How to Use the Salsa Engage MCP in AutoGen

Q: What's a good use case for AutoGen and Salsa Engage for fundraising?

Set up an agent to monitor getengagementmetrics. If a key metric drops, it can initiate a conversation with another agent to diagnose the problem, perhaps by pulling data with listsupporters to find a pattern. They work together to find the root cause.

Assemble a team of AI agents to manage your Salsa Engage data. Use AutoGen to debate, plan, and execute non-profit strategy.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Salsa Engage MCP to AutoGen

Create your Vinkius account to connect Salsa Engage to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Salsa Engage with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Supporter Analysis

Create a team of agents to work on your data. A 'DataAnalyst' agent can use `get_engagement_metrics` to pull performance stats, while a 'CampaignManager' agent uses `list_supporter_groups` to review audience lists. They don't just act; they discuss the findings. The agents converse to reach a conclusion. The Analyst might report low engagement, and the Manager might suggest creating a new segment. This leads to a concrete plan, like having an 'Executor' agent call `upsert_supporter_group` based on their consensus.

Debate and Decide on Outreach Strategy

AutoGen lets you model real-world team dynamics. You can have one agent propose a new supporter segment, and a 'RiskAssessor' agent can check for potential data conflicts using `list_supporters` before any changes are made. This isn't just automation, it's simulated deliberation. An agent might use `list_configured_webhooks` to see how a change could affect other systems, adding a layer of safety before another agent is permitted to run `assign_supporters_to_group`.

Run Your Salsa Engage MCP Server with an Agentic Workforce

Assign roles and give them access to the Salsa Engage toolset. A 'DatabaseAdmin' agent can be responsible for data hygiene, using `upsert_supporter_profile` to clean up records, while a 'FundraisingDirector' agent monitors high-level numbers with `list_offline_donations`. Your user prompt kicks off a conversation. When you ask, 'Should we create a new group for event attendees?', the agents collaborate, check data with tools like `list_engagement_activities`, and present a reasoned answer with an execution plan. It's a team effort.

Setup guide

Set up Salsa Engage 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 Salsa Engage 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="Salsa Engage_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You define different agents and give them access to the Salsa Engage tools. When one agent proposes a plan, like using `assign_supporters_to_group`, the other can critique it or execute it based on the conversation.

Absolutely. You can have one agent identify a data issue, and another agent can be authorized to fix it by calling `upsert_supporter_profile`. The conversation log shows you exactly why the change was made.

Set up an agent to monitor `get_engagement_metrics`. If a key metric drops, it can initiate a conversation with another agent to diagnose the problem, perhaps by pulling data with `list_supporters` to find a pattern. They work together to find the root cause.

Multiple agents allow for checks and balances. One agent might want to aggressively create groups with `upsert_supporter_group`, but a 'QA' agent can review the plan first, preventing errors. The MCP toolset is powerful; this adds a layer of safety.

Each tool call, like fetching engagement activities or donation history, is an independent, sandboxed operation managed by Vinkius. The agents themselves don't store your Salsa Engage data from `list_engagement_activities`; they only process the information in memory to inform their conversation.

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