How to Use the DonorsChoose MCP in OpenAI Agents SDK

Q: How do I initialize the DonorsChoose server using the OpenAI Agents SDK?

Install the package with pip install openai-agents and set up the streamable HTTP parameters. You pass MCPServerStreamableHttp pointing to the Vinkius endpoint directly into your agent constructor. The SDK automatically registers the school search tools.

Q: How does the OpenAI Agents SDK handle expired school projects on DonorsChoose?

Your agent can check expiration dates by calling listurgentfundingneeds. If a project is too close to its deadline, your guardrails can trigger an automated agent handoff to find fresh alternatives in the same region.

Run safe, production-grade school funding workflows using your OpenAI Agents SDK setup connected to live public education needs.

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 OpenAI Agents SDK

Create your Vinkius account to connect DonorsChoose to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate classroom funding queries via this MCP Server

Connect your agent workflows directly to classroom requests without worrying about bad API payloads by running `list_high_poverty_needs` through the OpenAI Agents SDK. This setup lets you build safe donor-matching loops. Your agent calls `get_classroom_project_details` to pull specific teacher requests, while the OpenAI dashboard traces every call to prevent runaway API spend.

Handle multi-agent handoffs for regional audits

Split the work between specialized agents using `list_urgent_funding_needs` to keep your system fast and reliable. When a donor asks for local impact, the routing agent passes the task to a regional specialist. That specialist uses `quick_regional_funding_audit` to get a high-level summary of active projects in the donor's state.

Auto-discover educational project tools

Stop writing manual tool definitions and let your agent discover `search_classroom_projects` automatically. You turn on caching with `cacheToolsList=True` to keep your system snappy. Your agent can instantly search by location with `search_projects_by_zipcode` without re-fetching the tool schema on every turn.

Setup guide

Set up DonorsChoose MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all DonorsChoose tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives DonorsChoose tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate DonorsChoose tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="DonorsChoose Agent",
            instructions="You have access to DonorsChoose tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package with `pip install openai-agents` and set up the streamable HTTP parameters. You pass `MCPServerStreamableHttp` pointing to the Vinkius endpoint directly into your agent constructor. The SDK automatically registers the school search tools.

Yes, every tool execution is logged directly in your OpenAI developer dashboard. If your agent runs `quick_regional_funding_audit`, you can view the exact payload, latency, and token usage for that run.

Your agent can check expiration dates by calling `list_urgent_funding_needs`. If a project is too close to its deadline, your guardrails can trigger an automated agent handoff to find fresh alternatives in the same region.

No, Vinkius handles the underlying platform authentication. Your code only needs one endpoint token to give your agent access to tools like `list_projects_by_subject` and `list_projects_by_state`.

Vinkius runs this MCP integration in a zero-trust, ephemeral V8 sandbox. When your agent searches location data with `search_projects_by_zipcode`, the query is processed in isolation and never stored or used to train public models.

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