Deepy MCP Server
Thin MCP server that enables AI agents to generate video, image, and audio content via the Deepy API using a personal API key, with safe generation flow and no business logic.
README
@deepy/mcp-server
Thin MCP server that lets external AI agents (Cursor, Claude Desktop, Claude Code, Windsurf, …) drive Deepy generation of video / image / audio over the public Deepy API using a personal API key.
It carries no business logic — billing, moderation, idempotency, rate limits, provider access and ownership checks all stay in the Deepy backend, which is the source of truth. This server is only a safe adapter that exposes Deepy as MCP tools, prompts and resources.
1. Requirements
- Node.js 22+ (the connector runs on your machine).
- A Deepy API key — create one in the Deepy web app under API access.
It is shown only once and looks like
sk_live_…(orsk_test_…).
2. Install & configure
Point your MCP client at the connector and give it two environment values:
| Variable | Value |
|---|---|
DEEPY_API_BASE_URL |
Deepy API base URL, no trailing slash, e.g. https://app.prod.einfra.tech |
DEEPY_API_KEY |
your personal key (sk_live_…) — only from config/env, never chat |
DEEPY_LOG_LEVEL |
optional: debug|info|warn|error|silent (default info) |
Option A — run straight from GitHub (works today, no npm needed)
npx clones this repo, installs its dependencies and runs the committed build —
no npm publish required.
Cursor — put this in ~/.cursor/mcp.json (all projects) or
.cursor/mcp.json (one project):
{
"mcpServers": {
"deepy": {
"command": "npx",
"args": ["-y", "github:deepy-to/deepy-mcp-server"],
"env": {
"DEEPY_API_BASE_URL": "https://app.prod.einfra.tech",
"DEEPY_API_KEY": "sk_live_your_key_here"
}
}
}
}
Claude Desktop — same block in claude_desktop_config.json, then restart
Claude Desktop. Ready-made copies live in mcp-configs/.
Option B — npm (once published)
When @deepy/mcp-server is published to npm, the args simplify to
["-y", "@deepy/mcp-server"].
Option C — local copy (offline / development)
Clone this repo (git clone https://github.com/deepy-to/deepy-mcp-server), run
npm install, then point the config at the built entrypoint:
{
"mcpServers": {
"deepy": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/deepy-mcp-server/dist/index.js"],
"env": {
"DEEPY_API_BASE_URL": "https://app.prod.einfra.tech",
"DEEPY_API_KEY": "sk_live_your_key_here"
}
}
}
}
3. Tools
| Tool | Purpose | Backend |
|---|---|---|
deepy_list_models |
list available models | GET /api/v1/public/models |
deepy_get_model |
model schema / options | GET /api/v1/public/models/{name} |
deepy_improve_prompt |
rewrite a draft prompt | POST /api/v1/public/improve-prompt |
deepy_estimate_generation |
price a generation (no charge) | POST /api/v1/public/generations/estimate |
deepy_create_generation |
start a generation (requires confirmed=true) |
POST /api/v1/public/generations |
deepy_get_generation |
poll status | GET /api/v1/public/generations/{id} |
deepy_get_result |
fetch result media (server-side) | GET /api/v1/public/generations/{id}/results/{i} |
The server also ships MCP prompts and resources (skills) that teach an agent the safe generation flow.
4. Safe generation flow
- Understand the task (ask 1–2 clarifying questions if unclear).
- Pick a model (
deepy_list_models/deepy_get_model). - Improve the prompt (
deepy_improve_prompt). - Estimate the cost (
deepy_estimate_generation). - Show the price and get explicit user approval.
- Only then
deepy_create_generationwithconfirmed=true. - Poll
deepy_get_generation, then fetchdeepy_get_result.
deepy_create_generation refuses to run without confirmed=true, generates
an idempotency key when none is given, and never retries a paid create.
5. Security
- The API key is read only from
DEEPY_API_KEY(config/env), never from tool arguments or chat text, and is redacted from every log line. - The server never talks to WaveSpeed/RunPod, the database or S3 directly, and never returns private provider/S3 URLs.
- The backend remains authoritative for moderation, billing, rate limits and
ownership. On
INSUFFICIENT_CREDITStop up; onCONTENT_REJECTEDthe content broke the rules; onMODEL_NOT_FOUNDre-list the catalog; onIDEMPOTENCY_CONFLICTdo not auto-retry.
6. Troubleshooting
| Symptom | Fix |
|---|---|
| No Deepy tools appear | Node.js installed? config saved in the right file? client fully restarted? |
Unauthorized |
key missing/mistyped/disabled — reissue it on API access |
Insufficient balance |
top up the balance and retry |
Model not found |
list models and pick one from the catalog |
7. Development
npm install
npm run build # tsc -> dist/
npm test # vitest (safety-critical behaviour)
npm run dev # tsx src/index.ts
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。