How to Use the DonorsChoose MCP in LangChain

Q: Can I trace classroom API latency inside LangChain workflows?

Yes, every DonorsChoose tool call like quickregionalfundingaudit is tracked as a distinct span in your LangChain-linked LangSmith dashboard. You can monitor input tokens, output payloads, and exact execution times for every DonorsChoose classroom query inside your LangChain application.

Feed real-time DonorsChoose classroom funding needs directly into your LangChain reasoning loops to match donors with high-impact school projects.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DonorsChoose MCP to LangChain

Create your Vinkius account to connect DonorsChoose 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 DonorsChoose with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step DonorsChoose matching chains in LangChain

You can build a LangChain chain where your agent first calls the DonorsChoose `search_projects_by_zipcode` tool to find local school needs and then passes those IDs to `get_classroom_project_details` to extract classroom supply lists. This lets you construct deep LangChain reasoning workflows that don't just dump raw school data but actually evaluate which classroom needs match a specific donor's profile. Every single step of this DonorsChoose query runs through your LangChain adapter, giving you full observability of tool executions in LangSmith. You see the exact latency of the DonorsChoose MCP Server and trace how the LangChain agent decides to route the query based on real-time classroom requirements.

Trace urgent DonorsChoose needs with LangSmith

Connect `list_urgent_funding_needs` to a LangChain agent to catch expiring classroom projects before they lose their chance at DonorsChoose funding. The LangChain agent looks at the urgency metrics of the school projects and automatically runs a `quick_regional_funding_audit` to see if a local corporate sponsor can cover the remaining balance. Because this DonorsChoose MCP Server integrates directly with your existing LangChain chains, you can combine school data with external SQL databases in a single run. You get clean, traceable LangChain executions that show you exactly why a specific DonorsChoose school was recommended for a grant.

Map DonorsChoose poverty metrics to LangChain profiles

This DonorsChoose integration lets you feed low-income school data straight into your LangChain vector stores. Your LangChain agent calls `list_high_poverty_needs` to pull active requests and then uses LangChain document transformers to prepare the classroom text for semantic search. Linking these DonorsChoose tools together helps you construct a LangChain system that matches donor intent with actual classroom shortages. That agent queries `list_projects_by_subject` to filter results down to literacy or math needs, delivering highly specific DonorsChoose recommendations without any manual sorting.

Setup guide

Set up DonorsChoose 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 DonorsChoose 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({
    "donorschoose-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 DonorsChoose 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 DonorsChoose. 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 DonorsChoose 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 DonorsChoose MCP in LangChain

The DonorsChoose server exposes clean JSON schemas that LangChain ReAct agents parse to determine the next logical step. Your LangChain agent can call `list_projects_by_state` and immediately feed the output into a second LangChain chain that filters by subject area.

Yes, every DonorsChoose tool call like `quick_regional_funding_audit` is tracked as a distinct span in your LangChain-linked LangSmith dashboard. You can monitor input tokens, output payloads, and exact execution times for every DonorsChoose classroom query inside your LangChain application.

You load the DonorsChoose tools via the LangChain MCP adapter and pass them directly to your agent constructor. The outputs from `search_classroom_projects` are formatted as standard LangChain tool messages, which your chains can write directly to vector databases or external CRMs.

Yes, you can initialize the DonorsChoose toolset alongside other servers using the LangChain MultiServerMCPClient. This allows your LangChain agent to query school budgets from one source and classroom projects via `get_classroom_project_details` simultaneously.

Vinkius runs this DonorsChoose MCP Server in an isolated V8 sandbox, preventing any unauthorized access to your queries or school ZIP codes. Only the raw classroom project details retrieved via `search_projects_by_zipcode` pass through to your LangChain agent, keeping your internal donor profiles completely private.

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