Coze MCP for AI. Manage Bot Deployments and Knowledge Bases
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Coze MCP lets you manage entire bot lifecycles—from publishing drafts to running complex conversations and manipulating knowledge bases. You can programmatically list workspaces, upload documents for RAG, chat with bots in real-time, or submit tool outputs when the bot needs external results.
What your AI can do
Create chat
Starts a new conversation with a specified Coze bot and returns the initial response.
List bots
Shows all published bots available within a specified Coze Space.
List datasets
Returns a list of knowledge base datasets housed in the current Coze Space.
Send messages to any published bot and track the full history of the conversation.
Upload raw documents or link external files into specific knowledge base datasets for AI context.
List all available workspaces, published bots, and active datasets across your Coze account.
Submit results from external tools or plugins when a bot requires human-in-the-loop input.
Ask an AI about this
Waiting for input…
Coze: 11 Tools for Bot & Data Management
These tools let your agent interact with the Coze backend to perform actions like uploading data, managing conversations, or listing available bots.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Coze on VinkiusCreate Chat
Starts a new conversation with a specified Coze bot and returns the initial response.
List Bots
Shows all published bots available within a specified Coze Space.
List Datasets
Returns a list of knowledge base datasets housed in the current Coze Space.
List Workspaces
Provides a list of all available Coze workspaces across your account.
Publish Bot
Makes a draft Coze bot visible and operational to other users.
Submit Tool Outputs
Sends external results back into the conversation when a bot requires human or plugin data.
Upload Document
Adds raw text files directly to a designated knowledge base dataset.
Upload File Url
Ingests content from an external web URL into the Coze storage system.
Clear Conversation
Resets all messages from a specific bot chat session.
Delete Document
Removes specific documents from a knowledge base dataset using its unique ID.
Get Conversation History
Retrieves the complete list of messages that took place in a past conversation...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Coze integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Coze, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Coze. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 11 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Keeping AI Context Up-to-Date Is a Pain Point
Today, updating a bot's knowledge base means logging into the platform and manually uploading new documents or links. If you have hundreds of pages of updated documentation, that process is slow, error-prone, and requires constant copy-pasting across multiple interfaces.
With this MCP, your agent takes over the tedious work. You can programmatically feed new information—whether it's a raw text file using `upload_document` or content from an external link via `upload_file_url`. The bot instantly gets access to fresh context without human intervention.
Managing Bot Conversations with Coze
The manual steps that disappear include starting a new chat, manually clearing old data before a test run, and then checking the chat history to see exactly what was said. It's all separate clicks in different tabs.
Now, your agent handles it all in sequence. You can start the conversation with `create_chat`, review the whole exchange using `get_conversation_history`, and finish the test by calling `clear_conversation`. The process is clean, predictable, and runs automatically.
What your AI can actually do with this
This connector gives your AI agent full control over the Coze platform. Instead of just chatting with a finished bot, you manage the whole system—the knowledge base, the conversations, and the development process itself. You can upload documentation to various datasets, keeping your Retrieval-Augmented Generation (RAG) context fresh. Need to test how a bot behaves? Use it; chat with published bots and keep track of every message sent or received.
The power here is managing actions: if an AI needs human input or results from another service, you can programmatically submit those tool outputs. You can also check what spaces are available across your account or list the specific bots already deployed within a space. It's essentially giving your agent access to the entire backend workflow of Coze, making it easy to build complex automation flows right from Vinkius.
019d842a-de90-71a0-a6f0-fcd3af8513fe 
Here's how it actually works
The bottom line is that you get a single connection point to run complex, multi-step AI workflows across the entire Coze ecosystem.
Subscribe to this MCP, then sign up at the Coze platform and generate your Personal Access Token (PAT).
Identify your required Base URL (e.g., for international or China regions) and connect your credentials via Vinkius.
Your agent can now access all 11 tools, allowing it to manage bot interactions and data lifecycles programmatically.
Who is this actually for?
Knowledge Engineers who waste hours manually updating documentation datasets. RAG Developers trying to debug why semantic search fails. System Integrators building mission-critical, stateful bot pipelines.
Needs to automate the ingestion of new technical manuals and ensure that all historical documentation is indexed correctly in multiple datasets.
Spends time debugging why a bot gives outdated answers, needing to programmatically delete old documents or check conversion history.
Builds complex multi-step workflows that require dynamic management of both the AI's conversation state and external tool outputs.
What Changes When You Connect
You can manage the entire development pipeline. Use list_bots to see what's deployed, and then use publish_bot to make a draft live immediately.
Debugging RAG is now programmatic. Instead of guessing, you can use delete_document or upload_document to precisely control the content indexed by the bot.
Conversation state never gets lost. Check the full context using get_conversation_history, and if needed, wipe the slate clean with clear_conversation before a new test run.
The system handles external data gracefully. If your bot needs results from an external service, you simply use submit_tool_outputs to feed the data back into the chat context.
You can automate content ingestion by linking documents via URL using upload_file_url, or push raw text directly with upload_document.
See it in action
A bot's answers are based on old manuals.
The agent needs to update its knowledge. Instead of manually uploading PDFs, the developer uses upload_file_url to pull content from a new SharePoint site and then runs list_datasets to confirm the data landed in the right place.
Testing bot functionality after a major feature change.
Before deploying, the developer uses create_chat to run a test conversation. After testing is done, they use clear_conversation so that subsequent tests start from a clean slate.
Needing to check which bots are available in a project space.
The architect uses list_workspaces first to find the correct environment, then runs list_bots on that workspace to see every bot built for that specific client.
A complex workflow requires human approval before continuing.
The agent hits a roadblock and needs external data. Instead of failing, the system uses submit_tool_outputs, allowing the developer's agent to inject the required final results and proceed.
The honest tradeoffs
Relying only on manual UI uploads
Manually clicking through the Coze dashboard, uploading a document, waiting for indexing, then repeating this process when 50 new files arrive.
Instead, use upload_document or upload_file_url to automate ingestion. For batch updates, run your agent to manage the data flow via these tools.
Assuming conversation history persists forever
Rerunning a test and getting confused because the bot is still referencing messages from three days ago.
Always call clear_conversation at the start of any new session to guarantee a clean, predictable chat experience.
Forgetting to publish changes
A developer finishes building a bot draft and assumes it's live for testing by QA, only for QA to report that the bot is unresponsive.
After finishing development, use publish_bot to make sure the work moves from draft status into an active, usable state.
When It Fits, When It Doesn't
Use this MCP if your process involves managing the entire lifecycle of AI bots or knowledge bases. You need more than just a chat interface; you need control over the content (via upload_document and delete_document), the deployment status (list_bots, publish_bot), and the conversation state management (create_chat, get_conversation_history). Don't use this if your only goal is to ask a simple question. If you just want chat access, there are simpler connectors available that focus solely on message passing without needing full backend control.
Questions you might have
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 tool 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 tool with the target Dataset ID and the raw text content. Your agent will handle the ingestion process into the Coze RAG engine.
How do I use the `get_conversation_history` tool to check a session's full message list? +
It retrieves every message sent and received for that specific chat ID. This is critical for debugging multi-turn conversations or reconstructing user context when building complex workflows.
What happens when I need to provide external data using `submit_tool_outputs`? +
You pass structured outputs needed by the bot's tools or plugins. This mechanism allows your agent to complete multi-step workflows that require manual input or results from an external API.
Can I use `delete_document` if a knowledge base dataset contains outdated information? +
Yes, you delete documents using their unique ID within the specific dataset. This is necessary for maintaining accurate RAG context and preventing semantic search errors based on old data.
After designing a bot, how do I use `publish_bot` to make it available? +
Running publish_bot takes your draft configuration and makes the bot accessible for user interaction within a defined Coze Space. This action completes the deployment cycle.
How do I find all available operational scopes using `list_workspaces`? +
This tool fetches a list of all active workspaces attached to your account. Knowing these spaces helps you correctly scope subsequent bot management tasks and deployments.
We've already built the connector for Coze. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 11 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.