How to Use the DonorsChoose MCP in AutoGen

Q: How do AutoGen agents execute DonorsChoose tools?

You register the DonorsChoose tools using the mcpservertools adapter and pass them to your AutoGen AssistantAgent. The AutoGen agents then call tools like searchclassroomprojects autonomously during their conversation.

Let your AutoGen agents debate and coordinate to find the absolute highest-impact DonorsChoose projects to fund.

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 AutoGen

Create your Vinkius account to connect DonorsChoose to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate DonorsChoose funding debates in AutoGen

You can set up an AutoGen multi-agent system where one agent uses `list_urgent_funding_needs` to find expiring projects, while another runs `quick_regional_funding_audit` to check local coverage. They debate which DonorsChoose project deserves immediate attention based on real-time data. This collaborative AutoGen approach ensures you don't just fund the first project that shows up. The AutoGen agents look at the data retrieved from this MCP Server to negotiate the best allocation of corporate donation budgets.

Validate DonorsChoose poverty metrics with AutoGen

Deploy a dedicated AutoGen analysis agent that calls `list_high_poverty_needs` to gather target schools. A separate AutoGen security agent then uses `get_classroom_project_details` to verify the proposal details and flag any anomalies before approval. Because AutoGen supports structured MCP Server tool execution, the agents pass these DonorsChoose API payloads back and forth naturally. They resolve discrepancies internally before presenting the final, audited funding recommendations to your team.

Segment DonorsChoose searches using AutoGen agents

Build an AutoGen dispatch routing pattern where a coordinator agent assigns tasks to specialized searchers. One AutoGen agent queries `search_projects_by_zipcode` while another runs `list_projects_by_subject` to find science projects in that same area. The AutoGen agents combine their findings into a single, cohesive proposal. This multi-agent coordination matches donors with highly specific DonorsChoose classroom requirements far better than a single prompt ever could.

Setup guide

Set up DonorsChoose MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes DonorsChoose tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="DonorsChoose_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent DonorsChoose data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="DonorsChoose_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent DonorsChoose data")
    print(result.messages[-1].content)

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 AutoGen

You register the DonorsChoose tools using the mcp_server_tools adapter and pass them to your AutoGen AssistantAgent. The AutoGen agents then call tools like `search_classroom_projects` autonomously during their conversation.

Yes, the server handles concurrent requests from different agents in your AutoGen group chat. One AutoGen agent can check `list_projects_by_state` while another concurrently fetches details via `get_classroom_project_details`.

You can configure your AutoGen coordinator agent to limit the frequency of tool calls. This prevents the group chat from spamming `quick_regional_funding_audit` during intense multi-agent deliberations.

Yes, the AutoGen MCP extension automatically translates the DonorsChoose tool definitions. Tools like `list_latest_classroom_proposals` map directly to the schema format that your AutoGen agents expect.

Yes. The DonorsChoose MCP Server runs in an ephemeral, sandboxed environment that processes requests in memory. No school ZIP codes or DonorsChoose proposal texts are cached or stored outside your local AutoGen execution context.

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