AceDataCloud MCP Server
Manages your AceDataCloud account through the platform management API, enabling balance checks, usage/spend lookup, API key management, order creation/payment, announcement publishing, and more.
README
AceDataCloudMCP
<!-- mcp-name: io.github.AceDataCloud/mcp-acedatacloud -->
A Model Context Protocol (MCP) server for managing your AceDataCloud account through the platform management API.
Check your balance, look up usage and spend, manage API keys, list services, create and pay recharge orders, manage platform tokens, list models, and (for admins) publish announcements — directly from Claude, VS Code, or any MCP-compatible client.
This is the management / console API (
platform.acedata.cloud) — different from the data-generation MCP servers (Suno, Midjourney, …) that callapi.acedata.cloud.
Tool Reference
Read (always safe)
| Tool | Description |
|---|---|
acedatacloud_get_balance |
Remaining credits per subscription, plus a total. |
acedatacloud_list_applications |
Your subscriptions with balance/spend. |
acedatacloud_list_services |
List or search available services. |
acedatacloud_list_usage |
Recent API call records (status, latency, credits). |
acedatacloud_usage_summary |
Spend aggregated by API over N days. |
acedatacloud_list_credentials |
Your API keys (token values masked). |
acedatacloud_list_orders |
Recharge orders. |
acedatacloud_list_platform_tokens |
Platform tokens (masked). |
acedatacloud_list_models |
Available chat models. |
acedatacloud_list_announcements |
Published announcements. |
acedatacloud_list_distributions |
Your referral/affiliate status + commission history. |
Catalog & Docs (public — no token needed)
| Tool | Description |
|---|---|
acedatacloud_get_service |
One service's detail (type, unit, free_amount, cost), by alias or id. |
acedatacloud_get_pricing |
A service's billing unit, free_amount and display pricing. |
acedatacloud_list_apis |
API endpoints, optionally scoped to one service (path, method, cost). |
acedatacloud_get_api_spec |
One API's OpenAPI definition + cost, by path. |
acedatacloud_list_datasets |
Downloadable datasets (price, download/preview URLs). |
acedatacloud_list_integrations |
Third-party integrations. |
acedatacloud_search_docs |
Full-text search the documentation (alias/title/snippet/url). |
acedatacloud_list_docs |
Browse documentation pages. |
acedatacloud_get_doc |
Fetch one doc's full content by UUID. |
acedatacloud_list_model_catalog |
Rich model catalog (provider, modality, credit pricing). |
acedatacloud_get_model |
Look up a model's pricing & capabilities by id/name. |
Write (require confirm=true)
| Tool | Description |
|---|---|
acedatacloud_create_credential |
Create an API key on an application. |
acedatacloud_delete_credential |
Revoke an API key. |
acedatacloud_create_order |
Create a recharge order. |
acedatacloud_pay_order |
Create a payment session and return pay_url. |
acedatacloud_create_platform_token |
Create a new platform token. |
acedatacloud_delete_platform_token |
Revoke a platform token. |
Admin (superuser token)
| Tool | Description |
|---|---|
acedatacloud_create_announcement |
Publish a platform announcement (confirm=true). |
Calling a write/admin tool without confirm=true returns a dry-run preview
and changes nothing.
Quick Start
1. Get a platform token
Create one at platform.acedata.cloud/console/platform-tokens.
It starts with platform- and never expires.
Use a platform token, not the per-service
api.acedata.cloudtoken — the latter returns 401 against the management API.
2. Install
pip install mcp-acedatacloud
3. Configure your client
Claude Desktop / VS Code (stdio):
{
"mcpServers": {
"acedatacloud": {
"command": "mcp-acedatacloud",
"env": {
"ACEDATACLOUD_PLATFORM_TOKEN": "platform-v1-xxxxxxxx"
}
}
}
}
Hosted (HTTP) — token per request:
{
"mcpServers": {
"acedatacloud": {
"url": "https://mcp.acedata.cloud/mcp",
"headers": { "Authorization": "Bearer platform-v1-xxxxxxxx" }
}
}
}
Example prompts
- "How many credits do I have left?"
- "What did I spend on Suno in the last 7 days?"
- "List my API keys and show which ones have a spend cap."
- "Create a new API key on application
<id>named ci." → previews, then run with confirm. - "Top up application
<id>with package<id>and give me the Stripe pay link."
Configuration
| Variable | Default | Description |
|---|---|---|
ACEDATACLOUD_PLATFORM_TOKEN |
— | Required. Platform token. |
PLATFORM_API_BASE_URL |
https://platform.acedata.cloud |
Management API base. |
PLATFORM_REQUEST_TIMEOUT |
30 |
Request timeout (seconds). |
LOG_LEVEL |
INFO |
Logging level. |
Development
pip install -e ".[dev,test,http]"
pytest -m "not integration" # unit tests
ruff check . # lint
mypy core tools # type-check
mcp-acedatacloud --transport http --port 8000
Notes
- Amounts (
remaining_amount,used_amount, totals) are in Credits, not USD. - Newly created credential/platform tokens are returned in full only once — store them immediately.
- Credential rotation = delete + recreate (no in-place rotate endpoint).
- Announcement tools require a superuser token.
License
MIT — see LICENSE.
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。