How to Use the DonorsChoose MCP in Google ADK

Q: How do I configure the DonorsChoose integration in a Google ADK project?

Install the package using pip install google-adk and define your toolset. Use McpToolset with the streamable HTTP parameters pointing to the Vinkius URL, then pass it to your LlmAgent instance.

Q: How do I limit Google ADK to only search specific regions on DonorsChoose?

You can restrict the toolset to only expose searchprojectsbyzipcode and listprojectsbystate. This ensures your enterprise agent only queries geographic regions that match your corporate giving guidelines.

Q: How does Google ADK protect sensitive classroom proposal details?

All school data retrieved via getclassroomprojectdetails is processed in a secure, isolated V8 sandbox on Vinkius. No student or teacher PII is stored locally, keeping your educational compliance checks clean.

Connect Gemini to classroom funding data using Google ADK to analyze school needs alongside your BigQuery datasets.

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 Google ADK

Create your Vinkius account to connect DonorsChoose to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map regional donor insights using Gemini and BigQuery

Combine your internal corporate giving data with live classroom needs by running `list_projects_by_state` via the Google ADK. The long-context window allows your agent to ingest hundreds of project proposals at once. It can process the output of `quick_regional_funding_audit` alongside your historical donor tables to find the best local matches.

Run deep semantic searches across school proposals

Let Gemini analyze complex teacher requests natively using `search_classroom_projects`. The Google ADK handles the tool execution loop without manual coding. When Gemini identifies a promising project, it uses `get_classroom_project_details` to fetch the complete itemized list of materials requested by the teacher.

Restrict exposed tools within your Google ADK agent

Keep your enterprise agent focused by limiting access to tools like `list_high_poverty_needs`. For instance, you can limit the agent to `search_projects_by_zipcode`. This prevents the model from wandering off into unrelated queries and keeps API usage predictable.

Setup guide

Set up DonorsChoose MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with DonorsChoose tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="DonorsChoose_agent",
    model="gemini-2.0-flash",
    instruction="You have access to DonorsChoose tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the package using `pip install google-adk` and define your toolset. Use `McpToolset` with the streamable HTTP parameters pointing to the Vinkius URL, then pass it to your `LlmAgent` instance.

Yes, Google ADK lets Gemini ingest large volumes of project details. Your agent can call `list_projects_by_subject` to gather hundreds of literacy proposals and summarize them in a single prompt.

You can restrict the toolset to only expose `search_projects_by_zipcode` and `list_projects_by_state`. This ensures your enterprise agent only queries geographic regions that match your corporate giving guidelines.

The server supports both Stdio and HTTP transports. For cloud deployments, we recommend using the streamable HTTP transport to connect your hosted Gemini models directly to the live classroom database.

All school data retrieved via `get_classroom_project_details` is processed in a secure, isolated V8 sandbox on Vinkius. No student or teacher PII is stored locally, keeping your educational compliance checks clean.

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