How to Use the Blackbaud MCP in AutoGen

Q: How do I register the Blackbaud MCP Server tools in AutoGen?

You use the mcpservertools helper with your Vinkius HTTP URL to fetch the tools. Then, pass the resulting tool list directly to your AutoGen AssistantAgent constructor to give them database access.

Q: How does AutoGen handle the schema for Blackbaud MCP tools?

The McpToolAdapter in the AutoGen extension handles the schema conversion automatically. It maps the parameters for Blackbaud tools like creategift so your agents can call them using standard JSON structures.

Let specialized AutoGen agents debate and execute donor management tasks with the Blackbaud 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 Blackbaud MCP to AutoGen

Create your Vinkius account to connect Blackbaud 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 Blackbaud with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate donor data accuracy

Prevent database duplication by matching records with `get_constituent` before calling `create_constituent`. AutoGen agents can discuss the match confidence in a structured conversation before committing any changes. This team-based approach keeps your Blackbaud CRM clean without requiring constant human oversight. The validator agent reviews the record against existing data, ensuring only clean profiles are written.

Automate gift entry with automated agent reviews

Execute financial entries with automated reviews by passing data to `create_gift` only after validation. You can set up an AutoGen agent to format the transaction details, and another to execute the tool once the data passes verification. If the payload contains errors, the execution agent rejects it and asks the writer agent to fix the fields. This loop avoids failed API calls and keeps your Blackbaud financial records accurate.

Coordinate school roster updates across agents

Coordinate school roster updates by pulling active classes using `list_academic_sections` and matching students with `list_school_users`. This structure keeps your school management system aligned with actual classroom assignments. When changes are needed, the coordinator AutoGen agent assigns the update task to the database writer. Your Blackbaud academic data remains synchronized without manual intervention.

Setup guide

Set up Blackbaud 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 Blackbaud 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="Blackbaud_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Blackbaud 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="Blackbaud_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Blackbaud 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 Blackbaud. 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 Blackbaud 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 Blackbaud MCP in AutoGen

You use the `mcp_server_tools` helper with your Vinkius HTTP URL to fetch the tools. Then, pass the resulting tool list directly to your AutoGen `AssistantAgent` constructor to give them database access.

Yes, you can distribute Blackbaud tools across different AutoGen agents. For example, your research agent can use `get_constituent` to find records, while your writer agent holds the permission to call `update_constituent`.

The `McpToolAdapter` in the AutoGen extension handles the schema conversion automatically. It maps the parameters for Blackbaud tools like `create_gift` so your agents can call them using standard JSON structures.

The tool returns the error message directly to the AutoGen conversation. The agent can then analyze the failure, correct the parameters, and try running the tool again, such as retrying a failed `create_constituent` call.

Yes, the MCP connection runs through a zero-trust, ephemeral V8 sandbox. Your API keys and sensitive outputs from Blackbaud tools like `list_school_users` or `get_gift` are never stored or logged on our infrastructure.

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