How to Use the Every.org MCP in Pydantic AI

Q: How does Pydantic AI validate Every.org search results?

Every tool response is mapped to a Pydantic model. If searchnonprofits returns data that doesn't match your schema, the framework raises a validation error.

Q: Can I check the Every.org API health inside Pydantic AI?

You can. Calling checkeveryorgstatus is a standard tool invocation. It returns a boolean or status string that your agent can use for flow control.

Use Pydantic AI for type-safe Every.org integrations. Ensure every donation and nonprofit search matches your schema exactly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Every.org MCP to Pydantic AI

Create your Vinkius account to connect Every.org 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 Every.org with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict types for Every.org data

Pydantic AI validates every response from `get_nonprofit` or `search_nonprofits` against your defined models. If the Every.org API returns unexpected fields, the agent stops immediately, preventing silent data corruption. This is critical when handling sensitive records like tax-deductible donation receipts. You get the peace of mind that your agent is only working with data that fits your exact application requirements.

Build reliable donation workflows with Pydantic AI

When you call `create_donation`, Pydantic AI ensures the input parameters are correct before the request leaves your system. This reduces the risk of API errors caused by malformed data. Your agent can then use `list_donations` to reconcile state. Because the framework validates these responses, you know your internal logs are always accurate and ready for audit.

Explore Every.org causes with type-safe agents

Use `browse_causes` and `get_featured` to pull data into your agent. Pydantic AI models the output, so your code always knows exactly what it's getting back from the server. This makes building complex logic for `create_fundraiser` much simpler. Your agent handles the data mapping, and Pydantic AI handles the safety checks, leaving you with code that just works.

Setup guide

Set up Every.org 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": {
        "everyorg-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Every.org 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 Every.org. 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 Every.org 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 Every.org MCP in Pydantic AI

Every tool response is mapped to a Pydantic model. If `search_nonprofits` returns data that doesn't match your schema, the framework raises a validation error.

It is. You initialize the MCPToolset with the server URL and pass it to your agent. Pydantic AI handles the rest, including type-safe tool calls.

You can. Calling `check_everyorg_status` is a standard tool invocation. It returns a boolean or status string that your agent can use for flow control.

Your Pydantic model will catch it. If your schema expects a value, the framework throws a validation error, preventing your agent from hallucinating.

The server uses secure transport, and Pydantic AI limits access to data via strict type definitions. Only authorized tools can touch your donation records.

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