Skip to main content

将 Anthropic Messages API 连接到 aicharged.io

215 个工具，一个端点：https://aicharged.io/api/v1/mcp

Anthropic Messages API

Anthropic Messages API 的 MCP 连接器（beta）：mcp_servers 加上 mcp_toolset——Claude 直接从 API 调用 aicharged.io。

  • API 密钥（Bearer）

托管的 MCP 工具——由 API 代你调用 aicharged.io

推荐 
import os
import anthropic

client = anthropic.Anthropic()
response = client.beta.messages.create(
    model="claude-opus-5-5",
    max_tokens=16000,
    betas=["mcp-client-2025-11-20"],
    messages=[{"role": "user", "content": "List my recent aicharged.io runs"}],
    mcp_servers=[{
        "type": "url",
        "url": "https://aicharged.io/api/v1/mcp",
        "name": "aicharged",
        "authorization_token": os.environ["AICHARGED_API_KEY"],
    }],
    tools=[{"type": "mcp_toolset", "mcp_server_name": "aicharged"}],
)
print(response.content)

测试版功能：请保留 mcp-client-2025-11-20 beta 标志。API 会把 authorization_token 作为 Bearer token 发送给 aicharged.io。

用 curl 发送同样的请求

curl https://api.anthropic.com/v1/messages \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "anthropic-beta: mcp-client-2025-11-20" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-opus-5-5",
    "max_tokens": 16000,
    "messages": [{"role": "user", "content": "List my recent aicharged.io runs"}],
    "mcp_servers": [{"type": "url", "url": "https://aicharged.io/api/v1/mcp", "name": "aicharged", "authorization_token": "<API_KEY>"}],
    "tools": [{"type": "mcp_toolset", "mcp_server_name": "aicharged"}]
  }'

或者让 CLI 自动设置

aicharged setup 会自动查找此电脑上的 AI 客户端，通过浏览器引导您登录，并写入相应的配置。

一行命令，轻松连接

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

流式 HTTP。发送 Authorization: Bearer <API_KEY> 请求头，或者在客户端支持的情况下通过 OAuth 登录。

或者告诉您的智能体
阅读 https://aicharged.io/agent.md，并为我设置 aicharged.io

使用此提示词打开于 Claude (在新标签页中打开) ChatGPT (在新标签页中打开) Perplexity (在新标签页中打开)