media-gen-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | Google Gemini API key for Veo video generation (optional). | |
| GOOGLE_API_KEY | No | Google API key for Gemini/Veo (optional). | |
| OPENAI_API_KEY | No | OpenAI API key for image and video generation. | |
| OPENAI_API_VERSION | No | OpenAI API version (optional, default: 2024-12-01-preview). | |
| AZURE_OPENAI_API_KEY | No | Azure OpenAI API key (alternative to OpenAI API key). | |
| AZURE_OPENAI_ENDPOINT | No | Azure OpenAI endpoint. |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| openai-images-generateC | Generate images from text prompts using OpenAI gpt-image-1.5 (default) or gpt-image-1. Returns MCP CallToolResult with content[] (ResourceLink or ImageContent based on tool_result param) and structuredContent (OpenAI ImagesResponse format with data[].url, data[].path, or data[].b64_json based on response_format param). |
| openai-images-editA | Edit images (inpainting, outpainting, compositing) from 1 to 16 inputs using OpenAI gpt-image-1.5 (default) or gpt-image-1. Returns MCP CallToolResult with content[] (ResourceLink or ImageContent based on tool_result param) and structuredContent (OpenAI ImagesResponse format with data[].url, data[].path, or data[].b64_json based on response_format param). |
| openai-videos-createB | Create a video generation job using the OpenAI Videos API. Returns structuredContent with the OpenAI Video job object, and (optionally) downloaded assets as MCP content blocks (tool_result=resource_link|resource). |
| openai-videos-remixB | Create a remix video job from an existing video_id. Returns structuredContent with the OpenAI Video job object, and (optionally) downloaded assets as MCP content blocks (tool_result=resource_link|resource). |
| openai-videos-listB | List video jobs using the OpenAI Videos API. Returns structuredContent with the OpenAI list response shape { data, has_more, last_id }. |
| openai-videos-retrieveA | Retrieve a video job by id using the OpenAI Videos API. |
| openai-videos-deleteC | Delete a video job by id using the OpenAI Videos API. |
| openai-videos-retrieve-contentA | Retrieve a video asset (video/thumbnail/spritesheet) for a completed job, write it under MEDIA_GEN_DIRS, and return content blocks (tool_result=resource_link|resource). |
| google-videos-generateB | Generate videos using Google GenAI (Veo). Can optionally wait for completion and download generated videos to MEDIA_GEN_DIRS. |
| google-videos-retrieve-operationA | Retrieve the status/result of a Google video generation operation (response_format=url|b64_json controls uri vs videoBytes in structuredContent). |
| google-videos-retrieve-contentA | Download generated video content for a completed Google video operation, write it under MEDIA_GEN_DIRS, and return content blocks (tool_result=resource_link|resource). |
| fetch-imagesA | Fetch and process images from URLs or local file paths. Returns MCP CallToolResult with content[] (ResourceLink or ImageContent based on tool_result param) and structuredContent (OpenAI ImagesResponse format with data[].url, data[].path, or data[].b64_json based on response_format param). |
| fetch-videosB | Fetch videos from URLs or local file paths. Returns MCP CallToolResult with content blocks (tool_result=resource_link|resource) and structuredContent listing resolved files/URLs. |
| fetch-documentB | Fetch documents from URLs or local file paths. Downloads remote URLs into MEDIA_GEN_DIRS and returns MCP content blocks as resource_link (default) or embedded resource. |
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 14 tools
Tools are clearly grouped by provider and media type (fetch, google-videos, openai-images, openai-videos). Each tool serves a distinct purpose: fetching existing content, generating/editing images, or creating/managing videos. No significant overlap in functionality.
Most tools follow a consistent {provider}-{mediaType}-{action} pattern (e.g., openai-images-generate, google-videos-retrieve-operation). The generic fetch tools (fetch-document, fetch-images, fetch-videos) break the pattern slightly but are still clear and predictable.
14 tools is well-scoped for a media generation server. It covers fetching, image generation/editing, and video creation/management without being overwhelming. Each tool has a clear role.
The tool surface covers core media operations: fetch, generate, edit images, and create/retrieve/delete videos from OpenAI. Minor gaps include lack of Google video job listing/deletion and no image generation from other providers, but the domain is competently covered.