Apiany Mcp

io.github.ailingqu由 GitHub 账号 ailingqu 发布v0.1.2更新于 Oct 24, 2026

APIAny MCP server for model discovery, pricing, docs, and integration examples.

已验证STDIO仅桌面开发者工具AI 与机器学习

概览

AI 生成的概览

APIAny 官方 MCP 服务器，让助手探索 AI 模型、估算点数成本、查询文档并生成接入示例。

可以做什么
按供应商、模态、能力与价格浏览、搜索并查询 APIAny 公开模型。依据公开价格数据估算点数成本。获取精简的 APIAny 文档内容。生成 cURL、Python、JavaScript、Go、Java 与 PHP 的兼容示例。在配置密钥并明确确认付费后创建图片或视频任务，并查询异步任务状态。
适用场景
当你想在写代码前先挑选 APIAny 的模型、比较点数成本，或获取各语言的接入示例时使用；若需要实际生成图片或视频，也可在配置密钥后使用付费任务工具。
运行要求
以 npm 包在本机运行，需要 Node.js 与网络连接。可选环境变量 APIANY_BASE_URL 可指定服务地址，默认为官方站点。付费的图片与视频任务工具另需环境变量 APIANY_API_KEY。
安装前请注意
付费工具会产生实际费用，需同时具备 APIANY_API_KEY 并明确确认付费才会执行；请留意点数消耗。服务器从当前进程环境读取密钥，请妥善保护。查询模型与文档时会连接至 APIAny 服务。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Apiany Mcp，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

APIAny MCP

Official MCP server for APIAny model discovery, pricing context, documentation lookup, and OpenAI-compatible integration examples.

APIAny connects agents and developers to 100+ AI models for chat, image, video, and multimodal workflows.

[npm version] [npm package] [release] [license] [Node.js] [MCP server]

Quick Start · Visual Setup · MCP Tools · Agent Skill · Development

English | 中文

[APIAny MCP overview]

What This Repository Provides

APIAny MCP gives AI agents a structured way to understand and use APIAny:

  • Discover public APIAny models by provider, modality, capability, and pricing metadata.
  • Estimate APIAny credits before choosing a model or running a workflow.
  • Fetch compact documentation context from APIAny docs and llms.txt.
  • Generate OpenAI-compatible cURL, Python, JavaScript, Go, Java, and PHP examples.
  • Create image or video generation tasks only when an API key is configured and the user explicitly confirms paid usage.
  • Package an agent skill at skills/apiany-integration so supported agents can learn the APIAny workflow.

Quick Start

Run the server directly with npm:

bash
npx -y @apiany-ai/mcp

Or install and run it from this repository:

bash
git clone [email protected]:ailingqu/ApiAny.AI-MCP.gitcd ApiAny.AI-MCPnpm installnpm start

Visual Setup

1. Install and Start the MCP Server

[Install APIAny MCP with npx]

2. Add APIAny MCP to Your Agent Client

Use this configuration in Claude Code, Cursor, VS Code, or another MCP-compatible client:

[APIAny MCP client configuration]

json
{  "mcpServers": {    "apiany": {      "command": "npx",      "args": ["-y", "@apiany-ai/mcp"],      "env": {        "APIANY_BASE_URL": "https://apiany.ai"      }    }  }}

For paid image or video task tools, also set APIANY_API_KEY:

json
{  "APIANY_BASE_URL": "https://apiany.ai",  "APIANY_API_KEY": "your_apiany_api_key"}

3. Ask Your Agent to Use APIAny

[APIAny MCP tool usage in an agent conversation]

Example prompts:

text
Use APIAny MCP to find an image model for product photos, compare pricing, and show JavaScript integration code.
text
Use APIAny MCP to estimate credits for 20 gpt-style chat requests with 10k input tokens and 5k output tokens.
text
Use APIAny MCP to show JavaScript usage for nano-banana-pro and Python usage for veo3-1-fast.

MCP Tools

ToolPurposeAPI key
list_modelsList public APIAny models with pricing and capability metadata.No
search_modelsSearch models by text, provider, modality, or capability.No
get_modelGet one public model by model id or display name.No
estimate_costEstimate credits from public pricing metadata.No
get_model_usageReturn endpoint, payload, async behavior, and language examples for models.No
get_integration_examplesReturn cURL, Python, JavaScript, Go, Java, or PHP examples.No
get_docs_contextReturn compact APIAny documentation context from /llms.txt.No
create_image_taskCreate a paid async image task after explicit confirmation.Yes
create_video_taskCreate a paid async video task after explicit confirmation.Yes
get_task_statusRead async media task status.Yes

Agent Skill

The APIAny Integration skill lives in skills/apiany-integration.

It helps agents:

  • Choose APIAny models by modality, provider, pricing, and capability.
  • Generate examples for chat, image, video, and media workflows.
  • Explain async task creation and polling.
  • Require explicit confirmation before paid generation tasks.

Environment Variables

VariableRequiredDescription
APIANY_BASE_URLNoAPIAny base URL. Defaults to https://apiany.ai.
APIANY_API_KEYOnly for paid toolsAPI key used for paid image/video task creation and task polling.

Safety Model

Read-only tools work without an API key. Paid generation tools require both:

  • APIANY_API_KEY
  • confirm_paid_request=true

The server does not persist API keys. It only reads them from the current process environment.

Development

bash
npm installnpm run checknpx -y @modelcontextprotocol/inspector node src/server.js

Useful files:

Links

License

MIT

来源：README.md，提交 0fc4e24

工具

0
SourceWeft 尚未在沙箱中启动过该软件包，因此其工具未知。

版本历史

1
  1. v0.1.2最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手；SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分