How to Use the Coze MCP in Mastra AI

Q: Can Mastra AI require approval before publishing a Coze bot?

Yes. You can enable requireToolApproval on the publishbot action. The workflow pauses and waits for human confirmation before pushing the draft live.

Q: Can I branch logic based on Coze chat responses in Mastra AI?

Your workflow can evaluate the output from createchat. If the bot returns a specific keyword, you can route the execution to a different set of tools or notify an admin.

Build resilient conditional workflows that manage Coze bots and RAG datasets using Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coze MCP to Mastra AI

Create your Vinkius account to connect Coze to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Coze with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Coze bot deployments

Moving bots from draft to production shouldn't require clicking through a web interface. Connecting this MCP Server to Mastra AI lets you handle the release cycle with built-in retry logic if the API times out. Set up a workflow that runs `publish_bot`. If the deployment fails, the framework catches the error and applies exponential backoff before trying again. You can verify the rollout by checking `list_bots` in the next step.

Sync external files to Coze via Mastra AI

Keeping your knowledge base accurate requires constant updates. By adding this MCP toolset to your workflow, your agent can replace old versions in Coze whenever a file changes in your external storage. Create a branch that triggers `delete_document` to remove the outdated record. The next node runs `upload_file_url` to pull the fresh data in. Mastra handles the sequential execution and alerts you if either step breaks.

Manage chat session memory

Long-running bots accumulate massive context windows that slow down responses. You need a reliable way to dump old data while keeping the active session clean. Your workflow can pull the recent log using `get_conversation_history` and save it to a database. Once archived, the agent fires `clear_conversation` to reset the context. This MCP Server makes the entire cleanup process programmable.

Setup guide

Set up Coze MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Coze tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "coze-mcp-client",
  servers: {
    "coze-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Coze Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Coze tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Coze transactions"
);
console.log(result.text);

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Coze now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Coze MCP in Mastra AI

Install @mastra/mcp@latest and instantiate a new MCPClient with your server URL. Call listTools() and spread the results directly into your agent's tool array. The framework automatically detects the transport layer.

Yes. You can enable requireToolApproval on the publish_bot action. The workflow pauses and waits for human confirmation before pushing the draft live.

The framework includes automatic retries with exponential backoff. If a tool hits a limit, the agent waits and tries again without crashing the entire run.

Your workflow can evaluate the output from create_chat. If the bot returns a specific keyword, you can route the execution to a different set of tools or notify an admin.

Vinkius routes your external file URLs and knowledge base text through a zero-trust architecture. The isolated environment drops all network connections immediately after the request finishes. Your credentials never persist on disk.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript