How to Use the Chargeblast MCP in LlamaIndex

Q: Can I index Chargeblast deflection logs for semantic search?

Yes. You can write a script that periodically runs listdeflectionlogs and feeds the JSON array into a Document object. Your engine will embed the logs for future querying.

Q: Can I restrict which actions the agent takes?

Definitely. Pass an allowedtools list when configuring the spec. You can grant read-only access by only including the list and get commands, keeping destructive actions off the table.

Index your chargeback alerts and deflection logs directly into LlamaIndex for semantic querying.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chargeblast MCP to LlamaIndex

Create your Vinkius account to connect Chargeblast 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 Chargeblast with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a searchable dispute knowledge base

LlamaIndex takes the output from `list_dispute_alerts` and embeds it directly into your vector store. Raw API responses are hard to query historically. Your application can now search across months of fraud attempts using natural language instead of rigid database queries. When a user asks about recent chargeback trends, the engine does not guess. It pulls the exact context from your indexed alerts. You can also run `get_dispute_alert_details` to enrich specific high-value cases before adding them to the index.

Ground your RAG apps in real order data

Pass `list_uploaded_orders` to your FunctionAgent to give it direct access to your transaction history. Giving an agent access to your history usually requires building custom scrapers. Here, it grabs the exact receipts sent for deflection and makes them immediately available for retrieval. You can map these orders to specific storefronts by indexing the results of `list_enrolled_merchants`. If a support rep asks why a specific store has a high refund rate, the engine cross-references the merchant data with the order history to generate a factual answer.

Take action through your MCP Server

Configure `update_alert_status` in your allowed tools list to let LlamaIndex fix problematic transactions. LlamaIndex is not just for reading static documents anymore. Once the engine finds a problematic transaction in your index, it can reach out and fix it. The agent identifies a false positive from the vector search and immediately calls `request_dispute_credit` to reclaim the alert fee. You get a unified system that both understands your historical fraud patterns and actively manages them.

Setup guide

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

Install the llama-index-tools-mcp package. Create a BasicMCPClient with your Vinkius URL, wrap it in an McpToolSpec, and call to_tool_list_async() to feed it to your agent.

Yes. You can write a script that periodically runs list_deflection_logs and feeds the JSON array into a Document object. Your engine will embed the logs for future querying.

The framework reads the descriptions from the MCP protocol. When a user asks to upload a receipt, the agent matches the intent to upload_order_data and executes the function.

Definitely. Pass an allowed_tools list when configuring the spec. You can grant read-only access by only including the list and get commands, keeping destructive actions off the table.

We route your requests through an ephemeral, zero-trust environment. Your merchant IDs, dispute amounts, and customer names exist in memory just long enough to complete the API call, then vanish entirely.

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