_image | Receives one or more image URLs and analyzes their content. |
| Arguments | imageUrls (array of strings, required), prompt (string, optional). |
| analyze_image_from_path | Receives one or more local image file paths and analyzes their content. |
| analyze_video | Receives one or more video URLs and analyzes their content. Best for smaller videos (see Video Notes). |
| analyze_video_from_path | Receives one or more local video file paths and analyzes their content. Best for smaller videos (see Video Notes). |
| analyze_youtube_video | Receives a single YouTube video URL and analyzes its content. |
{
"mcpServers": {
"image-mcp-server-gemini": {
"command": "npx",
"args": ["-y", "@smithery/cli"],
"env": {
"GEMINI_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| GEMINI_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.