Image Search MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PEXELS_API_KEY | No | Your Pexels API key. At least one provider key is required. | |
| PIXABAY_API_KEY | No | Your Pixabay API key. At least one provider key is required. | |
| UNSPLASH_ACCESS_KEY | No | Your Unsplash access key. At least one provider key is required. | |
| IMAGE_SEARCH_MCP_ALLOWED_HOSTS | No | Comma-separated list of allowed hosts for optional transport security. | |
| IMAGE_SEARCH_MCP_ALLOWED_ORIGINS | No | Comma-separated list of allowed origins for optional transport security. |
Instructions
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.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_stock_imagesA | Search for royalty-free stock images across multiple providers. Args: query: Search query string providers: Providers to search. Valid values are pexels, unsplash, and pixabay. Names are case-insensitive. If a provider is requested but invalid or unavailable, the search returns an error instead of silently substituting. per_page: Number of results per page page: Page number for pagination sort_by: Sort order ('relevant', 'newest') include_attribution: Whether to include attribution links (defaults to value from ENABLE_ATTRIBUTION_LINKS env var) Returns: Search results with metadata |
| get_image_detailsA | Get detailed information about a specific image. Args: image_id: Provider-prefixed image ID (e.g., 'pexels_12345') include_attribution: Whether to include attribution links (defaults to value from ENABLE_ATTRIBUTION_LINKS env var) Returns: Detailed image information or None if not found |
| download_imageA | Download an image to local storage or return base64 encoded data. Args: image_id: Image ID in format provider_id (e.g., pexels_123456) size: Image size variant to download Options: thumbnail, small, medium, large, original output_path: Optional path to save the image locally. NOTE: If a relative path is provided, it will be resolved from the Image Search MCP server's current working directory, which may not be the project directory. To ensure the file is saved in a specific location, use an absolute path (e.g., /home/user/image-search-mcp/downloads/image.jpg). Returns: Path to downloaded file or base64 data Example: download_image("pexels_123456", size="medium", output_path="/absolute/path/to/save.jpg") |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| help_resource | Provide help documentation for the Image Search MCP server. |
TDQS
Scored across 3 tools
Each tool has a distinctly different purpose: searching for images, retrieving metadata for a specific image, and downloading an image. There is no overlap or ambiguity between them.
All tool names follow a consistent verb_noun pattern: search_stock_images, get_image_details, download_image. The naming is uniform and predictable.
Three tools is well-scoped for an image search server, covering the essential operations of discovery, inspection, and retrieval. Each tool earns its place in the set.
The tool surface covers the complete image search workflow: search, get details, and download. For the stated purpose of searching stock images, there are no obvious missing operations.