How to Use the Blackbaud MCP in LlamaIndex

Q: How do I index Blackbaud donor data into LlamaIndex?

You use BasicMCPClient to connect to the Vinkius endpoint and load the tools via McpToolSpec. From there, your LlamaIndex agent can call getconstituent or getgift and insert the resulting text directly into your vector index.

Q: How do I limit which Blackbaud tools LlamaIndex can access using this MCP Server?

You can use the allowedtools filter when initializing your McpToolSpec in LlamaIndex. This lets you restrict the agent to reading data with listschoolusers while blocking write operations like creategift if needed.

Q: Does this MCP Server support asynchronous execution in LlamaIndex?

Yes, you can load the tools asynchronously using totoollistasync() on your tool spec. This prevents blocking your main LlamaIndex application thread when querying large lists with listacademicsections.

Q: Where is the donor PII processed when using Blackbaud with LlamaIndex?

All sensitive data from Blackbaud tools like getconstituent passes directly through our secure, ephemeral V8 isolate sandbox to your local LlamaIndex client. No donor profiles or school records are stored on Vinkius servers.

Index live fundraising and academic data into your LlamaIndex vector stores for accurate, context-rich RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Blackbaud MCP to LlamaIndex

Create your Vinkius account to connect Blackbaud 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 Blackbaud with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed live donor records into LlamaIndex vector stores

Pull live data directly from your CRM using `get_constituent` and `get_gift` to ground your LlamaIndex agent's answers. This MCP Server lets LlamaIndex ingest real-time fundraising data directly into your semantic index. The tool output is converted into document nodes that feed straight into your vector store. Your LlamaIndex agent can answer complex questions about recent giving trends without fabricating names or amounts.

Build context-aware school directories

Query your student database using `list_school_users` and `list_academic_sections` to build an active semantic index of your school's structure. This setup allows your LlamaIndex pipeline to answer organizational questions using live data. When an administrator asks which parents are associated with a specific class, LlamaIndex retrieves the relevant nodes from the vector store. It ensures your staff gets accurate, structured answers from the Blackbaud database instantly.

Ground financial reporting in real database records

Ground your financial summaries in hard facts by using `get_gift` to pull exact transaction details. This ensures your LlamaIndex engine drafts reports using actual Blackbaud data instead of guessing. You prevent your LlamaIndex agent from making up donation numbers or dates. Every financial claim points directly to an actual gift record in your CRM.

Setup guide

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

You use `BasicMCPClient` to connect to the Vinkius endpoint and load the tools via `McpToolSpec`. From there, your LlamaIndex agent can call `get_constituent` or `get_gift` and insert the resulting text directly into your vector index.

It can do both. While you can index data for search, your LlamaIndex agent can also invoke write tools like `create_constituent` or `update_constituent` when your pipeline detects a new donor or updated contact info.

You can use the `allowed_tools` filter when initializing your `McpToolSpec` in LlamaIndex. This lets you restrict the agent to reading data with `list_school_users` while blocking write operations like `create_gift` if needed.

Yes, you can load the tools asynchronously using `to_tool_list_async()` on your tool spec. This prevents blocking your main LlamaIndex application thread when querying large lists with `list_academic_sections`.

All sensitive data from Blackbaud tools like `get_constituent` passes directly through our secure, ephemeral V8 isolate sandbox to your local LlamaIndex client. No donor profiles or school records are stored on Vinkius servers.

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