Skip to main content

將 OpenAI Responses API 連接到 aicharged.io

215 個工具，單一端點：https://aicharged.io/api/v1/mcp

OpenAI Responses API

OpenAI Responses API：代管的 mcp 工具——由 OpenAI 代你呼叫 aicharged.io；金鑰放入 authorization 欄位。

  • API 金鑰（Bearer）

代管的 MCP 工具——由 API 代你呼叫 aicharged.io

推薦 
import os
from openai import OpenAI

client = OpenAI()
response = client.responses.create(
    model="gpt-6-astra",
    input="List my recent aicharged.io runs",
    tools=[{
        "type": "mcp",
        "server_label": "aicharged",
        "server_url": "https://aicharged.io/api/v1/mcp",
        "authorization": os.environ["AICHARGED_API_KEY"],
        "require_approval": "never",
    }],
)
print(response.output_text)

OpenAI 絕不儲存 authorization 的值——請在每個請求中都傳送它。

用 curl 送出同樣的請求

curl https://api.openai.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-6-astra",
    "input": "List my recent aicharged.io runs",
    "tools": [{"type": "mcp", "server_label": "aicharged", "server_url": "https://aicharged.io/api/v1/mcp", "authorization": "<API_KEY>", "require_approval": "never"}]
  }'

或讓 CLI 進行設定

aicharged setup 會尋找此電腦上的 AI 用戶端，引導您透過瀏覽器登入，並寫入其設定檔。

一行指令輕鬆連接

安裝 CLI · macOS / Linux
curl -fsSL https://aicharged.io/install.sh | sh && aicharged setup
安裝 CLI · Windows
irm https://aicharged.io/install.ps1 | iex; aicharged setup
MCP 端點
https://aicharged.io/api/v1/mcp

可串流的 HTTP。傳送標頭 Authorization: Bearer <API_KEY>，或在您的用戶端支援時使用 OAuth 登入。

或告訴您的代理
閱讀 https://aicharged.io/agent.md，並幫我設定 aicharged.io

使用此提示詞開啟於 Claude (在新分頁中開啟) ChatGPT (在新分頁中開啟) Perplexity (在新分頁中開啟)