How to Use the Donorbox MCP in LangChain

Q: How do I connect Donorbox to my LangChain agents?

Install langchain-mcp-adapters and use the MultiServerMCPClient to connect to the MCP Server URL. This exposes all twelve tools directly to your agent, allowing it to run tools like listdonations inside your existing chains.

Q: Can a LangChain agent pause a Donorbox recurring plan?

Yes, the agent can call pauserecurringplan when triggered by a customer request. You can set up a guardrail in your LangGraph chain to require human approval before the agent executes the change.

Q: Can I query campaigns and donations in a single chain?

You can chain listfundraisingcampaigns and listdonations sequentially. The agent reads the campaign IDs from the first tool and uses them to filter the donation records in the second tool.

Run complex donor management chains in LangChain using real-time fundraising data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Donorbox MCP to LangChain

Create your Vinkius account to connect Donorbox 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 Donorbox with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step donor workflows with LangChain

The `create_new_donor` tool lets your agent add a donor record to your database as soon as a new contact form comes in. Your LangChain agent handles the incoming contact details, formats the name and email, and writes the record directly to your account. You don't need to write manual glue code for this process. The output of this tool feeds right into the next step of your chain, letting you assign the donor to specific segments or campaigns without manual intervention.

Track and audit recurring donation plans automatically

The `list_recurring_plans` tool gives your agent immediate access to active donation commitments. LangChain chains use this data to inspect active plans, detect payment failures, or trigger follow-up sequences based on actual donor commitments. Your ReAct agents can inspect a plan and instantly decide whether to call `pause_recurring_plan` or `resume_recurring_plan` based on customer support emails. This MCP Server lets you trace every step of this decision, showing you exactly why an agent modified a subscription.

Verify fundraising progress and API health

The `list_fundraising_campaigns` tool returns live performance data for all your active giving pages. Your agent reads these campaign totals to build status updates or flag underperforming campaigns that need attention. Before running these data-heavy chains, the agent runs `check_api_health` to verify that your connection to the MCP Server is active. This prevents failed runs and keeps your automated reporting pipelines running without hitting unexpected API blocks.

Setup guide

Set up Donorbox 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 Donorbox 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({
    "donorbox-alternative-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 Donorbox 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 Donorbox. 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 Donorbox 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 Donorbox MCP in LangChain

Install `langchain-mcp-adapters` and use the `MultiServerMCPClient` to connect to the MCP Server URL. This exposes all twelve tools directly to your agent, allowing it to run tools like `list_donations` inside your existing chains.

Yes, the agent can call `pause_recurring_plan` when triggered by a customer request. You can set up a guardrail in your LangGraph chain to require human approval before the agent executes the change.

LangSmith traces every tool call, showing you the exact inputs and outputs for operations like `list_donors`. You see the latency, token count, and raw payload for every single interaction.

You can chain `list_fundraising_campaigns` and `list_donations` sequentially. The agent reads the campaign IDs from the first tool and uses them to filter the donation records in the second tool.

The server processes donor email addresses and donation amounts through secure V8 isolates. No transaction details or donor contact records are stored on our servers; they pass straight to your local client.

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