How to Use the Givebutter MCP in LlamaIndex

Q: How do I index Givebutter donor profiles into LlamaIndex?

You use listdonorcontacts via the MCP Server to retrieve donor profiles, then wrap the output in LlamaIndex Document objects. These documents are then split, embedded, and loaded into your vector store for semantic search.

Q: Can LlamaIndex query live Givebutter campaign metrics?

Yes, your query engine calls getcampaigndetails to fetch real-time metadata before generating answers. This ensures your agent bases its responses on current API data rather than stale cached indexes.

Q: How does this MCP Server handle recurring plans in LlamaIndex?

The MCP Server exposes listrecurringplans, which your agent calls to gather active subscription data. LlamaIndex indexes these plans so you can run natural language queries about expected monthly donor revenue.

Q: Can I verify my API connection before running indexing jobs?

Yes, you run verifyapiconnection at the start of your ingestion script. This prevents your indexing pipeline from failing halfway through due to an expired API key.

Index your Givebutter campaign metrics and donor histories directly into your LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Givebutter MCP to LlamaIndex

Create your Vinkius account to connect Givebutter 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 Givebutter with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live donor records into LlamaIndex

`list_donor_contacts` extracts donor profiles from your Givebutter database and feeds them directly into your LlamaIndex document pipeline using our MCP Server. This turns raw donor lists into searchable document nodes for semantic retrieval. Your agent queries these indexed profiles alongside offline documents to find giving patterns. By passing these nodes to a vector store, you search donor history using natural language queries instead of exact database matching.

Ground campaign queries with live API metrics

`get_campaign_details` retrieves the latest metadata for active fundraising campaigns directly into your index. Your query engine uses this live data to answer questions about progress toward goals. The engine cross-references this with `list_recent_donations` to ensure your RAG system has the last ten transactions indexed. This prevents your agent from hallucinating donation totals or campaign statuses.

Audit recurring donation plans via semantic search

`list_recurring_plans` pulls active recurring donation structures directly into your index pipelines. Your agent parses these plans to identify active versus lapsed giving patterns over time. You combine this output with `list_donation_transactions` to verify that scheduled payments match actual settled transactions. This gives your finance queries an accurate, grounded dataset to search against.

Setup guide

Set up Givebutter 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 Givebutter 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 Givebutter tools.",
)
response = await agent.run("List recent Givebutter 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 Givebutter. 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 Givebutter 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 Givebutter MCP in LlamaIndex

You use `list_donor_contacts` via the MCP Server to retrieve donor profiles, then wrap the output in LlamaIndex Document objects. These documents are then split, embedded, and loaded into your vector store for semantic search.

Yes, your query engine calls `get_campaign_details` to fetch real-time metadata before generating answers. This ensures your agent bases its responses on current API data rather than stale cached indexes.

The MCP Server exposes `list_recurring_plans`, which your agent calls to gather active subscription data. LlamaIndex indexes these plans so you can run natural language queries about expected monthly donor revenue.

Yes, you run `verify_api_connection` at the start of your ingestion script. This prevents your indexing pipeline from failing halfway through due to an expired API key.

Yes, transaction metadata processed by this MCP Server remains fully local to your execution environment. The server runs in an ephemeral, zero-trust sandbox, ensuring donor financial data is never leaked or cached externally.

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