APIAny MCP Server
Provides tools for discovering AI models, checking pricing, retrieving API documentation context, and generating integration examples; also supports paid async image/video tasks.
README
APIAny MCP
Official APIAny MCP server and agent skill package for model discovery, pricing lookup, documentation context, and OpenAI-compatible integration examples.
Official website: https://apiany.ai
What Is Included
src/server.js: MCP server for APIAny public model discovery, docs context, usage examples, and confirmed paid media tasks.skills/apiany-integration: Agent skill for choosing APIAny models, estimating credits, and generating safe integration code.examples/mcp.json: MCP client configuration example.docs/distribution.md: Release checklist for npm, MCP registries, and skill marketplaces.
Links
- Website: https://apiany.ai
- GitHub: https://github.com/ailingqu/ApiAny.AI-MCP
- Models: https://apiany.ai/models
- Docs context: https://apiany.ai/llms.txt
Install MCP
npx @apiany/mcp
During local development from this repository:
npm install
npm start
Configuration
Environment variables:
APIANY_BASE_URL: APIAny site/API base URL. Defaults tohttps://apiany.ai.APIANY_API_KEY: optional APIAny API key. Read-only public tools work without it.
Claude Code / Cursor / VS Code Config Example
{
"mcpServers": {
"apiany": {
"command": "npx",
"args": ["-y", "@apiany/mcp"],
"env": {
"APIANY_BASE_URL": "https://apiany.ai"
}
}
}
}
Tools
list_models: list public APIAny models with pricing and capability metadata.search_models: search models by text, provider, modality, or capability.get_model: get one public model by model id or display name.estimate_cost: estimate credits from public pricing metadata.get_integration_examples: return cURL, Python, JavaScript, Go, Java, or PHP examples for chat, image, or video models.get_model_usage: return endpoint, payload, async behavior, and language example for one or more models.get_docs_context: return compact APIAny documentation context from/llms.txt.create_image_task: create a paid async image task. RequiresAPIANY_API_KEYandconfirm_paid_request=true.create_video_task: create a paid async video task. RequiresAPIANY_API_KEYandconfirm_paid_request=true.get_task_status: read async task status. RequiresAPIANY_API_KEY.
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.
Prompt Examples
Ask an agent:
Use the APIAny MCP server to find an image model for product photos, compare pricing, and show a JavaScript integration example.
Use APIAny MCP to estimate the credits for 20 requests to gpt-5.5 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.
Use APIAny MCP to create an image task with nano-banana-pro after I confirm the paid request, then poll the task status.
Safety
Read-only tools work without an API key. Paid generation tools require APIANY_API_KEY and confirm_paid_request=true; the server does not persist API keys.
Development
npm install
npm run check
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.