How to Use the Bolt MCP in Google ADK

Q: Can I use Google ADK to filter specific Bolt tools?

Yes, use the toolnames argument in your McpToolset configuration. This lets you expose only getorderdetails while hiding sensitive tools like refundtransaction.

Analyze and action Bolt transactions directly from your enterprise Google ADK MCP pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bolt MCP to Google ADK

Create your Vinkius account to connect Bolt 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 Bolt with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync Bolt transaction data with Gemini context

The `list_transactions` tool pulls recent payment records directly into your Gemini long-context window. Your Google ADK agent parses thousands of transaction records at once, matching them against BigQuery tables to spot payment anomalies. Because Gemini handles massive token limits, you can feed entire histories retrieved by this tool into a single reasoning step. This allows your enterprise pipeline to run complex fraud checks without hitting context walls.

Audit merchant accounts with Google ADK MCP Server

The `get_merchant_status` tool checks whether your store is ready to accept payments. Your Google ADK agent runs this check before executing downstream Vertex AI tasks, ensuring your sales environment is fully operational. You configure the McpToolset with your Vinkius HTTP transport URL to expose these status checks to your enterprise agents. The agent uses this real-time status to route purchase orders or flag system outages on Google Cloud.

Manage payment captures in Vertex workflows

The `capture_transaction` tool settles pre-authorized payments directly from your agentic workflows. Your Google ADK setup triggers this tool when warehouse events in your Google Cloud infrastructure signal that an order is ready to ship. You can also use `void_transaction` to cancel authorizations if stock checks fail. By restricting the McpToolset tool_names filter, you ensure your fulfillment agent only sees these two payment-clearing tools.

Setup guide

Set up Bolt 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 Bolt 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="Bolt_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Bolt 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 Bolt. 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 Bolt 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 Bolt MCP in Google ADK

Import McpToolset and pass your Vinkius HTTP URL to StreamableHttpServerParameters. Then, add this toolset to your LlmAgent instance.

Yes, use the tool_names argument in your McpToolset configuration. This lets you expose only `get_order_details` while hiding sensitive tools like `refund_transaction`.

The ADK manages HTTP transport retries natively. If a call to `list_webhooks` fails, the framework raises a standard transport exception that you can catch in your Google Cloud run loop.

No, Vinkius hosts the MCP server in a zero-trust sandbox. Your Google ADK agent connects directly to the managed HTTP endpoint, removing the need for local node processes.

Yes, Vinkius processes all checkout tokens and account details inside ephemeral V8 sandboxes. No payment data is cached on disk, and Google ADK communications are encrypted in transit via TLS.

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