How to Use the NeonCRM MCP in LangChain

Q: How do I use these NeonCRM tools with a LangChain agent?

First, get the tools from the client with .gettools(). Then, pass that list directly into a LangChain agent constructor like createagent. The adapter handles all the schema mapping for you.

Build fundraising bots and data chains for NeonCRM with LangChain. Pull donor data, event lists, and more without writing API code.

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 LangChain

Create your Vinkius account to connect NeonCRM to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain NeonCRM data into workflows

This MCP server gives your agent direct, read-only access to your NeonCRM database. You can build chains that first find a donor with `list_accounts`, then pull their full giving history with `get_donation`, and finally list their event attendance with `list_crm_events`. Each tool is a link in the chain. The output of one tool becomes the input for the next, letting your agent reason through multi-step tasks. It's perfect for things like building a daily briefing on major donor activity or summarizing a contact's entire history before a call.

Automate Donor and Grant Research

Stop digging through the NeonCRM interface for basic facts. Just ask your LangChain agent to get the data for you. It can use `list_donations` to find recent high-value contributions or `list_grants` to check the status of pending applications. The agent decides which tool to use based on your question. This means you can build internal assistants that give your fundraising team instant answers, cutting down on the time they spend on data entry and research.

Connect Your LangChain Agent to Live Data

Ground your agent's responses in what's actually happening in your nonprofit. The tools let it see real-time information, from new signups in `list_memberships` to custom data points you've configured with `list_custom_fields`. Because your agent is working with live data, its answers are current and accurate. You don't have to worry about it hallucinating donor information or making up event details. It checks the source of truth every time.

Setup guide

Set up NeonCRM MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes NeonCRM tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "neoncrm-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent NeonCRM transactions"
    })
    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 LangChain

First, get the tools from the client with `.get_tools()`. Then, pass that list directly into a LangChain agent constructor like `create_agent`. The adapter handles all the schema mapping for you.

Yes, that's what it's for. You can create a chain that uses `get_account` to pull a donor's info from NeonCRM, then uses another tool to search for them on the web. The results are combined in a single flow.

Use a tracer like LangSmith. It shows you exactly which tools your agent called, what inputs it used for tools like `get_donation`, and what data NeonCRM returned. It makes finding issues in your chains much simpler.

No. LangChain lets you build chains that are as simple or complex as you need. You could use all 10 NeonCRM tools in one agent if the task requires that level of reasoning.

Your NeonCRM credentials are never exposed to your LangChain code. The Vinkius MCP Server manages the connection, and your agent just makes requests to it. Every call to get contact or donation data is an isolated, ephemeral transaction.

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