How to Use the BallotReady MCP in Google ADK

Q: How do I register BallotReady tools in Google ADK?

Install the google-adk package and create a McpToolset using StreamableHttpServerParameters. Pass that toolset to your LlmAgent initialization and it will read the civic endpoints.

Q: Can I restrict which BallotReady tools my Google ADK agent sees?

You sure can. The toolset configuration accepts a toolnames list where you can specify exactly which functions the agent is allowed to execute, like restricting it to just listdistricts.

Q: How do I verify my Google ADK connection to the BallotReady API?

The server includes a specific getaccountcheck tool. Your agent can run this on startup to confirm the Vinkius endpoint token is valid before attempting any heavy data pulls.

Connect Gemini agents to live voter data using Google ADK and build enterprise civic applications on Google Cloud.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BallotReady MCP to Google ADK

Create your Vinkius account to connect BallotReady 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 BallotReady with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Live Civic Data into Gemini

Google ADK lets your enterprise agents pull real-time election data straight into Gemini's massive context window. You set up a `McpToolset` with your Vinkius URL and pass it to your `LlmAgent`. The agent immediately knows how to run `get_elections_by_address`. This setup shines when you combine it with Google Cloud infrastructure. Your agent grabs a list of upcoming races via `list_positions` and cross-references them against historical voting patterns stored in BigQuery. You get deep, data-driven political analysis without writing custom API wrappers.

Google ADK BallotReady MCP Server Setup

We built this for developers who want tight control over what their agents can do. If you only want your Gemini agent to look up incumbents, you use the `tool_names` filter to expose just `get_officeholders` and `get_account_check`. The integration supports both Stdio and HTTP transports natively. Since Vinkius handles the heavy lifting, your agent securely fetches candidate profiles using `get_candidate` while staying entirely within your Vertex AI environment.

Resolve Voter Geography at Scale

Mapping voters to their correct districts is usually a massive headache. Your Gemini agent uses `get_districts_by_address` over the MCP protocol to instantly resolve a street location into precise electoral boundaries. It pulls the exact local, state, and federal maps. Once the district is locked in, the agent cascades into other tools. It fires `list_candidates` to see who is running and `get_ballot_measures` to pull local propositions. Gemini reads all that structured data and synthesizes a localized voter guide in seconds.

Setup guide

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

Install the `google-adk` package and create a `McpToolset` using `StreamableHttpServerParameters`. Pass that toolset to your `LlmAgent` initialization and it will read the civic endpoints.

You sure can. The toolset configuration accepts a `tool_names` list where you can specify exactly which functions the agent is allowed to execute, like restricting it to just `list_districts`.

Yes. Your agent can pull live candidate data using the server and immediately write those insights into BigQuery tables for further analysis by your data science team.

The server includes a specific `get_account_check` tool. Your agent can run this on startup to confirm the Vinkius endpoint token is valid before attempting any heavy data pulls.

We run a zero-trust architecture. When your agent sends a home address to find local elections, the query executes in an isolated sandbox and the memory is wiped immediately after the response routes back to your cloud.

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