How to Use the ChurchStamp MCP in LlamaIndex

Q: How does LlamaIndex index physical mail campaigns from ChurchStamp?

It calls listcampaigns and loads the resulting JSON payload into a VectorStoreIndex. Your agent then performs semantic searches over past outreach topics to draft new postcard content.

Q: Can I use LlamaIndex to verify if a ChurchStamp contact exists?

Yes, you can query your indexed contact list or have the BasicMCPClient invoke getcampaign directly to check specific recipient details. This keeps your RAG application grounded in actual API records.

Q: How do I retrieve specific postcard design details?

Use getdesign within your query pipeline to pull template dimensions and layout details. LlamaIndex feeds this structural data directly to the LLM to verify if your message fits the physical postcard limits.

Index your ChurchStamp mailing campaigns into LlamaIndex to query physical outreach data with semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChurchStamp MCP to LlamaIndex

Create your Vinkius account to connect ChurchStamp 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 ChurchStamp with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index postcard designs for semantic search

`list_designs` retrieves all your active postcard layouts through the ChurchStamp MCP Server so LlamaIndex can turn their metadata into queryable vector embeddings. Your agent searches through past physical mail assets using natural language instead of hunting for specific IDs. This semantic indexing lets you quickly locate winter templates or donation appeals. You get immediate access to design details without hardcoding any template references in your application.

Build a LlamaIndex RAG pipeline for campaigns

`list_campaigns` downloads your historical mail runs directly into your LlamaIndex document store. The framework structures this raw API data into nodes, making your physical outreach history fully searchable by your agent. When preparing a new mailer, your agent queries this index to see what worked in previous months. It prevents duplicate campaigns and keeps your physical outreach aligned with past messaging.

Check live recipient lists during queries

`list_contacts` pulls your current member mailing list using this MCP Server so your LlamaIndex query engine can ground its answers in real-time directory data. This keeps your agent from hallucinating recipient counts or mailing to non-existent addresses. By combining live directory lookups with your vector store, your agent answers complex questions about who has received which mailer. It bridges the gap between static documents and live church database states.

Setup guide

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

It calls `list_campaigns` and loads the resulting JSON payload into a VectorStoreIndex. Your agent then performs semantic searches over past outreach topics to draft new postcard content.

Yes, you can query your indexed contact list or have the `BasicMCPClient` invoke `get_campaign` directly to check specific recipient details. This keeps your RAG application grounded in actual API records.

Define an allowed tools list when setting up your MCP Tool Spec in Python. For instance, you can expose only `list_designs` and block sending tools to prevent accidental physical mailings during testing.

Use `get_design` within your query pipeline to pull template dimensions and layout details. LlamaIndex feeds this structural data directly to the LLM to verify if your message fits the physical postcard limits.

Yes, Vinkius runs the server in an ephemeral, zero-trust environment where your API credentials never touch the client side. Your congregation's contact records are processed in-memory and wiped instantly, leaving no trace behind once the tool call concludes.

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