How to Use the NeonCRM MCP in AutoGen

Q: How do I give my AutoGen agents access to the NeonCRM tools?

Use the mcpservertools function from the AutoGen extension library. Point it at your Vinkius server URL, and it returns a list of tools you can pass directly to your AssistantAgent constructor.

Q: Do I need to write code for each tool like getdonation?

No. The McpToolAdapter handles the conversion from the server's tool definitions to something AutoGen can use. You just build the agents and give them the tools; the adapter does the rest.

Create teams of AI agents that collaborate on NeonCRM tasks. Let them debate the best way to analyze donor data using AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NeonCRM MCP to AutoGen

Create your Vinkius account to connect NeonCRM 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 NeonCRM with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Delegate NeonCRM Tasks to Agent Teams

This server gives your AutoGen agents the tools they need to work with NeonCRM data. You can build a team of agents that collaborate on a problem. For example, one agent can use `list_donations` to find major donors, while another uses `list_crm_events` to identify popular events. They don't just execute tasks; they talk to each other. The agents can discuss their findings and work together to come up with a strategy, like which donors to invite to a specific fundraising event. It's a way to automate complex analysis that would normally require a team meeting.

Build Consensus on Fundraising Strategy

AutoGen's strength is in multi-agent conversation, and these tools provide the fuel. Have a 'Growth Agent' look for patterns in `list_memberships` while a 'Retention Agent' analyzes data from `list_donations` to spot donors at risk of lapsing. They can then debate the best course of action. Should you focus on acquiring new members or retaining existing ones? The agents present their data-backed arguments, helping you make a more informed decision. This MCP server provides the facts for their debate.

A Dedicated MCP Server for AutoGen

Connecting AutoGen to NeonCRM is straightforward. The `autogen-ext` package includes an adapter that automatically finds and configures the tools from this server. You just provide the URL. This lets you focus on designing your agent conversations, not on writing boilerplate API code. Your agents get immediate, reliable access to all 10 read-only tools, from `get_account` to `list_custom_fields`, right out of the box.

Setup guide

Set up NeonCRM 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 NeonCRM 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="NeonCRM_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the `mcp_server_tools` function from the AutoGen extension library. Point it at your Vinkius server URL, and it returns a list of tools you can pass directly to your `AssistantAgent` constructor.

Yes. You can create multiple tool lists from the MCP server and assign them to different agents. For instance, give your 'Finance Agent' access to `list_donations` and your 'Events Agent' access to `list_crm_events`.

This setup is ideal for complex, open-ended problems. Use it to brainstorm new fundraising campaigns, analyze donor churn, or identify underserved segments in your contact list by having agents analyze the data from multiple angles.

No. The `McpToolAdapter` handles the conversion from the server's tool definitions to something AutoGen can use. You just build the agents and give them the tools; the adapter does the rest.

Each agent's access is contained. Data fetched by one agent, like a list of contacts, isn't visible to other agents unless it's explicitly shared in the conversation. The connection to NeonCRM itself is managed and secured by the Vinkius MCP Server, keeping your core credentials safe.

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