Deepy MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEEPY_API_KEY | Yes | Your personal Deepy API key (sk_live_...) | |
| DEEPY_LOG_LEVEL | No | Log level: debug|info|warn|error|silent | info |
| DEEPY_API_BASE_URL | Yes | Deepy API base URL, no trailing slash | |
| DEEPY_MAX_RESULT_MB | No | Runaway-body guard for downloads, in MiB | 2048 |
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
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| deepy_list_modelsA | List the AI models available to your Deepy API key (only opened/available models are returned). Returns every matching model grouped by generation type; |
| deepy_get_modelA | Fetch the full schema for one model: its parameters, reference-file limits, generation type, and max prompt length. A closed or unknown model returns MODEL_NOT_FOUND (closed models are never revealed). |
| deepy_improve_promptA | Rewrite a draft prompt into a stronger one for the given modality (image/video/audio). Returns the improved prompt text to use as the base in estimate/create — review it first, the rewriter can invent style references that do not exist. |
| deepy_upload_fileA | Upload an image, video, or audio attachment (up to 50 MiB) to Deepy and return its fileId. For files attached directly to the agent window, pass their absolute local path as filePath. Call this before estimate/create and pass the returned id in referenceFiles. |
| deepy_estimate_generationA | Get the integer token cost and resulting balance for a generation, without charging anything. Always estimate and confirm with the user before creating. The exact same params must be passed to deepy_create_generation (quote == charge). |
| deepy_create_generationA | Start a PAID generation. Requires confirmed=true — the tool refuses otherwise and contacts no backend. Params must be byte-identical to the estimate (quote == charge). An X-Idempotency-Key is auto-generated to prevent double-charging. |
| deepy_get_generationA | Fetch a generation's current status, error info, and result indexes by publicId. Poll this after create until status is COMPLETED or FAILED. |
| deepy_get_resultA | Fetch a COMPLETED generation's result media. The server fetches the bytes with its own API key, saves the full-resolution file locally on the user's device and returns its path, and inlines small images/audio (base64) so they render in-chat. Videos and large media are streamed straight to the saved local file (never inlined as base64), so there is no practical size limit. Never exposes the API key or a raw URL. |
| deepy_open_topup_pageA | Open the Deepy credits top-up page in the user's default browser and return its URL. Call this when a balance is too low to cover a generation (deepy_estimate_generation returned canAfford=false, or a create failed with INSUFFICIENT_CREDITS) and the user wants to add credits. Opens a page only — it never moves money or charges anything. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| deepy_safe_generation_flow | The end-to-end, confirmation-gated flow for creating a Deepy generation. |
| deepy_choose_model | Help select an available Deepy model for a task/modality. |
| deepy_prompt_optimizer | Improve a draft prompt for a given modality. |
| deepy_troubleshooting | Explain a Deepy error code and the correct next step. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| deepy-skill-model-selection | Guidance for the Deepy safe generation flow (model-selection). Hint only — the backend enforces the real rules. |
| deepy-skill-prompt-optimization | Guidance for the Deepy safe generation flow (prompt-optimization). Hint only — the backend enforces the real rules. |
| deepy-skill-safe-generation-flow | Guidance for the Deepy safe generation flow (safe-generation-flow). Hint only — the backend enforces the real rules. |
| deepy-skill-cost-confirmation | Guidance for the Deepy safe generation flow (cost-confirmation). Hint only — the backend enforces the real rules. |
TDQS
Scored across 9 tools
Each tool targets a distinct step in the AI generation workflow: model discovery, schema lookup, prompt refinement, file upload, cost estimation, paid creation, status polling, result retrieval, and top-up navigation. There is no overlap or ambiguity between them.
All tool names share the 'deepy_' prefix and follow a consistent verb_noun pattern (list_models, get_model, improve_prompt, upload_file, estimate_generation, create_generation, get_generation, get_result, open_topup_page). The naming is uniform and predictable.
With 9 tools, the server is well-scoped for the domain of AI media generation. Each tool covers a necessary step in the process, and the count feels neither excessive nor sparse.
The toolset covers the full generation lifecycle: model exploration, prompt enhancement, file upload, cost estimation, creation, status tracking, result retrieval, and credit top-up. No critical operations are missing for the stated purpose.