# Lingyi Wanwu MCP for AI Agents AI Agent Connect > Lingyi Wanwu MCP. Connect your AI agent to 01.AI's high-performance Yi models to handle complex bilingual tasks. This Connector lets you manage chat completions, generate high-dimensional semantic embeddings, and monitor your account usage directly from your AI client. It's the fastest way to integrate the Yi series into your custom apps, RAG pipelines, and enterprise systems without the usual API headache. ## Overview - **Category:** industry-titans - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_JkyG9ZUTy0GPyUj394Vmol76jPwT4EVBKA0NvupX/ai-agent-connect - **Tags:** yi-models, 01-ai, llm-api, embeddings, chinese-ai, kai-fu-lee ## Description Lingyi Wanmu MCP lets you have your AI agent directly interact with the Yi series of models from 01.AI. This means your agent can handle complex bilingual tasks, generate high-dimensional embeddings for your search tools, and check for content policy violations without you having to swap between different platforms. It's about giving your agent the ability to pull from a high-performance foundation model while you keep your eyes on the bigger picture. You can monitor your token usage and balance programmatically, so you won't get hit with surprise costs in the middle of a big job. When you find this in the Vinkius catalog, you're getting a direct line to 01.AI's high-performance infrastructure. Whether you're building a custom RAG pipeline or just need a reliable way to hit a bilingual model, this connection makes it happen. It handles the heavy lifting of the API handshake so you can focus on the logic of your application. ## Tools ### chat_completions Send a prompt to a Yi model to get a high-quality response. It works for both English and Chinese queries. ### check_moderation Scan your content for policy violations before you use it. This keeps your AI's output safe and compliant. ### get_embeddings Turn text into semantic vectors for your search tools. It's perfect for building out RAG pipelines. ### list_models See which Yi models are currently available. This helps you pick the right balance of speed and intelligence for your specific task. ## Prompt Examples **Prompt:** ``` What's the current balance on my Lingyi Wanwu account? ``` **Response:** ``` Checking your balance now... **Current Balance:** 50.00 CNY **Estimated Capacity:** - Yi-Large: ~2 million tokens - Yi-34B: ~1.2 million tokens Would you like me to check the token usage for a specific model? ``` **Prompt:** ``` Generate embeddings for this mission statement: 'To provide the best tech for everyone'. ``` **Response:** ``` Generating embeddings... I've created a semantic vector for your mission statement using the Yi-embedding model. **Status:** Success **Vector Dimensions:** 1024 You can now use this vector in your RAG search pipeline. ``` **Prompt:** ``` Chat with Yi-Large and ask it to summarize the benefits of RAG. ``` **Response:** ``` Connecting to Yi engine... **Yi-Large responded:** RAG offers several key benefits: - **Contextual Awareness:** It provides specific facts from your data. - **Reduced Hallucination:** It grounds the AI in your actual documents. - **Efficiency:** It allows you to use smaller models more effectively. Would you like me to expand on any of these points? ``` ## Capabilities ### Chat with Yi models Send prompts to the Yi series and get high-quality responses in both English and Chinese. ### Generate text embeddings Convert your text into semantic vectors to power your own search and RAG systems. ### Check content moderation Scan your content for policy violations before it gets processed by your agent. ### List available models See every model option in the Yi family and their technical specs in one go. ### Monitor account balance Check your remaining token count and spend to keep your project costs on track. ## Use Cases ### Bilingual Customer Support A developer needs a chatbot that handles both English and Chinese queries fluently. They use chat_completions to get accurate responses for both languages. ### Multilingual Knowledge Base A knowledge engineer is building a RAG system. They use get_embeddings to turn a library of bilingual documents into searchable vectors. ### Content Safety Gate A dev wants to ensure user-generated content is safe. They use check_moderation to scan inputs before the agent processes them. ### Model Comparison A developer needs to see the latest specs for the Yi-34B model. They use list_models to see all available options and their technical details. ## Benefits - Access bilingual models: Use Yi-Large and Yi-34B for high-quality English and Chinese responses in your own apps. - Power your RAG: Generate high-dimensional vectors for your knowledge base to make your search tools more accurate. - Stay on budget: Monitor your token balance and costs in real time so you don't get hit with surprise bills. - Safety first: Scan your content for policy violations before you use it to keep your AI's output compliant. - Quick setup: Skip the manual API boilerplate and let your agent handle the requests directly. ## How It Works The bottom line is you get a direct connection to 01.AI's models without the manual API setup. 1. Get your API key from the Lingyi Wanwu Developer Platform. 2. Paste your key into your Connector settings. 3. Ask your agent to perform a task like chatting with a bilingual model. ## Frequently Asked Questions **What is the Lingyi Wanwu MCP?** It's a direct connection that lets your AI agent talk to 01.AI's Yi models. You can use it for chat, embeddings, and monitoring your account. **Can I use Lingyi Wanwu for Chinese language tasks?** Yes, it's specifically designed to handle high-quality bilingual tasks in both English and Chinese. **How does Lingyi Wanwu help with RAG?** It provides high-dimensional semantic embeddings. Your agent can turn your documents into vectors to power your search systems. **How do I monitor my costs with Lingyi Wanwu?** The Connector lets your agent check your current token balance and consumption. This helps you stay on budget while running your tasks. **Can the Lingyi Wanwu MCP check for unsafe content?** Yes, it includes a tool to scan your content for policy violations. This ensures your AI's output stays within your safety guidelines. **Is Lingyi Wanwu good for bilingual apps?** It's one of the best options for this. It's built to handle the nuances of both English and Chinese for chat and embeddings. **Which Yi model is best for complex reasoning?** For complex reasoning and high-quality outputs, `yi-large` is recommended. For faster response times and cost efficiency, `yi-medium` or `yi-spark` are excellent alternatives. **Can I automatically retrieve my remaining account balance?** Yes! Use the `get_balance` tool. Your agent will connect to the Lingyi Wanwu billing service and return your current remaining credits. **How do I list all the technical specs for the Yi models?** Use the `list_models` tool. Your agent will retrieve a list of all models currently available on the platform, along with their IDs and capabilities.