How to Use the iFLYTEK Open Platform / 讯飞开放平台 MCP in Cursor

Q: How do I add the iFLYTEK Open Platform / 讯飞开放平台 MCP Server to Cursor?

Create an mcp.json file in your .cursor directory or project root. Add the server under the mcpServers key with your API credentials. Once saved, Cursor will recognize the tools, allowing your agent to run them during chat or inline edits.

Q: Can the Cursor agent use iFLYTEK Open Platform / 讯飞开放平台 to generate voice files?

Yes, the agent can call texttospeech to generate audio files from your code strings. You provide the text, and the tool writes the resulting audio file directly to your project directory. This is useful for testing voice assets in your app.

Q: Does Cursor support translation via iFLYTEK Open Platform / 讯飞开放平台?

Yes, the translate tool allows your agent to run the MCP Server to translate localization files inside your workspace. You can ask Cursor to translate a JSON file of English keys into Chinese, and the tool will process the strings directly.

Write code that processes voice and localizes text by calling iFLYTEK Open Platform directly from Cursor.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect iFLYTEK Open Platform / 讯飞开放平台 MCP to Cursor

Create your Vinkius account to connect iFLYTEK Open Platform / 讯飞开放平台 to Cursor and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup iFLYTEK Open Platform / 讯飞开放平台 with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate code from voice using this MCP Server

The `speech_to_text` tool transcribes audio files to feed raw text directly into your active code editor. Your agent calls this tool to transcribe user voice inputs during debugging, letting you write code based on real audio data. You don't need to write custom boilerplate to test transcription APIs. Cursor runs the tool, gets the text, and writes the processing logic for you on the fly.

Analyze source text inside Cursor

The `entity_recognition` tool identifies names, organizations, and locations, while `keyword_extraction` isolates core concepts from text blocks. Your agent uses these tools to parse unstructured data files directly inside your workspace. This MCP Server setup lets you build and test data pipelines without leaving your editor. The agent uses the live extraction output to structure JSON schemas or seed database test files.

Extract code comments and text from mockups in Cursor

The `ocr_general` tool scans images to extract text and structure from mockups, UI screenshots, or scanned documents. Your agent runs this tool to grab text from design assets and inject it directly into your code files. Instead of copying text manually from a Figma mockup, you point Cursor to the image file. The tool extracts the strings, and the agent writes the corresponding localization keys.

Setup guide

Set up iFLYTEK Open Platform / 讯飞开放平台 MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the iFLYTEK Open Platform / 讯飞开放平台 MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent iFLYTEK Open Platform / 讯飞开放平台 transactions." If the MCP tools are loaded correctly, Cursor will call the iFLYTEK Open Platform / 讯飞开放平台 tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "iflytek-open-platform-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by iFLYTEK Open Platform / 讯飞开放平台. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect iFLYTEK Open Platform / 讯飞开放平台 now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about iFLYTEK Open Platform / 讯飞开放平台 MCP in Cursor

Create an `mcp.json` file in your `.cursor` directory or project root. Add the server under the `mcpServers` key with your API credentials. Once saved, Cursor will recognize the tools, allowing your agent to run them during chat or inline edits.

Yes, the agent can call `text_to_speech` to generate audio files from your code strings. You provide the text, and the tool writes the resulting audio file directly to your project directory. This is useful for testing voice assets in your app.

Yes, the `translate` tool allows your agent to run the MCP Server to translate localization files inside your workspace. You can ask Cursor to translate a JSON file of English keys into Chinese, and the tool will process the strings directly.

Cursor displays tool execution logs in the output panel. If an API call fails due to incorrect credentials or bad audio formatting, you will see the exact error message from the server. This makes it easy to fix configuration issues.

Your source code, text strings, and audio assets are processed in a secure sandbox. The server acts as a direct bridge, sending the payload to the API and returning the output to Cursor. No data is cached locally or stored on external servers beyond the active API call.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript