Cody AI Connector for AI agents.
10 live capabilities
Query your private knowledge base and manage trained bots from your chat.
Waiting for input…
Why people use Cody AI
Cody AI Knowledge Base Management for Support Teams
With this Connector, your agent acts as a librarian. You just tell it what you need, and it pulls from your trained bots. You get instant, accurate answers based on your actual docs without ever leaving your chat window.
What Vinkius changes
You get a way to manage and query your private knowledge base using only natural language.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
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.
- Real-world use case 02
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.
- Real-world use case 03
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.
Complete set · 10capabilities
The complete Cody AI capability set.
These are the exact actions your AI can choose when you ask it to work with Cody AI.
01—04
4 capabilities in this set.
Part of 10 available through Cody AI.
- 01 Capability
Create conversation
Start a new session with a specific bot. This lets you isolate different types of queries in separate threads.
- 02 Capability
List bots
See every bot in your Cody AI account. This helps you keep track of your different specialized assistants.
- 03 Capability
List conversations
View a list of your recent interactions. You can quickly jump back into previous threads.
- 04 Capability
List documents
See every file in your knowledge base. This helps you audit what data the AI currently has access to.
05—07
3 capabilities in this set.
Part of 10 available through Cody AI.
- 05 Capability
List folders
See the folder structure of your knowledge base. Use this to understand how your training data is organized.
- 06 Capability
List messages
Pull up the message history for a specific chat. You can review past answers to check for accuracy.
- 07 Capability
Send message
Send a prompt to a bot in an existing conversation. This is how you actually ask the bot questions.
08—10
3 capabilities in this set.
Part of 10 available through Cody AI.
- 08 Capability
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.
- 09 Capability
Get document status
Check if a document is done syncing. This tells you if the AI has finished learning the new info.
- 10 Capability
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.
Set up in minutes
One URL. Then ask Cody AI to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Cody AI from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_3sdhdxz69A9PNCbHGNcvaVvLSXZIq9OFM5te4LTv/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Cody AI, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Cody AI for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_3sdhdxz69A9PNCbHGNcvaVvLSXZIq9OFM5te4LTv/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Cody AI URL.
- Step 03
Save and start
Save the connection and enable Cody AI in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"cody-ai": {
"url": "https://edge.vinkius.com/vk_preview_3sdhdxz69A9PNCbHGNcvaVvLSXZIq9OFM5te4LTv/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Cody AI
Open Agent mode in chat and ask: "Using Cody AI, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"cody-ai": {
"url": "https://edge.vinkius.com/vk_preview_3sdhdxz69A9PNCbHGNcvaVvLSXZIq9OFM5te4LTv/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Cody AI
Ask Copilot: "Using Cody AI, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"cody-ai": {
"url": "https://edge.vinkius.com/vk_preview_3sdhdxz69A9PNCbHGNcvaVvLSXZIq9OFM5te4LTv/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Cody AI
Open Cascade and ask: "Using Cody AI, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"cody-ai": {
"url": "https://edge.vinkius.com/vk_preview_3sdhdxz69A9PNCbHGNcvaVvLSXZIq9OFM5te4LTv/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Cody AI
Ask Cline: "Using Cody AI, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add cody-ai --transport http "https://edge.vinkius.com/vk_preview_3sdhdxz69A9PNCbHGNcvaVvLSXZIq9OFM5te4LTv/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Cody AI
Ask Claude: "Using Cody AI, show me...". 10 tools are ready
Where the request belongs
Work Cody AI can move forward.
This is for the support lead who's tired of manual QA on bot answers or the knowledge manager who needs to update training data without digging through a complex UI.
Support Lead
Uses the Connector to check bot configurations and query answers to ensure the AI is hitting the right notes for customers.
Knowledge Manager
Imports new web pages and documents into the correct folders to keep the training data fresh without manual uploads.
Developer
Connects the bots to automated workflows to trigger actions based on specific knowledge base queries.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsBotsonic
Train custom AI chatbots on your own data to deliver instant, accurate support that learns from your knowledge base.
CHATFLY
Manage AI chatbots and knowledge bases via CHATFLY. train bots on custom data and track conversations directly from any AI agent.
VectorShift (AI Workflow & RAG Automation)
Automate AI workflows and RAG via VectorShift. manage pipelines, query knowledge bases, and deploy chatbots directly from any AI agent.
Chaindesk
Build no-code AI agents trained on your own data that handle customer support, lead qualification, and FAQ resolution.
Bot9
Manage your AI agents via Bot9. orchestrate bots, train them, and automate conversations directly from any AI agent.
FastGPT
Manage FastGPT Knowledge Bases. automate dataset creation, document ingestion, and RAG search directly from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Cody AI connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Cody AI.
The practical details behind the request, access and result.
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.
One connection away
Give your agent a direct line to Cody AI.
Connect Cody AI once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available