How to Use the NeonCRM MCP in OpenAI Agents SDK

Q: How do I register NeonCRM tools in the OpenAI Agents SDK?

Use pip install openai-agents and initialize MCPServerStreamableHttp with your Vinkius endpoint. This registers the MCP Server directly in your Python code.

Q: Can my OpenAI Agents SDK system handle custom fields from NeonCRM?

Yes, the listcustomfields tool fetches all custom definitions directly into your agent's context. This allows your OpenAI Agents SDK setup to parse non-standard attributes without manual code updates.

Q: Why should I cache the tool list in OpenAI Agents SDK?

Setting cacheToolsList=True prevents the SDK from querying the Vinkius API on every single turn. This speeds up your agent's response times when it repeatedly calls getcrmevent during event planning.

Connect your NeonCRM database to the OpenAI Agents SDK to build secure, self-verifying donor management agents.

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 OpenAI Agents SDK

Create your Vinkius account to connect NeonCRM to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verify NeonCRM donor profiles safely with OpenAI Agents SDK

The `get_account` tool retrieves complete profile records so your agent can verify donor status before executing any automated tasks. By hooking this tool into your agent stream, the SDK validates the retrieved payload against your system rules before the agent can write an email draft or trigger an action. You don't have to worry about the agent hallucinating donor histories or pulling the wrong records. Using `list_contacts` alongside this validation layer ensures your agent only looks at active, verified contacts during high-priority fundraising drives.

Track active campaigns using this MCP Server

The `list_donations` tool extracts live transaction records to feed directly into your agent's decision-making loop. Because the OpenAI Agents SDK supports clean state handoffs, one agent can pull the raw donation list while another specialized agent calculates the remaining gap for your current campaign targets. If a specific transaction looks unusual, the agent immediately spins up a task to run `get_donation` for that specific ID. This keeps your financial data accurate and ensures your team gets immediate alerts for major gifts without manual report building.

Coordinate event rosters and active memberships

The `list_crm_events` tool pulls scheduled non-profit gatherings directly into your agent's context window. Your agent uses this live calendar feed to cross-reference event registrations against active donor profiles retrieved by `list_memberships`. This setup allows your OpenAI Agents SDK system to run background checks on event attendees to identify lapsed members. Connect your agent via our managed MCP endpoint to run these checks automatically.

Setup guide

Set up NeonCRM MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all NeonCRM tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives NeonCRM tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NeonCRM tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="NeonCRM Agent",
            instructions="You have access to NeonCRM tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Use `pip install openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius endpoint. This registers the MCP Server directly in your Python code.

Yes, the `list_custom_fields` tool fetches all custom definitions directly into your agent's context. This allows your OpenAI Agents SDK setup to parse non-standard attributes without manual code updates.

Absolutely, you can route grant tracking to a specialized agent. The primary agent uses `list_grants` to find records, then hands the payload off to a writing agent to draft progress reports.

Setting `cacheToolsList=True` prevents the SDK from querying the Vinkius API on every single turn. This speeds up your agent's response times when it repeatedly calls `get_crm_event` during event planning.

Your donor names, email addresses, and transaction histories remain private because all traffic runs through Vinkius's isolated V8 sandboxes. The server only exposes read-only tools like `list_contacts` and `get_donation`, ensuring your underlying database cannot be modified or deleted by an autonomous agent.

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