How to Use the Accessibility Checker MCP in Pydantic AI

Q: Can I use Accessibility Checker with Pydantic AI for ramp compliance?

Yes. The checkrampcompliance tool's output is also strictly validated. You can trust that any slope measurement or landing requirement reported back is formatted and correct.

For Pydantic AI: Type-safe compliance checks for reliable structural data validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Accessibility Checker MCP to Pydantic AI

Create your Vinkius account to connect Accessibility Checker to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Accessibility Checker with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Check Doorway Clearances

The `check_doorway` tool verifies if an entry point provides adequate clear opening width for mobility aid users. Because the response is typed, you know exactly what data fields to expect back—no garbage outputs. This function forces correctness when checking clearances, making sure your agent doesn't trust unexpected or corrupted dimensions.

Inspect Passageway Widths

Use `check_corridor_and_passage` to confirm if a corridor or passage meets minimum clear width. The response is validated against Pydantic models, guaranteeing the compliance status and violation details are structured correctly. You get reliable data every time. If the API sends anything unexpected, your agent fails loudly—you know immediately it's wrong.

Assess Bathroom Functionality

The `check_bathroom_spaciousness` tool confirms if a bathroom provides enough functional space for mobility aid maneuverability. Since the output is strictly typed, you can write code that relies absolutely on the returned compliance status. This means when your agent flags non-compliance, you're certain the reason and measurement are solid.

Setup guide

Set up Accessibility Checker 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": {
        "accessibility-checker-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Accessibility Checker 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 Accessibility Checker. 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 Accessibility Checker 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 Accessibility Checker MCP in Pydantic AI

The MCP response is validated against Pydantic models at runtime. This means your agent receives predictable, typed data, eliminating the risk of silent corruption or unexpected fields.

Yes. The `check_ramp_compliance` tool's output is also strictly validated. You can trust that any slope measurement or landing requirement reported back is formatted and correct.

It handles dimensional metrics related to widths, slopes, and clearances across structural elements like ramps, passages, and bathrooms.

Absolutely. The MCP is designed for model-agnostic use, ensuring that regardless of your underlying LLM (Anthropic, Gemini, etc.), the data received will be structurally sound.

You call the tools sequentially. The typed nature of the output makes chaining checks easy; you'll get reliable data for every single point in your building.

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