MCP^Alpha

Call web data and other tools directly from MCP-capable AI clients such as Claude Code and Cursor.

Alpha, coming soon: the MCP service is in limited testing and its address and tool list may change. Once it opens, the "Web Data" page in the console shows the MCP address and setup steps; if it is not shown, your site does not offer it yet.

Why MCP

MCP (Model Context Protocol) is the common protocol AI clients use to call external tools. Coding tools such as Claude Code and Cursor, and many agent frameworks, already support it.

With the OneFast API MCP service connected, the AI can decide on its own during a conversation when to search the web, fetch a page, look up businesses on the map or find company contacts, without you writing call code for each tool.

Same key, same balance: MCP calls share the API key with the Web Data REST endpoints, are billed by the same rules and are recorded in the same place.
Timeout-friendly: long-running jobs return a job ID first so the AI can check back later, instead of being charged twice after a client timeout.

Setup (once available)

Add a remote MCP server (Streamable HTTP) in your client with the MCP address shown in the console, and send your API key in a header:

Claude Code

claude mcp add --transport http webdata <MCP address> --header "Authorization: Bearer $API_KEY"

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "webdata": {
      "url": "<MCP address>",
      "headers": { "Authorization": "Bearer sk-xxx" }
    }
  }
}

The tools match Web Data, with the same billing and limits.

Getting started

Overview — OneFast API gives you GPT, Claude, Gemini, DeepSeek, Qwen and other leading models with one API key, compatible with the OpenAI, Anthropic and Gemini native protocols.
Quickstart — Create an API key and send your first request with cURL, Python or Node.js.
Authentication — How to send your API key, how to choose a group, and the quota, model and IP limits you can set on a key.
Groups & billing — What groups (routes) are, how prices are calculated, and when you aren't charged.
Supply lines^Alpha — The same model is offered by different supply lines; choose by price, speed and data policy, and pay for the line you use.
Referral rewards — Invite new users with your link and earn 10% of what they spend as account credit, up to $100 per account.

Text & chat

Chat completions (OpenAI-compatible) — Call any text model — GPT, Claude, Gemini, DeepSeek, Qwen and more — with the OpenAI Chat Completions format.
Responses API — OpenAI's next-generation Responses endpoint, used by default by Codex CLI and similar tools.
Claude Messages (Anthropic native) — Call Claude with Anthropic's official Messages API, with full native support for extended thinking, prompt caching, tool use and more.
Gemini native API — Call Gemini models with Google's official generateContent API, compatible with the Google GenAI SDK and Gemini CLI.
Tools & reasoning — Function calling, structured output, and controlling reasoning (thinking) for GPT, Claude and Gemini.
Prompt caching — Long prefixes you send repeatedly (system prompts, documents, tool definitions) can hit the cache, cutting input cost and latency significantly.

Images, video & audio

Image generation — Call GPT Image, Gemini (Nano Banana) and other image models with the OpenAI Images format, at 1K / 2K / 4K.
Video generation — Video runs as an async task — submit → poll status → download the result. Supports Seedance, Wan, Grok Imagine, MiniMax H3, HappyHorse, Gemini Omni and more.
Audio & embeddings — Text-to-speech (TTS), speech recognition (ASR) and text embeddings.

Data services

Web Data^Alpha — Call web search, page fetch, map places and company contacts tools with the same API key and balance, billed per item.
MCP^Alpha — Call web data and other tools directly from MCP-capable AI clients such as Claude Code and Cursor.
Prospects^Alpha — Tell us what you sell and where you want to sell it, and the team builds you a verifiable list of business prospects.

Client integrations

Claude Code — Use OneFast API in Claude Code, Anthropic's official command-line coding assistant.
Codex CLI — Use OneFast API in Codex CLI, OpenAI's official command-line coding assistant.
Gemini CLI — Use OneFast API in Gemini CLI, Google's official command-line assistant.
Cherry Studio — Add OneFast API to the Cherry Studio desktop AI client and use every model with one key.
Other clients & frameworks — Setup notes for common tools such as Cursor, Cline / Roo Code, LangChain, Dify and LobeChat.

Reference

API reference — Parameters, examples and live testing for every endpoint. Download the OpenAPI file to import into Postman / Apifox.
Model catalog — Every available model with live prices. When you're logged in, it shows all groups available to your account and their prices.
Errors — Error response formats, what common HTTP status codes mean and how to handle them.
FAQ — Frequently asked questions about integration, billing and choosing models.

MCPAlpha

Why MCP

Setup (once available)

MCP^Alpha