APIAny MCP Server
The APIAny MCP Server connects AI agents and developers to 100+ AI models, enabling model discovery, pricing estimation, documentation lookup, code generation, and paid media generation workflows.
List Models: Browse public APIAny models filtered by type (chat, image, video, audio), provider, or search text, with pricing and capability metadata.
Search Models: Search models using natural-language queries, filtered by modality or provider.
Get Model Details: Retrieve detailed information about a specific model by ID or display name.
Estimate Costs: Calculate APIAny credit costs based on number of requests, input/output tokens, and cached tokens.
Get Integration Examples: Generate ready-to-use code examples in cURL, Python, JavaScript, Go, Java, or PHP for integrating with APIAny models.
Get Model Usage: Retrieve endpoint details, payload structure, async behavior, and language-specific examples for one or more models.
Create Image Tasks: Initiate a paid asynchronous image generation task (requires API key and explicit confirmation).
Create Video Tasks: Initiate a paid asynchronous video generation task (requires API key and explicit confirmation).
Check Task Status: Poll the status of an async image or video generation task using its task ID (requires API key).
Get Documentation Context: Fetch compact APIAny documentation from
llms.txtfor context-aware agent assistance.
All non-paid operations work without an API key, making the server safe for exploratory use.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@APIAny MCP Server show JavaScript example for nano-banana-pro"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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-integrationso supported agents can learn the APIAny workflow.
Related MCP server: ask-another
Quick Start
Run the server directly with npm:
npx -y @apiany-ai/mcpOr install and run it from this repository:
git clone git@github.com:ailingqu/ApiAny.AI-MCP.git
cd ApiAny.AI-MCP
npm install
npm startVisual Setup
1. Install and Start the MCP Server
2. Add APIAny MCP to Your Agent Client
Use this configuration in Claude Code, Cursor, VS Code, or another MCP-compatible client:
{
"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:
{
"APIANY_BASE_URL": "https://apiany.ai",
"APIANY_API_KEY": "your_apiany_api_key"
}3. Ask Your Agent to Use APIAny
Example prompts:
Use APIAny MCP to find an image model for product photos, compare pricing, and show JavaScript integration code.Use APIAny MCP to estimate credits for 20 gpt-style chat requests with 10k input tokens and 5k output tokens.Use APIAny MCP to show JavaScript usage for nano-banana-pro and Python usage for veo3-1-fast.MCP Tools
Tool | Purpose | API key |
| List public APIAny models with pricing and capability metadata. | No |
| Search models by text, provider, modality, or capability. | No |
| Get one public model by model id or display name. | No |
| Estimate credits from public pricing metadata. | No |
| Return endpoint, payload, async behavior, and language examples for models. | No |
| Return cURL, Python, JavaScript, Go, Java, or PHP examples. | No |
| Return compact APIAny documentation context from | No |
| Create a paid async image task after explicit confirmation. | Yes |
| Create a paid async video task after explicit confirmation. | Yes |
| Read 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
Variable | Required | Description |
| No | APIAny base URL. Defaults to |
| Only for paid tools | API 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_KEYconfirm_paid_request=true
The server does not persist API keys. It only reads them from the current process environment.
Development
npm install
npm run check
npx -y @modelcontextprotocol/inspector node src/server.jsUseful files:
src/server.js: MCP server implementation.examples/mcp.json: client configuration example.docs/distribution.md: release checklist for npm, MCP directories, and skill marketplaces.CHANGELOG.md: release history.
Links
Website: https://apiany.ai
Models: https://apiany.ai/models
Docs context: https://apiany.ai/llms.txt
License
MIT
Available Tools
10 toolscreate_image_taskC
Create a paid APIAny asynchronous image generation task. Requires APIANY_API_KEY and confirm_paid_request=true.
Inputs: model (required), prompt (required), size, quality, +4 more.
create_video_taskC
Create a paid APIAny asynchronous video generation task. Requires APIANY_API_KEY and confirm_paid_request=true.
Inputs: model (required), prompt (required), duration, aspect_ratio, +7 more.
estimate_costC
Estimate APIAny credits for a model using public pricing metadata.
Inputs: model (required), requests, input_tokens, output_tokens, +1 more.
get_docs_contextC
Return compact APIAny documentation context from llms.txt.
Inputs: max_chars.
get_integration_examplesB
Return APIAny integration examples for a model and language.
Inputs: language, model.
get_modelA
Get one APIAny model by public model id or display name.
Inputs: model (required).
get_model_usageC
Return endpoint, payload, async behavior, and language example for one or more APIAny models.
Inputs: model, type, language, limit.
get_task_statusC
Get an APIAny async generation task status. Requires APIANY_API_KEY.
Inputs: task_id (required).
list_modelsC
List public APIAny models with pricing and capability metadata.
Inputs: q, type, provider, limit.
search_modelsC
Search APIAny models by natural-language text, provider, modality, or capability.
Inputs: query (required), type, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
All tools have clearly distinct purposes: image/video task creation, cost estimation, documentation retrieval, model lookup, usage examples, task status, listing, and searching. No overlap is evident.
All tool names follow a consistent verb_noun pattern with underscores (e.g., create_image_task, list_models). Verbs like create, get, list, search are used uniformly, and naming conventions are fully consistent.
With 10 tools, the set is well-scoped for an API abstraction layer. It covers discovery (list, search), details (get_model, get_model_usage), cost estimation, task creation (image/video), status checking, and documentation—each tool earns its place.
The tool surface covers key workflows: model discovery, cost estimation, async task creation and status checking. Minor gaps include lack of task cancellation or listing, but these are non-essential for core usage, so it's nearly complete.
Maintenance
Related MCP Connectors
Generate images, videos and music with model discovery, cost estimates and asynchronous results.
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Generate AI video, images and music. Browse models and prices; OAuth and one prepaid balance.
Related MCP Servers
- AlicenseAqualityFmaintenanceProvides AI assistants with real-time access to 1000+ AI models including their latest pricing, context windows, capabilities, and specifications. Supports model search, comparison, recommendations, and live testing.31MIT
- AlicenseAqualityBmaintenanceEnables AI assistants to query hundreds of models across OpenAI, Google, and OpenRouter, with model discovery, deep-research jobs, and image generation.103MIT
- -licenseNot gradedqualityNot gradedmaintenanceEnables discovery of public AI models with pricing, documentation context, and OpenAI-compatible integration examples. Supports both read-only queries and paid async media generation tasks.-

spicyapi-mcpofficial
AlicenseAqualityBmaintenanceLets AI assistants browse live model catalogs, compare prices, create generation tasks, and collect results, with confirmation for every billable step.15168 npmMIT