How to Use the Ko-fi MCP in LlamaIndex

Q: Can I index my Ko-fi donations into a LlamaIndex vector store?

Yes, LlamaIndex can take the output from the listtransactions tool and insert it into any vector database. This lets you perform semantic searches over your Ko-fi transaction history using natural language.

Q: Can I filter which Ko-fi tools are exposed to my LlamaIndex agent?

Yes, you can use the allowedtools filter in LlamaIndex. Since this server only contains the listtransactions tool, you will typically expose it directly to let your LlamaIndex agent manage financial queries.

Index your live Ko-fi transaction history directly into LlamaIndex using this MCP server to query donations 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 Ko-fi MCP to LlamaIndex

Create your Vinkius account to connect Ko-fi 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 Ko-fi with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Ko-fi transactions for LlamaIndex RAG

The `list_transactions` tool retrieves your recent Ko-fi donations and active subscriptions so your LlamaIndex agent can index them. LlamaIndex stores these Ko-fi records in a vector database, letting you run semantic queries across your entire creator sales history. Instead of writing custom SQL queries, you ask your LlamaIndex agent which Ko-fi products sold best last week. The MCP server feeds the raw Ko-fi data directly into the LlamaIndex index, keeping your financial context fresh.

Query Ko-fi data without AI hallucinations

The `list_transactions` tool provides the exact ground truth for your Ko-fi creator earnings within your LlamaIndex application. LlamaIndex uses this raw Ko-fi transaction output to answer user questions, ensuring the agent doesn't hallucinate fake sales numbers. Your LlamaIndex agent cites actual Ko-fi transaction IDs and buyer names when answering billing questions. This makes your automated LlamaIndex support reliable enough to handle real Ko-fi customer inquiries about their purchases.

Let your LlamaIndex agent search transaction histories

The `list_transactions` tool is called dynamically by your LlamaIndex agent when a user asks about their Ko-fi subscription status. LlamaIndex matches the user's natural language query to the tool's schema, pulling only the relevant Ko-fi transaction logs. This tight integration means your LlamaIndex agent doesn't waste resources downloading your entire Ko-fi history. It targets specific Ko-fi buyer records, processes them through your LlamaIndex index, and delivers a fast response.

Setup guide

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

Initialize the BasicMCPClient with the server URL, wrap it in a McpToolSpec, and call to_tool_list_async(). You can then pass the resulting list_transactions tool to your LlamaIndex FunctionAgent for immediate use.

Yes, LlamaIndex can take the output from the list_transactions tool and insert it into any vector database. This lets you perform semantic searches over your Ko-fi transaction history using natural language.

No, because this MCP server is poll-based. You must write a loop in LlamaIndex that calls list_transactions at set intervals to check for new Ko-fi shop orders or subscriptions.

Yes, you can use the allowed_tools filter in LlamaIndex. Since this server only contains the list_transactions tool, you will typically expose it directly to let your LlamaIndex agent manage financial queries.

Only your local LlamaIndex application receives the transaction records fetched by the list_transactions tool. Vinkius manages the connection using ephemeral, zero-trust infrastructure, meaning your customer names, donation amounts, and email addresses are never cached or exposed.

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