How to Use the Indy MCP in Google ADK

Q: How do I connect the Indy MCP Server to a Google ADK agent?

Pass the Vinkius HTTP URL into the McpToolset constructor inside your Python script. The toolset exposes all 12 endpoints to your Gemini model.

Q: Is it possible to limit which Indy tools my Google ADK agent can access?

Yes, pass a specific list of allowed tools to the McpToolset parameters. This stops the agent from executing administrative tasks like deletewebhook.

Q: How does Google ADK analyze massive amounts of form submissions using this MCP Server?

The agent pulls hundreds of entries using listrecords and loads them into Gemini's long-context window. This allows the model to find patterns across your entire client history in one pass.

Q: Is my sensitive freelance contract data safe with Google ADK?

Yes, all data retrieved via listrecords is processed in ephemeral V8 sandboxes. Vinkius ensures your client intake records are encrypted in transit and never exposed to public LLM training loops.

Feed your freelance business metrics into Google ADK using this MCP Server to run deep analytics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Indy MCP to Google ADK

Create your Vinkius account to connect Indy 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 Indy with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync Indy Form Data into BigQuery with Google ADK

The `list_records` tool extracts all form submissions so your Google ADK agent can feed them directly into your BigQuery warehouse. This pipeline lets you run SQL queries on your freelance lead conversion rates without exporting CSV files manually. Because Gemini handles over one million tokens of context, the agent analyzes months of historical submissions fetched via `get_record`. It spots trends in client budgets and project scopes that standard analytics tools miss.

Live Event Pipelines using Google ADK and Webhooks

Live freelance events route directly into your Google Cloud functions via the `create_webhook` tool. This allows your Google ADK agent to trigger automated background checks or send welcome emails the second a client submits a form. When you close a project, the agent calls `delete_webhook` to tear down the cloud endpoint and prevent orphaned serverless runs. This strict lifecycle management keeps your Google Cloud infrastructure clean and cost-effective.

Dynamic Form Generation via Enterprise Prompts

Generating brand-new intake flows is automated by the `create_form` tool based on raw unstructured RFPs. Your Google ADK agent reads a massive PDF proposal, extracts the required fields, and generates the matching form using this MCP Server integration. Verify the layout immediately using `get_form` to ensure the structure matches your enterprise branding rules. This eliminates the back-and-forth of manual form design for complex corporate clients.

Setup guide

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

Pass the Vinkius HTTP URL into the `McpToolset` constructor inside your Python script. The toolset exposes all 12 endpoints to your Gemini model.

Yes, pass a specific list of allowed tools to the `McpToolset` parameters. This stops the agent from executing administrative tasks like `delete_webhook`.

The agent pulls hundreds of entries using `list_records` and loads them into Gemini's long-context window. This allows the model to find patterns across your entire client history in one pass.

The Google ADK framework catches the API error and lets your agent log the failure directly to Google Cloud Logging for quick debugging.

Yes, all data retrieved via `list_records` is processed in ephemeral V8 sandboxes. Vinkius ensures your client intake records are encrypted in transit and never exposed to public LLM training loops.

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