How to Use the FundraisingBox MCP in Pydantic AI

Q: How do I register the FundraisingBox MCP Server in Pydantic AI?

You initialize the connection using MCPToolset with your Vinkius server's HTTP URL. Pass this toolset directly to your Agent instance, and the framework will handle tool discovery and runtime validation for endpoints like listcampaigns.

Q: What happens if FundraisingBox returns unexpected data to my Pydantic AI agent?

If an endpoint like getdonorhistory returns a field that doesn't match your schema, Pydantic AI will raise a validation error. This prevents your agent from operating on malformed donor data and alerts you immediately to any schema mismatch on the MCP Server.

Q: Can I use Pydantic AI to validate recurring donations from FundraisingBox?

Yes, when calling listrecurringdonations, the framework validates the subscription amounts, intervals, and donor IDs against strict schemas. This ensures your recurring revenue calculations are always based on clean data.

Q: Does this setup support checking connection status?

Yes, you can call checkfundraisingboxstatus to verify the connection is active before running multi-step tasks. This is a quick way to ensure your agent can access donation forms and campaign data without network issues.

Build type-safe Pydantic AI agents with this MCP Server to validate every FundraisingBox donor record and transaction at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FundraisingBox MCP to Pydantic AI

Create your Vinkius account to connect FundraisingBox 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 FundraisingBox with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe FundraisingBox donor management with Pydantic AI

When your Pydantic AI agent pulls donor information using `get_donor`, a single missing field can break your downstream database sync. Pydantic AI solves this by validating every response against strict Python schemas before your code executes. If the FundraisingBox CRM returns unexpected data, the framework raises a clear validation error instead of failing silently. This strict validation applies to search operations too. When your Pydantic AI agent calls `search_donors`, the results are parsed and verified against your defined models. This guarantees that your agent always works with clean, structured FundraisingBox donor profiles, preventing runtime exceptions during automated email campaigns.

Validate FundraisingBox transactions using this MCP Server

Handling financial data requires absolute precision when your Pydantic AI agents retrieve records using `list_receipts` and `list_donations`. This MCP Server lets your agents safely process transactions while the framework validates the currency formats, timestamps, and amounts. This ensures your accounting scripts never process corrupt data. If you need to generate high-level reports, your Pydantic AI agent can call `get_dashboard` to pull active metrics. Pydantic AI checks the structure of this dashboard payload at runtime. You can confidently pass these validated FundraisingBox metrics to external reporting APIs without worrying about schema drift.

Validate FundraisingBox recurring donations and campaigns

Tracking FundraisingBox subscription gifts requires monitoring active intervals via `list_recurring_donations`. Your Pydantic AI agent can retrieve active plans with the framework validating every subscription interval and amount. This prevents your agent from making bad calculations when forecasting future revenue. You can also track active fundraising drives by calling `list_campaigns` and `list_donations_by_project`. Because Pydantic AI is model-agnostic, you can use these validated FundraisingBox tools with any LLM provider. Your agent will always receive structured, verified data, regardless of the underlying model's reasoning capabilities.

Setup guide

Set up FundraisingBox 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": {
        "fundraisingbox-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You initialize the connection using `MCPToolset` with your Vinkius server's HTTP URL. Pass this toolset directly to your `Agent` instance, and the framework will handle tool discovery and runtime validation for endpoints like `list_campaigns`.

If an endpoint like `get_donor_history` returns a field that doesn't match your schema, Pydantic AI will raise a validation error. This prevents your agent from operating on malformed donor data and alerts you immediately to any schema mismatch on the MCP Server.

Yes, when calling `list_recurring_donations`, the framework validates the subscription amounts, intervals, and donor IDs against strict schemas. This ensures your recurring revenue calculations are always based on clean data.

Yes, you can call `check_fundraisingbox_status` to verify the connection is active before running multi-step tasks. This is a quick way to ensure your agent can access donation forms and campaign data without network issues.

All operations involving donor profiles, donation receipts, and recurring donation plans are processed in memory within secure, ephemeral V8 isolates on Vinkius. The framework strictly validates data types locally, ensuring that raw financial records are never leaked or exposed to external APIs during validation.

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