How to Use the ChargeDesk MCP in LlamaIndex

Q: Can I search for a specific ChargeDesk customer by name with a LlamaIndex agent?

Yes. Your agent would use the listchargedeskcustomers tool, index the results, and then you could perform a semantic search over that index. For a direct lookup, it could also just call the tool with the right parameters.

Q: How do I set up the ChargeDesk tools for my LlamaIndex RAG app?

After installing the adapter, you create a BasicMCPClient with your Vinkius endpoint URL. Then you pass that client to McpToolSpec and call totoollistasync() to get the tools for your agent. It's a few lines of code to get everything connected.

Turn your ChargeDesk billing history into a searchable knowledge base with LlamaIndex. Ask questions, get answers grounded in your actual payment data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChargeDesk MCP to LlamaIndex

Create your Vinkius account to connect ChargeDesk 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 ChargeDesk with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Your Billing Data in Plain English

LlamaIndex doesn't just call tools; it indexes their output. When your agent calls `list_chargedesk_charges` or `list_chargedesk_subscriptions`, the results are automatically fed into a vector index. This creates a knowledge base of your real-time billing activity. Now you can ask questions like "who were our last five refunded customers?" or "show me all active subscriptions over $100." LlamaIndex finds the relevant data from its index of past tool calls, like `get_customer_details` and `refund_chargedesk_payment`, and synthesizes a direct answer.

Build a RAG Agent with LlamaIndex

This MCP Server provides the live data source for your LlamaIndex RAG application. Use the `McpToolSpec` to give your agent access to all ChargeDesk tools. Your agent can now answer questions by either querying its existing index or by calling a tool for fresh data. For example, if a user asks about a very recent payment, the agent might call `get_charge_details` directly. If they ask a more general question about billing trends, it will query the vectorized history of previous `list_chargedesk_charges` calls. It's a smart system that knows when to fetch live data versus when to search what it already knows.

Ground Responses in Your Configuration

It's not just for transactions. You can index your account's setup. Run `list_chargedesk_webhooks` and `list_connected_gateways` and let LlamaIndex ingest that configuration data. Now, your internal support agents can ask "which webhooks are configured for failed payments?" or "are we still connected to our primary gateway?" The agent will provide answers based on the actual, indexed state of your ChargeDesk account, preventing guesswork and mistakes. This is a powerful way to document and query your system's configuration.

Setup guide

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

LlamaIndex specializes in creating a searchable index from the output of tools like `list_chargedesk_customers`. This means your agent can answer questions by searching past results, not just by calling the API every single time. It builds up knowledge over time.

Yes. Your agent would use the `list_chargedesk_customers` tool, index the results, and then you could perform a semantic search over that index. For a direct lookup, it could also just call the tool with the right parameters.

After installing the adapter, you create a `BasicMCPClient` with your Vinkius endpoint URL. Then you pass that client to `McpToolSpec` and call `to_tool_list_async()` to get the tools for your agent. It's a few lines of code to get everything connected.

Your agent can be configured to refresh the index periodically by re-running tools like `list_chargedesk_subscriptions`. LlamaIndex also lets your agent decide at query time whether to call a tool for live data if it thinks the indexed information might be stale.

You control what gets indexed. The tool outputs, which can include customer details and subscription info from ChargeDesk, are processed on your infrastructure before being vectorized. Your Vinkius token secures the connection to the MCP server, and all data is transmitted over an encrypted channel. You decide the persistence and storage strategy for the resulting index.

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