How to Use the DonorsChoose MCP in LlamaIndex

Q: Can LlamaIndex query the DonorsChoose API to prevent model hallucinations?

Yes, the LlamaIndex agent calls searchclassroomprojects to retrieve live DonorsChoose classroom needs before answering. This ensures your LlamaIndex application displays active projects rather than hallucinating expired proposals.

Q: Can I filter which tools my agent can access?

Yes, you can use the allowedtools filter during LlamaIndex initialization to restrict the agent. For example, you can limit the LlamaIndex agent to only run searchprojectsbyzipcode to keep searches strictly local to DonorsChoose.

Index active DonorsChoose classroom proposals directly into your LlamaIndex vector stores for accurate, real-time RAG matching.

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 LlamaIndex

Create your Vinkius account to connect DonorsChoose to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build DonorsChoose RAG pipelines with LlamaIndex

You can index live DonorsChoose school proposals directly into your LlamaIndex storage. Your LlamaIndex agent uses `list_latest_classroom_proposals` to fetch raw project descriptions and converts them into searchable vector embeddings on the fly. This LlamaIndex setup eliminates hallucinations when your users ask about current DonorsChoose educational needs. By querying this MCP Server, your LlamaIndex pipeline pulls ground-truth data from `get_classroom_project_details` instead of relying on outdated model weights.

Index DonorsChoose regional audits for LlamaIndex search

Use LlamaIndex to run a `quick_regional_funding_audit` and index the summary statistics into a local LlamaIndex document store. This lets your LlamaIndex agent perform semantic queries across entire states or ZIP codes to find DonorsChoose funding gaps. The LlamaIndex agent uses `search_projects_by_zipcode` to fetch localized school data, which is then structured into a queryable index. You get a LlamaIndex search engine that knows exactly which neighborhoods need books, technology, or basic supplies from DonorsChoose.

Ground LlamaIndex matching in school poverty metrics

This MCP Server integration lets you build a LlamaIndex knowledge base of underfunded schools. Your LlamaIndex agent calls `list_high_poverty_needs` to retrieve projects, then structures this DonorsChoose data into node documents for precise retrieval. When a donor asks where their money will make the biggest impact, the LlamaIndex agent queries the index. It cross-references the donor's preferences with DonorsChoose projects pulled via `list_projects_by_subject` to find the perfect match.

Setup guide

Set up DonorsChoose MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all DonorsChoose MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to DonorsChoose tools.",
)
response = await agent.run("List recent DonorsChoose data")

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 LlamaIndex

You load the DonorsChoose MCP Server tools into a LlamaIndex McpToolSpec and pass them to your agent. The LlamaIndex agent executes `get_classroom_project_details` and indexes the returned text directly into your vector store.

Yes, the LlamaIndex agent calls `search_classroom_projects` to retrieve live DonorsChoose classroom needs before answering. This ensures your LlamaIndex application displays active projects rather than hallucinating expired proposals.

The LlamaIndex McpToolAdapter automatically translates the DonorsChoose server's schemas into LlamaIndex-compatible function tools. Tools like `list_urgent_funding_needs` become immediately available for your LlamaIndex agent to call during query execution.

Yes, you can use the allowed_tools filter during LlamaIndex initialization to restrict the agent. For example, you can limit the LlamaIndex agent to only run `search_projects_by_zipcode` to keep searches strictly local to DonorsChoose.

The DonorsChoose MCP Server runs within a zero-trust V8 isolate that never stores your queries. Only the raw JSON responses from tools like `list_projects_by_state` are passed to your local LlamaIndex vector index, ensuring complete data isolation.

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