How to Use the Caiyun AI Translate / 彩云小译 MCP in LlamaIndex

Q: How do I ingest Chinese documents into LlamaIndex using Caiyun AI Translate / 彩云小译?

Run your raw documents through the translatezhtoen tool before chunking. This converts the text to English, allowing LlamaIndex to build a clean, searchable English vector index using this MCP tool.

Q: How does LlamaIndex handle language detection with Caiyun AI Translate / 彩云小译?

The agent uses the detectlanguageviaauto tool to inspect the query text. Based on the returned language code, LlamaIndex routes the query to the correct translation tool.

Q: What tools are available for Japanese translation?

You can use the translatejatozh tool to convert Japanese text into high-precision Chinese. This is perfect for indexing Japanese technical manuals into a Chinese knowledge base.

Index high-precision Chinese, Japanese, and Korean translations directly into your LlamaIndex vector stores via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Caiyun AI Translate / 彩云小译 MCP to LlamaIndex

Create your Vinkius account to connect Caiyun AI Translate / 彩云小译 to LlamaIndex 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 Caiyun AI Translate / 彩云小译 with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing Translated Content in LlamaIndex

The `translate_text` tool translates lists of text strings before they are chunked and indexed into your vector store. This allows your LlamaIndex pipeline to ingest multi-lingual documents and store them in a single target language for uniform search. By translating raw data with `translate_zh_to_en` first, you avoid semantic search mismatches. Your index stays clean because all nodes are stored in the same language, making retrieval highly accurate.

Live Query Translation via MCP Server

With the `translate_to_zh` tool, your system translates user queries on the fly before they hit a Chinese-language vector index. This enables cross-lingual RAG, where an English query retrieves relevant Chinese documents. If the input language is ambiguous, the agent calls `detect_language_via_auto` to identify the query language first. LlamaIndex then routes the query to the correct translation tool, ensuring your search matches the index's language.

Batch Document Translation for RAG

Running the `translate_multiple_lines` tool processes entire document sections in a single API call during the ingestion phase. This tool prevents your LlamaIndex ingestion pipeline from stalling when handling large multi-page PDFs. After translation, you run the status check tool `check_caiyun_status` to ensure the translation pipeline remains healthy. This keeps your automated document pipelines running without silent failures.

Setup guide

Set up Caiyun AI Translate / 彩云小译 MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Caiyun AI Translate / 彩云小译 MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Caiyun AI Translate / 彩云小译 tools.",
)
response = await agent.run("List recent Caiyun AI Translate / 彩云小译 data")

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 Caiyun AI Translate / 彩云小译. 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 Caiyun AI Translate / 彩云小译 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 Caiyun AI Translate / 彩云小译 MCP in LlamaIndex

Run your raw documents through the `translate_zh_to_en` tool before chunking. This converts the text to English, allowing LlamaIndex to build a clean, searchable English vector index using this MCP tool.

Yes, you can configure your query engine to call this MCP Server's `translate_to_zh` tool on the incoming query string. This lets users search your Chinese document indexes using English queries.

The agent uses the `detect_language_via_auto` tool to inspect the query text. Based on the returned language code, LlamaIndex routes the query to the correct translation tool.

You can use the `translate_ja_to_zh` tool to convert Japanese text into high-precision Chinese. This is perfect for indexing Japanese technical manuals into a Chinese knowledge base.

Your raw translation strings and document chunks are processed in a secure, zero-trust sandbox. No translation data is cached or stored on the Vinkius platform, keeping your proprietary documents private.

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