Eveoy
vlatest
MCP Serversmithery858
io.smithery.eveoy.mcp
io.smithery.beforeyouship.cost-model · vlatest
Model the realistic monthly cost of an LLM app **before you build it**. Not a token calculator: retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth are modeled in, across GPT-5.x, Claude, Gemini, DeepSeek, and more. **Works without a key.** Connect and ask — demo mode covers the six free-tier models. A Pro API key ([beforeyouship.dev](https://beforeyouship.dev)) unlocks the full 18-model catalog. ## Tools | Tool | What it does | |---|---| - **`estimate_cost`** Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case $/mo per model, growth scenarios, and an opinionated recommendation. | - **`get_model_prices`** Current per-1M-token pricing (input, output, cached, batch) with context windows and staleness metadata. | - **`list_archetypes`** Seven preset architecture patterns (chatbot, RAG pipeline, multi-step agent, …) used as starting points for estimates. | ## Try it Paste into Claude Code or Cursor after connecting: > Estimate the monthl
热度数据
//beforeyouship — LLM cost modeling from your editor 是一个MCP Server，收录自 smithery。支持 streamable-http 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。
选择你的平台查看安装方式
{
"mcpServers": {
"io-smithery-beforeyouship-cost-model": {
"url": "https://smithery.ai/servers/beforeyouship/cost-model"
}
}
}**Eveoy brings real customers into real stores** — you pay $24.99 only after a real person walks in, spends 10+ minutes, makes a purchase, and brings back ~2 on-brand UGC photos. No-shows are refunded, every time. No clicks, no bots, no influencers. This server is your **Eveoy expert associate** inside any AI — here to help and educate, not to sell. Ask how Eveoy works, get an exact quote, save the brand you represent, and (when you're ready) place an order for verified in-store visits — all anonymously, no sign-in. Pricing: Starter $999 (40 customers), Proof $2,499 (100), Rollout $9,996 (400+).
{
"id": "io.smithery.beforeyouship.cost-model",
"type": "mcp-server",
"version": "latest",
"displayName": "//beforeyouship — LLM cost modeling from your editor",
"description": "Model the realistic monthly cost of an LLM app **before you build it**. Not a token calculator: retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth are modeled in, across GPT-5.x, Claude, Gemini, DeepSeek, and more.\n\n**Works without a key.** Connect and ask — demo mode covers the six free-tier models. A Pro API key ([beforeyouship.dev](https://beforeyouship.dev)) unlocks the full 18-model catalog.\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n- **`estimate_cost`** Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case $/mo per model, growth scenarios, and an opinionated recommendation. |\n- **`get_model_prices`** Current per-1M-token pricing (input, output, cached, batch) with context windows and staleness metadata. |\n- **`list_archetypes`** Seven preset architecture patterns (chatbot, RAG pipeline, multi-step agent, …) used as starting points for estimates. |\n\n## Try it\n\nPaste into Claude Code or Cursor after connecting:\n\n> Estimate the monthl",
"iconUrl": "https://api.smithery.ai/servers/beforeyouship/cost-model/icon",
"homepage": "https://beforeyouship.dev/docs#mcp",
"distribution": {
"packages": [],
"remotes": [
{
"transport": "streamable-http",
"url": "https://smithery.ai/servers/beforeyouship/cost-model"
}
]
},
"dependencies": [],
"installTargets": [
"claude-code",
"claude-desktop",
"cursor",
"vscode"
],
"keywords": [
"use_count:2993",
"remote"
],
"provenance": {
"origin": "smithery",
"originalId": "beforeyouship/cost-model",
"originalUrl": "https://smithery.ai/servers/beforeyouship/cost-model",
"isOfficial": false,
"status": "active"
}
}