How to Use the Afosto MCP in LlamaIndex

Q: How do I index my Afosto catalog with LlamaIndex using MCP?

Use llama-index-tools-mcp to connect to the Vinkius endpoint. Retrieve product data using listproducts and pass the output to your indexer. This creates a searchable vector representation of your live store.

Q: Can LlamaIndex search customer history in Afosto?

Yes. The listcustomers tool retrieves centralized customer profiles and their historical shopping behavior. LlamaIndex indexes these profiles, allowing your agent to search for high-value buyers or common purchase patterns.

Q: How do I limit which Afosto tools LlamaIndex can access?

Pass an allowedtools list to your McpToolSpec constructor. This restricts the agent to specific operations, like only checking product listings while blocking order histories.

Ground your LlamaIndex RAG pipelines with live Afosto catalog, order, and inventory data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Afosto MCP to LlamaIndex

Create your Vinkius account to connect Afosto 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 Afosto with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build search indexes from real-time store catalogs

The `list_products` tool extracts your live product catalog, complete with active variants and pricing. LlamaIndex takes this raw data and indexes it directly into your vector store. Your agent then answers user queries using actual, current store listings instead of outdated static files. This method prevents hallucinations about product availability or pricing. Your RAG setup queries the vector index first to find matching items. If the user asks for specifics, the agent pulls fresh details live from the server.

Ground customer support queries in real-time order data

The `list_orders` tool retrieves recent multi-channel orders to provide instant context for user queries. LlamaIndex indexes these order records so your support bot can search past transactions semantically. When a customer asks about a delivery, the agent finds the exact order in seconds. You configure this by wrapping the client in `McpToolSpec` and passing it to a `FunctionAgent`. The agent decides when to query the live API and when to search the vector index. This keeps your support responses grounded in factual transaction records.

Run RAG-driven stock checks using this MCP Server

The `list_inventory` tool provides real-time stock levels aggregated across all your warehouse locations. LlamaIndex uses this data to update its knowledge base dynamically during customer conversations. Your agent will never recommend an out-of-stock item because it checks the indexed warehouse numbers first. To set this up, install `llama-index-tools-mcp` and initialize the basic client. You can filter the tools using the `allowed_tools` list to only expose inventory checks to specific agents. This keeps your pipeline fast and secure.

Setup guide

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

Use `llama-index-tools-mcp` to connect to the Vinkius endpoint. Retrieve product data using `list_products` and pass the output to your indexer. This creates a searchable vector representation of your live store.

Yes. The `list_customers` tool retrieves centralized customer profiles and their historical shopping behavior. LlamaIndex indexes these profiles, allowing your agent to search for high-value buyers or common purchase patterns.

Pass an `allowed_tools` list to your `McpToolSpec` constructor. This restricts the agent to specific operations, like only checking product listings while blocking order histories.

Yes. While LlamaIndex indexes data for semantic search, the MCP Server calls the live API. Your agent gets the most current stock and order details every time it executes a tool.

Inventory numbers and warehouse locations are processed entirely within an ephemeral V8 sandbox. Vinkius secures the connection with zero-trust protocols managed by the MCP Server, ensuring your stock levels are never exposed to public registries.

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