How to Use the Coze MCP in Google ADK

Q: Can I limit which Coze tools are exposed to my Google ADK agent?

Yes. You can use the toolnames filter when initializing McpToolset to restrict access. For example, you can expose only createchat and block destructive tools like deletedocument.

Q: Can my agent upload files directly from Google Cloud Storage?

Yes. Your agent can grab the GCS signed URL and pass it to uploadfileurl. The server will fetch the file and index it into your specified Coze dataset.

Run enterprise Coze bot workflows inside Google ADK using Gemini's massive context window and this MCP Server.

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 Google ADK

Create your Vinkius account to connect Coze to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed BigQuery data directly into Coze bots

Google ADK excels at pulling massive datasets from GCP infrastructure. By combining it with this MCP Server, your Gemini agent can query BigQuery and write those results straight to Coze using `upload_document`. You don't need to write custom integration pipelines. The Google ADK agent uses `list_datasets` to find the right target, then uploads the structured data so your Coze bots always work with fresh warehouse data.

Process massive context windows with Google ADK

Gemini's million-token context lets you analyze entire conversation histories at once. Your Google ADK agent can call `get_conversation_history` to pull massive Coze chat threads, digest them, and then run `clear_conversation` to reset the session. This setup avoids the chunking issues common in smaller models. The Google ADK agent handles the high-level reasoning across hours of Coze chat logs, then uses `create_chat` to send highly summarized instructions back to your bot.

Automate bot deployments from GCP

Manage your conversational assets alongside your cloud infrastructure. Your Google ADK agent can list available workspaces with `list_workspaces`, check active configurations, and deploy draft updates to Coze using `publish_bot`. This brings DevOps-style control to your conversational agents. Instead of manually clicking through dashboards, your Google ADK agent handles the lifecycle of your Coze bots programmatically.

Setup guide

Set up Coze MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Coze tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Coze_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Coze tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Use the McpToolset class with StreamableHttpServerParameters pointing to your Vinkius URL. Pass that toolset directly to your LlmAgent constructor to expose tools like `create_chat` to Gemini.

Yes. You can use the tool_names filter when initializing McpToolset to restrict access. For example, you can expose only `create_chat` and block destructive tools like `delete_document`.

Since Gemini models support massive token limits, your agent can ingest the entire payload from `get_conversation_history` without truncation. This lets the agent perform deep analysis of long-running bot interactions.

Yes. Your agent can grab the GCS signed URL and pass it to `upload_file_url`. The server will fetch the file and index it into your specified Coze dataset.

Your credentials are encrypted and stored securely in the Vinkius managed environment. They are injected into the tool execution context on demand and never exposed to the Google ADK runtime or your Gemini model.

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