How to Use the BallotReady MCP in Pydantic AI

Q: How do I configure BallotReady with Pydantic AI?

Use the MCPToolset class from the pydantic-ai-slimmcp package. Point it to your Vinkius HTTP endpoint and pass the toolset directly to your agent.

Q: Does Pydantic AI still support MCPServerHTTP for BallotReady?

No, that class is deprecated. You must use the unified MCPToolset approach to connect to external servers over Streamable HTTP or SSE transports.

Enforce strict typing on civic data with Pydantic AI and the BallotReady MCP server for hallucination-free agents.

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 Pydantic AI

Create your Vinkius account to connect BallotReady to Pydantic 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 BallotReady with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Election Data Retrieval

Missing a middle initial on a ballot is a big deal. When your agent calls `get_candidate` through the MCP integration, the response gets validated against your strict schemas at runtime. If the API returns a string where you expected an integer for the candidate ID, the framework fails loudly. You set this up using the unified `MCPToolset` approach. Pass the HTTP endpoint to your `Agent` and it automatically maps tools like `list_elections` and `list_positions`. You get absolute certainty that your election data matches your application's expectations.

BallotReady MCP Server for Pydantic

Building a voter guide requires precise geographic matching. Your agent executes `get_districts_by_address` and expects a very specific nested JSON structure in return. Pydantic AI catches any malformed district arrays before they corrupt your database. Vinkius hosts the external server, so you just plug in the URL. Your agent can safely run `get_officeholders` knowing that the returned list of politicians will strictly adhere to the models you defined. Zero silent corruption.

Model-Agnostic Civic Research

You might start building with OpenAI and switch to a local model later. Pydantic AI keeps your tool logic perfectly intact regardless of the LLM. The agent figures out how to call `get_ballot_measures` and `list_candidates` based on the exact same schemas. This framework forces the LLM to respect the boundaries of the civic data. It prevents the agent from hallucinating a fake local proposition because the output from `list_districts` must perfectly match the real-world API response.

Setup guide

Set up BallotReady MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "ballotready-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to BallotReady tools.",
)

result = await agent.run("List recent BallotReady transactions")
print(result.output)

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 Pydantic AI

Use the `MCPToolset` class from the `pydantic-ai-slim[mcp]` package. Point it to your Vinkius HTTP endpoint and pass the toolset directly to your agent.

Election data requires absolute precision. Pydantic AI guarantees that outputs from tools like `get_elections_by_address` match your data models exactly, throwing a validation error instead of passing bad data.

No, that class is deprecated. You must use the unified `MCPToolset` approach to connect to external servers over Streamable HTTP or SSE transports.

Yes. Because Pydantic AI is model-agnostic, you can swap out the underlying LLM at any time while keeping your election data pipelines perfectly intact.

Vinkius completely isolates every request. When you query a user's address to find their voting district, the execution happens in a single-use container that destroys itself the millisecond the data transfers back to your application.

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