Coze Connector for AI agents.
11 live capabilities
Manage bot lifecycles and RAG datasets programmatically.
Waiting for input…
Why people use Coze
Coze for Automated RAG Data Management
This Connector changes that. Your agent handles the ingestion for you. Just tell it which file to push to which dataset, and it handles the rest. You get a system that stays updated without the manual overhead.
What Vinkius changes
You get a programmatic way to manage your entire Coze bot ecosystem from a single chat interface.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Updating RAG data
A user tells their agent to upload 'safety_guidelines.
- Real-world use case 02
Checking bot status
A developer asks if their bots are live in the 'Customer Support' space.
- Real-world use case 03
Handling plugin walls
A bot gets stuck needing a tracking ID.
Complete set · 11capabilities
The complete Coze capability set.
These are the exact actions your AI can choose when you ask it to work with Coze.
01—04
4 capabilities in this set.
Part of 11 available through Coze.
- 01 Capability
Publish bot
Publish a Coze Bot draft. This moves your bot from a test state to a live environment.
- 02 Capability
Submit capability outputs
Submit outputs for capabilities/plugins required by the bot. This lets your agent provide data for bot actions.
- 03 Capability
Upload document
Upload a raw text document to a Knowledge Base. This keeps your RAG data updated with new files.
- 04 Capability
Create chat
Send a message to a Coze bot and get a response. This lets your agent interact with bots directly.
05—08
4 capabilities in this set.
Part of 11 available through Coze.
- 05 Capability
Upload file url
Upload an external file URL to Coze storage. Use this to bring in files hosted on other sites.
- 06 Capability
List bots
List published bots in a specific Coze Space. Use this to see what's live in your workspace.
- 07 Capability
List datasets
List knowledge base datasets in a Coze Space. This helps you see all your available RAG sources.
- 08 Capability
List workspaces
List available Coze workspaces/spaces. Use this to navigate different projects in your account.
09—11
3 capabilities in this set.
Part of 11 available through Coze.
- 09 Capability
Clear conversation
Clear all messages from a conversation session. This resets the chat history for a clean start.
- 10 Capability
Delete document
Delete documents from a dataset by ID. Use this to remove outdated or incorrect information.
- 11 Capability
Get conversation history
Retrieve the message list from a conversation. This lets your agent see what's been said previously.
Set up in minutes
One URL. Then ask Coze to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Coze 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_0lEt3NxYVz4nTDDqHVx3BleKwHs5oApqZrMC3qwh/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 Coze, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Coze for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_0lEt3NxYVz4nTDDqHVx3BleKwHs5oApqZrMC3qwh/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 Coze URL.
- Step 03
Save and start
Save the connection and enable Coze in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"coze": {
"url": "https://edge.vinkius.com/vk_preview_0lEt3NxYVz4nTDDqHVx3BleKwHs5oApqZrMC3qwh/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 Coze
Open Agent mode in chat and ask: "Using Coze, help me...". 11 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"coze": {
"url": "https://edge.vinkius.com/vk_preview_0lEt3NxYVz4nTDDqHVx3BleKwHs5oApqZrMC3qwh/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 Coze
Ask Copilot: "Using Coze, help me...". 11 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"coze": {
"url": "https://edge.vinkius.com/vk_preview_0lEt3NxYVz4nTDDqHVx3BleKwHs5oApqZrMC3qwh/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 Coze
Open Cascade and ask: "Using Coze, help me...". 11 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"coze": {
"url": "https://edge.vinkius.com/vk_preview_0lEt3NxYVz4nTDDqHVx3BleKwHs5oApqZrMC3qwh/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 Coze
Ask Cline: "Using Coze, help me...". 11 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add coze --transport http "https://edge.vinkius.com/vk_preview_0lEt3NxYVz4nTDDqHVx3BleKwHs5oApqZrMC3qwh/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 Coze
Ask Claude: "Using Coze, show me...". 11 tools are ready
Where the request belongs
Work Coze can move forward.
This is for the engineers and developers who are tired of manual copy-paste workflows when building RAG systems or managing hundreds of bot interactions.
Knowledge Engineer
Automate document ingestion and cleanup for RAG datasets to keep information accurate.
RAG Developer
Debug search results and optimize chunking by programmatically updating datasets.
System Integrator
Build complex workflows that require dynamic knowledge base management and capability output submission.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsTencent Yuanqi
Orchestrate Tencent Yuanqi AI Agents. manage assistants, trigger conversations, and handle RAG documents directly from any AI agent.
SmartChatAI
Manage AI bots, knowledge bases, and messaging on SmartChatAI with AI agents.
ThinkStack
Manage AI chatbots via ThinkStack u2014 query bots, manage knowledge sources, review conversations, and configure actions from your AI agent.
Voiceflow
Design, prototype, and launch conversational AI agents with a visual builder that handles complex dialog flows without code.
GPTBots
Manage your conversational AI agents, workflows, and knowledge bases via AI.
ChatBot.com
Manage conversational AI and bot workflows via ChatBot. track stories, interactions, and user data directly from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Coze 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 Coze.
The practical details behind the request, access and result.
Can the Coze MCP help me update my RAG knowledge base?
Yes. It lets your agent upload documents and delete old ones directly from the knowledge base, keeping your data current without manual uploads.
How do I manage multiple Coze bots with this Connector?
You can list all workspaces and bots across your account. This helps you monitor your entire bot ecosystem from a single interface.
Can I use this to handle complex bot actions?
Yes. It allows your agent to submit capability outputs, which is perfect for handling human-in-the-loop tasks or providing data for external plugins.
Does Coze MCP support multi-turn conversations?
It does. Your agent can engage in persistent conversations with your bots, maintaining context over multiple turns.
Is Coze MCP good for knowledge engineers?
It's built for them. It automates the ingestion of documentation across multiple datasets, making it much easier to manage large-scale RAG systems.
How does Coze MCP handle workspace management?
It provides capabilities to list all available workspaces and spaces, letting you navigate and manage different projects programmatically.
Which Base URL should I use for my account?
If you are using the international version, use https://api.coze.com. For the Chinese version, use https://api.coze.cn.
Can I automatically list all published bots in a space?
Yes! Use the list_bots capability with your Space ID. Your agent will return a list of all bots that have been published and are ready for interaction.
How do I upload a new document to my knowledge base?
Use the upload_document capability with the target Dataset ID and the raw text content. Your agent will handle the ingestion process into the Coze RAG engine.
One connection away
Give your agent a direct line to Coze.
Connect Coze once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available