# Cody AI MCP for AI Agents AI Agent Connect > Cody AI lets your AI agent manage your knowledge base bots, import new documents from the web, and query your trained assistants directly. It connects your internal data to your AI's actions, allowing you to turn static files into a live, queryable source of truth. ## Overview - **Category:** customer-support - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_3sdhdxz69A9PNCbHGNcvaVvLSXZIq9OFM5te4LTv/ai-agent-connect - **Tags:** rag, ai-assistant, knowledge-base, chatbot-training, document-query, automated-support ## Description You're likely trying to get your AI to actually know what's in your company's docs without copy-pasting everything into a prompt every single time. This Connector lets your agent take over the heavy lifting of managing those knowledge bases. Instead of jumping between tabs to check which bots are trained on which folders, you can just ask your agent to show you the status of a specific document or list your active bots. You can even have your agent grab a new webpage and shove it into a specific folder for the bot to learn from. It's about making your knowledge base an active part of your workflow rather than a static pile of files. When you use this through the Vinkius catalog, you're essentially giving your agent the keys to your company's brain. You can start conversations with specific bots to get answers based on your own data, or check message histories to see what's been asked before. It turns your AI from a generalist into a specialist that actually knows your specific business rules, products, and policies. ## Tools ### create_conversation Start a new session with a specific bot. This lets you isolate different types of queries in separate threads. ### list_bots See every bot in your Cody AI account. This helps you keep track of your different specialized assistants. ### list_conversations View a list of your recent interactions. You can quickly jump back into previous threads. ### list_documents See every file in your knowledge base. This helps you audit what data the AI currently has access to. ### list_folders See the folder structure of your knowledge base. Use this to understand how your training data is organized. ### list_messages Pull up the message history for a specific chat. You can review past answers to check for accuracy. ### send_message Send a prompt to a bot in an existing conversation. This is how you actually ask the bot questions. ### get_bot_details Get the full specs for a specific bot. You'll see exactly what it's trained on and how it's configured. ### get_document_status Check if a document is done syncing. This tells you if the AI has finished learning the new info. ### import_webpage Send a URL to a specific folder in your knowledge base. It's the fastest way to add new web content to your bot. ## Prompt Examples **Prompt:** ``` Check if the new security policy is ready for the HR bot. ``` **Response:** ``` I checked the status of 'security_policy_v2.pdf' in the HR folder. It's currently syncing and is about 60% complete. It should be ready to use in about 3 minutes. ``` **Prompt:** ``` What bots do we have for customer support? ``` **Response:** ``` You have 4 active bots for support: - **Product FAQ**: 12 docs, 89 convos - **Refunds**: 5 docs, 42 convos - **Shipping**: 8 docs, 110 convos - **Technical**: 20 docs, 250 convos ``` **Prompt:** ``` Add this new blog post to the product knowledge base: [URL] ``` **Response:** ``` I've sent that URL to the Product folder. The AI is now training on the new content. I'll let you know once it's finished syncing. ``` ## Capabilities ### Manage knowledge base bots List all active bots and see their specific configurations to keep your assistants organized. ### Query trained assistants Start new conversations with specific bots to get answers based on your private data. ### Import web content Add new URLs directly into your bot's training folders to keep your data fresh. ### Track training progress Check if a document has finished syncing so you know exactly when it's ready to use. ### Review conversation history Pull up old messages to see what the AI has already answered for your team. ### Organize knowledge folders View and manage the folder structure of your training data to keep your info sorted. ## Use Cases ### Updating a product FAQ A manager sees a new product launch and asks the agent to use import_webpage to add the new landing page to the Product folder. ### Verifying support answers A support lead uses list_messages to review how the bot handled a complex refund query from a customer earlier that day. ### Auditing bot coverage A knowledge manager asks the agent to list_bots and list_documents to make sure the HR bot has all the latest policy files. ### Starting a quick query A dev asks the agent to create_conversation with the Engineering Bot to ask about the latest API specs. ## Benefits - Stop manual data entry by using import_webpage to feed your AI new web content instantly. - Verify your training status with get_document_status so you know exactly when a file is ready to use. - Keep your bots organized by using list_bots and list_folders to audit your knowledge base structure. - Get faster answers by using create_conversation to talk directly to your most relevant trained assistant. - Audit your AI's performance by pulling up history with list_messages to see what's been answered. ## How It Works The bottom line is you get a way to manage and query your private knowledge base using only natural language. 1. Add the Cody AI MCP to your client and grab your API key from the Cody dashboard. 2. Tell your agent which bot you want to talk to or which folder needs new content. 3. Get instant answers based on your private docs or see the status of your latest imports. ## Frequently Asked Questions **Can Cody AI MCP help my AI agent read my private files?** Yes, it connects your agent to your private knowledge base. You can query documents, PDFs, and web pages that the AI wasn't originally trained on. **How do I update the info my bot knows?** You can use the Connector to import new web pages or files into specific folders. Your agent will then manage the training process for you. **Can I see what my bot has answered before?** Yes, you can view the message history for any conversation. This helps you audit the bot's accuracy and see past interactions. **Does Cody AI MCP support multiple different bots?** It does. You can list all your bots and start conversations with specific ones, like an HR bot or a technical support bot. **How do I know when my documents are finished uploading?** You can check the status of any specific document. The Connector tells you if the AI is still learning the content or if it's ready for use. **Is this for general AI chat or specific company data?** This is specifically for company data. It's designed for teams that need their AI to stay grounded in their own facts and documents. **How do I get a Cody AI API key?** In the Cody AI dashboard, go to **Settings > API** and copy your key. Paste it below. **What is Focus Mode?** Focus Mode restricts a bot's knowledge to specific documents for a given conversation, improving answer relevance. **How long does it take to learn new documents?** Usually seconds to minutes depending on document size. Use 'get_document_status' to check when sync is complete.