How do I connect my Coze account?

You need to generate a Personal Access Token (PAT) from your Coze profile settings and provide your Base URL to Vinkius. Once connected, your AI client can immediately start using the capabilities.

Which version of Coze should I use?

You can use either the international version (api.coze.com) or the China version (api.coze.cn). You just need to specify the correct Base URL when setting up the MCP.

Can I manage my RAG data through this MCP?

Yes. You can upload raw text documents, upload files via URLs, and delete specific documents from your datasets to manage your RAG optimization.

Does this work with any AI client?

This MCP works with any client that supports the Model Context Protocol, such as Claude, Cursor, Windsurf, and VS Code.

Can I talk to my bots directly?

Yes. The create_chat capability allows you to send messages to published bots and receive their responses within your agent's interface.

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.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Coze to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Control Coze bots and knowledge bases from your favorite AI client.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 11 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 11 available through Coze.

01
List bots
This capability shows you all the published bots currently active in a specific Coze Space.
02
Publish bot
Use this to take a Coze bot draft and make it live. It moves your bot from development to production.
03
Create chat
This capability starts a conversation with a Coze bot. You send a message and get the bot's response immediately.
04
Delete document
This capability removes a specific document from a dataset using its ID. It is useful for cleaning up outdated RAG data.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 11 available through Coze.

05
Get conversation history
This capability fetches the full list of previous messages from a specific conversation. It helps your agent maintain context.
06
List datasets
This capability retrieves a list of all knowledge base datasets within a designated Coze Space.
07
List workspaces
This capability pulls a list of all available Coze workspaces or spaces you have access to.
08
Submit tool outputs
This capability provides the necessary data when a bot calls for a plugin or human-in-the-loop input. It feeds the results back into the bot's workflow.

Capability set03 / 03

09-11

3 capabilities in this set.

Part of 11 available through Coze.

09
Upload document
This capability adds raw text files to your Coze Knowledge Base. It is the primary way to feed new data into your RAG system.
10
Upload file URL
Use this to pull an external file into Coze storage using its URL. It handles the transfer from the web to your Coze environment.
11
Clear conversation
Use this to wipe the message history of a conversation session. It resets the chat state.

Real work

What teams actually run

Automated Data Ingestion

You can tell your agent to upload multiple text files to a specific dataset to update a bot's knowledge.

Bot Debugging

Use the conversation history capability to review how a bot is responding to specific prompts.

Workspace Auditing

Quickly check which bots are published and which datasets are active in your Coze spaces.

Dynamic Bot Control

Publish new bot versions or clear chat histories without leaving your development environment.

Automate a task

Put Coze to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

How to debug and deploy bots

One connector, every AI

Coze works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Coze to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

850ms average. Fast in production.

Coze is checked daily against the live service.

Daily averagePeak 1029ms

Oct 3Today

Fastest day: 685ms
Slowest day: 1029ms
14-day trend: Slowing+6%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 11 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Coze, so you can see the experience inside your AI.

It does not authenticate your account with Coze. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Coze Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_0lEt3NxYVz4nTDDqHVx3BleKwHs5oApqZrMC3qwh/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Coze capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "coze-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_0lEt3NxYVz4nTDDqHVx3BleKwHs5oApqZrMC3qwh/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Coze in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Coze owners hand off.

This MCP is designed for technical users managing bot lifecycles and RAG-based AI systems.

01
Knowledge Engineers
They hand off document ingestion and dataset cleanup tasks to the agent.
02
RAG Developers
They use the agent to debug semantic search and manage knowledge base content.
03
System Integrators
They build complex workflows by connecting Coze bots to other AI-driven processes.

FAQ

Questions Coze owners ask.

01
How do I connect my Coze account?
You need to generate a Personal Access Token (PAT) from your Coze profile settings and provide your Base URL to Vinkius. Once connected, your AI client can immediately start using the capabilities.
02
Which version of Coze should I use?
You can use either the international version (api.coze.com) or the China version (api.coze.cn). You just need to specify the correct Base URL when setting up the MCP.
03
Can I manage my RAG data through this MCP?
Yes. You can upload raw text documents, upload files via URLs, and delete specific documents from your datasets to manage your RAG optimization.
04
Does this work with any AI client?
This MCP works with any client that supports the Model Context Protocol, such as Claude, Cursor, Windsurf, and VS Code.
05
Can I talk to my bots directly?
Yes. The create_chat capability allows you to send messages to published bots and receive their responses within your agent's interface.
06
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.
07
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.
08
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.

Explore

More in Industry Titans

Connect Coze to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

List bots

Publish bot

Create chat

Delete document

05-08

Get conversation history

List datasets

List workspaces

Submit tool outputs

09-11

Upload document

Upload file URL

Clear conversation

What teams actually run

Automated Data Ingestion

Bot Debugging

Workspace Auditing

Dynamic Bot Control

Building your own app? The connector is yours to use.

Coze Connector

Claude Desktop

Knowledge Engineers

RAG Developers

System Integrators

How do I connect my Coze account?

Which version of Coze should I use?

Can I manage my RAG data through this MCP?

Does this work with any AI client?

Can I talk to my bots directly?

Which Base URL should I use for my account?

Can I automatically list all published bots in a space?

How do I upload a new document to my knowledge base?

Mem AI (Knowledge Workspace) AI Connector

FastGPT AI Connector

rag-chunk-boundary-optimizer AI Connector

Bot9 AI Connector

Suggestions

VectorShift (AI Workflow & RAG Automation) AI Connector

RAG Chunk Optimization Calculator AI Connector

Botsonic AI Connector

RAG Chunk Selection Optimizer AI Connector