cerebro
Pay-per-call ($0.25 USDC) project cost estimator: modules + cheapest model mix that clears quality.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~176Token（工具定義）
~1.0 KB典型回應大小
極小的注意力影響（128k 上下文的 0.14%）
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"cerebro": {
"url": "https://cerebro-mcp-production-98cc.up.railway.app/mcp"
}
}
}遠端端點
https://cerebro-mcp-production-98cc.up.railway.app/mcpstreamable-http它能做什麼
工具清單
工具（1）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
⚪estimate_project_cost(project_description, architecture_template)
Break a software project description into modules and return a real dollar cost estimate per module: the cheapest model that clears a complexity-scaled quality bar for each one, plus the whole-project cost under every candidate model for comparison. architecture_template must be one of minimalista, clasica, state_of_the_art, hiperescalable, or left blank to auto-suggest one from the description. Requires x402 payment ($0.25 USDC on Base).
輸入結構描述
{
"type": "object",
"properties": {
"project_description": {
"title": "Project Description",
"type": "string"
},
"architecture_template": {
"default": "",
"title": "Architecture Template",
"type": "string"
}
},
"required": [
"project_description"
],
"title": "estimate_project_costArguments"
}輸出結構描述
{
"type": "object",
"additionalProperties": true,
"title": "estimate_project_costDictOutput"
}社群
證據
近期觀測
已驗證未記錄版本1 個工具
已驗證未記錄版本1 個工具
已驗證未記錄版本1 個工具