How to Use the DonorsChoose MCP in Pydantic AI

Q: How do I set up the DonorsChoose server with Pydantic AI?

Install the framework with pip install "pydantic-ai-slimmcp" and initialize the unified MCPToolset pointing to the Vinkius HTTP endpoint. Pass the toolset directly to your Agent instance to start querying classroom data.

Q: Can I use this MCP Server to filter school projects by subject in Pydantic AI?

Yes, you can run listprojectsbysubject through the agent. The framework validates the subject categories at runtime, ensuring your agent only processes valid educational topics like Math or Literacy.

Q: How is teacher request data secured when queried via Pydantic AI?

All classroom proposal details fetched by getclassroomprojectdetails pass through an ephemeral, zero-trust V8 sandbox. This prevents raw educational data from being cached or leaked during runtime validation.

Build type-safe education funding agents using Pydantic AI to validate school project data 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 DonorsChoose MCP to Pydantic AI

Create your Vinkius account to connect DonorsChoose 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 DonorsChoose with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict schemas on DonorsChoose project queries

Stop worrying about silent API failures when tracking classroom needs with `get_classroom_project_details`. When your agent calls this tool, the response is parsed against strict Pydantic models. You get clean, type-safe Python objects for every classroom request, ensuring your downstream database inserts never break.

Validate high-poverty school data at runtime

Ensure your donation matching logic only processes valid school profiles by querying `list_high_poverty_needs` inside your Pydantic AI agent. The framework works with any LLM provider, letting you switch models while keeping your data validation intact. Your agent can fetch urgent classroom needs using `list_urgent_funding_needs` and guarantee the structure matches your exact schema.

Query local school projects with strict ZIP code validation

Keep your geographic searches accurate by validating inputs before running `search_projects_by_zipcode`. The agent can then safely process the returned list of local proposals. It can also run `list_projects_by_subject` to categorize local school needs by topic, confident that every data point matches your type definitions.

Setup guide

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

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

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

Install the framework with `pip install "pydantic-ai-slim[mcp]"` and initialize the unified `MCPToolset` pointing to the Vinkius HTTP endpoint. Pass the toolset directly to your Agent instance to start querying classroom data.

The framework will raise a validation error immediately instead of passing corrupted data to your agent. This ensures your code fails safely when parsing complex school metadata from `get_donorschoose_api_metadata`.

Yes, you can run `list_projects_by_subject` through the agent. The framework validates the subject categories at runtime, ensuring your agent only processes valid educational topics like Math or Literacy.

No, Vinkius hosts and manages the MCP Server externally. Your Pydantic AI agent connects over a secure streamable HTTP or SSE transport, meaning you don't have to manage any local infrastructure.

All classroom proposal details fetched by `get_classroom_project_details` pass through an ephemeral, zero-trust V8 sandbox. This prevents raw educational data from being cached or leaked during runtime 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