# Coze MCP for AI Agents AI Agent Connect

> Coze MCP connects your AI agents to the Coze bot orchestration platform. It lets you manage bot lifecycles, handle multi-turn conversations, and manage RAG datasets programmatically. Use it to push documents to knowledge bases, monitor workspaces, and submit tool outputs for complex workflows.

## Overview
- **Category:** industry-titans
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_0lEt3NxYVz4nTDDqHVx3BleKwHs5oApqZrMC3qwh/ai-agent-connect
- **Tags:** coze, bytedance, bot-orchestration, rag-optimization, knowledge-base

## Description

This Connector gives your AI agent the keys to a major bot orchestration platform, letting it handle the heavy lifting of bot management. Instead of jumping between tabs to update knowledge bases or check bot statuses, your agent can do it for you. You can have it ingest new documents into specific datasets to keep your RAG systems fresh, or manage how bots interact with users across different workspaces. It even handles the tricky parts of human-in-the-loop workflows by submitting tool outputs when a bot hits a wall. It's a massive shortcut for anyone tired of manual data entry or constant context switching. When you find this in the Vinkius catalog, you're getting a direct line to high-end orchestration tools, making it way easier to scale your bot network without the usual friction. It's about making your AI agent a true operator rather than just a front-end interface.

## Tools

### publish_bot
Publish a Coze Bot draft. This moves your bot from a test state to a live environment.

### submit_tool_outputs
Submit outputs for tools/plugins required by the bot. This lets your agent provide data for bot actions.

### upload_document
Upload a raw text document to a Knowledge Base. This keeps your RAG data updated with new files.

### create_chat
Send a message to a Coze bot and get a response. This lets your agent interact with bots directly.

### upload_file_url
Upload an external file URL to Coze storage. Use this to bring in files hosted on other sites.

### list_bots
List published bots in a specific Coze Space. Use this to see what's live in your workspace.

### list_datasets
List knowledge base datasets in a Coze Space. This helps you see all your available RAG sources.

### list_workspaces
List available Coze workspaces/spaces. Use this to navigate different projects in your account.

### clear_conversation
Clear all messages from a conversation session. This resets the chat history for a clean start.

### delete_document
Delete documents from a dataset by ID. Use this to remove outdated or incorrect information.

### get_conversation_history
Retrieve the message list from a conversation. This lets your agent see what's been said previously.

## Prompt Examples

**Prompt:** 
```
I need to add the new training manual to our 'HR_Knowledge' dataset. Here's the text.
```

**Response:** 
```
I've received the text. I'm uploading it to the 'HR_Knowledge' dataset now. It will be indexed for your RAG workflows shortly.
```

**Prompt:** 
```
Show me all the bots we have live in the 'Marketing' workspace.
```

**Response:** 
```
I've checked the 'Marketing' workspace. Here are your live bots:

| Bot Name | ID | Status |
| :--- | :--- | :--- |
| Lead Gen | bot_99 | Live |
| Content Helper | bot_88 | Live |

Would you like to see the draft bots as well?
```

**Prompt:** 
```
The bot is stuck on the 'Shipping Info' step. It needs the tracking ID: 12345XYZ.
```

**Response:** 
```
I'm submitting the tracking ID 12345XYZ to the bot's plugin. It should proceed with the shipping update now.
```

## Capabilities

### Talk to published bots
Your agent can engage in multi-turn conversations with any bot in your space while keeping a persistent history.

### Update knowledge bases
Push new text documents into specific datasets to keep your RAG information current automatically.

### Monitor bot workspaces
Get a high-level view of all your active spaces and published bots from a single interface.

### Publish bot drafts
Move your bot configurations from a draft state to live status with a single command.

### Submit external tool results
Provide the necessary data for bots to complete complex actions involving external plugins.

## Use Cases

### Updating RAG data
A user tells their agent to upload 'safety_guidelines.txt' to the 'Operations' dataset. The agent uses upload_document to keep the RAG system current.

### Checking bot status
A developer asks if their bots are live in the 'Customer Support' space. The agent uses list_bots to verify the status of the entire fleet.

### Handling plugin walls
A bot gets stuck needing a tracking ID. The user provides it, and the agent uses submit_tool_outputs to give the bot the data it needs to continue.

### Cleaning up datasets
A user wants to remove old 2022 reports from a knowledge base. The agent uses delete_document to purge the outdated information.

## Benefits

- Update RAG data instantly by using upload_document to push new info into your knowledge bases without manual uploads.
- Manage multiple bot environments at once using list_workspaces to see every project in your account from one place.
- Handle complex bot actions by using submit_tool_outputs to provide the data your bots need for external plugins.
- Keep your bot history clean by using clear_conversation to reset sessions whenever a user needs a fresh start.
- Speed up bot deployment by using publish_bot to move drafts to live status without leaving your AI client.

## How It Works

The bottom line is you get a programmatic way to manage your entire Coze bot ecosystem from a single chat interface.

1. Get a Personal Access Token from your Coze profile settings.
2. Provide your Base URL and token to your AI client.
3. Ask your agent to manage your bots, datasets, or conversations.

## Frequently Asked Questions

**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 tool 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 tools 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` 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.