Media Toolkit MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PEXELS_API_KEY | No | Pexels API key for stock photo search. Required only for search_stock_media tool. Free at https://www.pexels.com/api/ | |
| IMAGE_OUTPUT_DIR | No | Directory to save output images | ./output |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| remove_backgroundA | Remove the background from an image using AI (rembg). Works locally — no cloud API needed. The model (~170MB) is downloaded automatically on first use. |
| search_stock_mediaA | Search free stock photos via the Pexels API. Returns image URLs with photographer credits. Requires PEXELS_API_KEY env var (free at pexels.com/api). |
| resize_imageA | Resize or crop an image to specific dimensions. Supports three modes: fit (preserve aspect ratio, fit within bounds), fill (preserve aspect ratio, cover bounds), crop (center crop to exact size). Works locally with Pillow. |
| convert_formatC | Convert an image between formats: PNG, JPG, WebP, or SVG to PNG. Works locally with Pillow. Note: SVG input is rasterized to PNG via cairosvg if available, otherwise Pillow. |
| create_collageB | Arrange multiple images into a grid collage. Images are resized to fit uniformly. Works locally with Pillow. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: format conversion, collage creation, background removal, resizing, and stock photo search. There is no ambiguity or overlap among them.
All tool names follow the consistent verb_noun pattern (e.g., convert_format, create_collage, remove_background) with underscores, making them predictable and easy to understand.
With 5 tools, the set is well-scoped for a media toolkit. It covers essential image operations without being excessive or too sparse.
The toolkit covers common image tasks like conversion, collage, background removal, resizing, and stock search. However, missing operations like filtering, text overlay, or rotation represent minor gaps that agents may need to work around.