How to Use the Double the Donation MCP in AutoGen

Q: How do I register Double the Donation tools with AutoGen agents?

You use the mcpservertools helper with StreamableHttpServerParams to fetch the tool definitions. Pass this list to your AssistantAgent constructor, and the adapter will automatically handle the MCP schema conversion so your agents can call registerdonation.

Q: Can AutoGen agents debate matching eligibility using Double the Donation?

Yes. You can set up one agent to query company rules with getcompany and another to check the donor's record with getdonation. They will debate whether the donation meets the company's specific matching criteria before registering the match.

Q: How do AutoGen agents handle fuzzy company names with Double the Donation?

An agent can call searchcompany to retrieve a list of potential employer matches. If there are multiple matches, the agents can discuss the options or query listsubsidiaries to determine the correct corporate entity before proceeding.

Q: Where are our corporate match stats stored during agent execution?

The transaction records and match statistics retrieved by getdashboardstats and listdonations are processed purely in transit. Vinkius executes the MCP Server in an ephemeral sandbox that destroys the runtime state immediately after the agent session ends, ensuring zero data persistence.

Run multi-agent debates in AutoGen to verify and register matching gifts via the Double the Donation MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Double the Donation MCP to AutoGen

Create your Vinkius account to connect Double the Donation 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 Double the Donation with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run AutoGen debates to verify matching gifts

You run `search_company` within an AutoGen debate to prevent single LLM mistakes on matching gift eligibility. With AutoGen, you can set up a debate between a verification agent and a finance agent through this MCP server. The verification agent runs `search_company` to find the employer, while the finance agent checks the rules using `get_company` to ensure the match is valid. They cross-reference the results, debating whether the donor's transaction meets the minimum threshold.

Coordinate complex donation registrations

Your AutoGen group chat uses `list_donations` to coordinate complex matching gift registrations with high precision. Registering matching gifts requires careful checking of transaction logs. In your AutoGen group chat, one agent can list recent transactions using `list_donations`, while another agent calls `register_donation` to log the match. If a transaction looks incomplete, a supervisor agent can interject and prompt the user for clarification.

Monitor campaign performance via agent consensus

The `get_dashboard_stats` tool lets your AutoGen agents analyze fundraising progress without relying on static dashboards. Use AutoGen agents to analyze your campaigns by calling `list_campaigns` and `get_dashboard_stats` concurrently. An analyst agent can digest the raw stats, while a strategy agent suggests adjustments to your outreach campaigns. They collaborate to find underperforming segments and write updates back to your account using `update_organization` to optimize your matching gift settings.

Setup guide

Set up Double the Donation 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 Double the Donation 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="Double the Donation_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Double the Donation 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="Double the Donation_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Double the Donation 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 Double the Donation. 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 Double the Donation 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 Double the Donation MCP in AutoGen

You use the `mcp_server_tools` helper with `StreamableHttpServerParams` to fetch the tool definitions. Pass this list to your `AssistantAgent` constructor, and the adapter will automatically handle the MCP schema conversion so your agents can call `register_donation`.

Yes. You can set up one agent to query company rules with `get_company` and another to check the donor's record with `get_donation`. They will debate whether the donation meets the company's specific matching criteria before registering the match.

An agent can call `search_company` to retrieve a list of potential employer matches. If there are multiple matches, the agents can discuss the options or query `list_subsidiaries` to determine the correct corporate entity before proceeding.

AutoGen's conversational loop allows other agents to catch the error. If `register_donation` returns a validation error, a developer agent can inspect the schema, correct the payload, and retry the call automatically.

The transaction records and match statistics retrieved by `get_dashboard_stats` and `list_donations` are processed purely in transit. Vinkius executes the MCP Server in an ephemeral sandbox that destroys the runtime state immediately after the agent session ends, ensuring zero data persistence.

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