Media-infrastructure
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VAP_API_KEY | Yes | Your VAP API key, obtained by creating an agent at vapagent.com. This key is used to authenticate requests for AI image, video, and music generation. |
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 | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageA | Generate an AI image from text prompt using VAP (Flux2 Pro). Returns a task ID for async tracking. Cost: $0.18 |
| get_taskA | Get the status and result of a generation task. Returns image URL when completed. |
| list_tasksC | List recent generation tasks with optional status filter. |
| check_balanceA | Check VAP account balance. Returns available, reserved, and usable balances. |
| estimate_costB | Estimate the cost of an image generation before executing. Cost: $0.18 |
| generate_videoA | Generate an AI video from text prompt using VAP (Veo 3.1). Returns a task ID for async tracking. Cost: $1.96. IMPORTANT: Send ONLY the video description. Do NOT include any instructions, guidelines, or meta-text. Just the pure visual description. |
| estimate_video_costC | Estimate the cost of a video generation. Cost: $1.96 (Veo 3.1) |
| generate_musicA | Generate AI music from text description using VAP (Suno V5). Returns a task ID for async tracking. Cost: $0.68. IMPORTANT: Send ONLY the music description. Do NOT include any instructions or meta-text. Describe: genre, mood, instruments, tempo, vocal style (or specify instrumental). Example prompt: "Upbeat indie folk song with acoustic guitar, warm vocals, and light percussion. Feel-good summer vibes. |
| estimate_music_costC | Estimate the cost of music generation. Cost: $0.68 (Suno V5) |
| inpaintA | Remove or replace objects in an image using AI inpainting. Cost: $0.15. Requires Tier 1+. |
| ai_editA | Edit images using AI with natural language prompts. Supports single and multi-image editing. Cost: $0.15. Requires Tier 1+. |
| background_removeA | Remove the background from an image, leaving only the subject with transparency. Cost: $0.10. Requires Tier 1+. |
| upscaleB | Upscale/enhance an image to higher resolution using AI. Cost: $0.15. Requires Tier 1+. |
| video_trimC | Trim a video to a specific time range. Cost: $0.05. Requires Tier 1+. |
| video_mergeA | Merge multiple video clips into one continuous video. Cost: $0.05. Requires Tier 1+. |
| get_operationB | Get the status and result of an operation. Returns output URL when completed. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Account Information | Current account details, tier, and limits |
| Account Balance | Current balance breakdown |
| Current Pricing | Current pricing for all operations |
| Recent Tasks | Last 10 tasks |
TDQS
Scored across 16 tools
Most tools have distinct purposes, but there is notable overlap between get_operation and get_task, which both retrieve task/operation statuses, potentially causing confusion. Additionally, the three estimate_* tools are clearly differentiated by media type, but their naming and purpose similarity could lead to misselection if not carefully read.
The naming is mostly consistent with a verb_noun pattern (e.g., generate_image, check_balance, list_tasks), but there are minor deviations like ai_edit (noun_verb) and background_remove (noun_verb). These inconsistencies are few and do not severely impact readability, but they break the overall pattern.
With 16 tools, the count is reasonable for a media infrastructure server covering image, video, and music generation and editing, plus account management. It is slightly on the higher side but well within a manageable scope, as each tool serves a specific function in the domain.
The tool set provides good coverage for media generation and editing, including CRUD-like operations (generate, edit, upscale, list, get status) and cost estimation. However, there are minor gaps, such as no explicit tool for deleting tasks or managing media assets beyond generation and editing, which agents might need to work around.