How to Use the Pylon MCP in LlamaIndex

Q: How do I build a query engine over Pylon articles in LlamaIndex?

You start by calling listarticles to fetch your documentation. Then, load these documents into a LlamaIndex VectorStoreIndex to enable semantic search and natural language queries over your support base.

Q: Can LlamaIndex agents update issues in Pylon?

Yes, the agent can use updateissue or replytoissue based on its reasoning loop. The LlamaIndex FunctionAgent evaluates the query, retrieves context from your index, and then executes the write tool.

Q: How do I load Pylon account details into a LlamaIndex pipeline?

You use the MCP tool spec to expose listaccounts to your agent. The pipeline calls this tool, extracts the customer metadata, and injects it directly into the LLM prompt context for personalized responses.

Q: Is live data fetched every time a query runs?

Yes, the agent calls tools like getissue in real-time to fetch the latest state. This guarantees your pipeline never relies on stale ticket statuses or outdated message threads.

Q: How is my B2B customer and ticket data protected?

All data fetched via getissue and listaccounts is processed in memory during the LlamaIndex query lifecycle. Vinkius runs this MCP Server in an ephemeral sandbox, ensuring your support tickets and account records are never written to persistent disk.

Index live Pylon support issues and knowledge bases directly into LlamaIndex for grounded, hallucination-free RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pylon MCP to LlamaIndex

Create your Vinkius account to connect Pylon to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pylon with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index Pylon knowledge bases for LlamaIndex RAG

This MCP Server connects LlamaIndex directly to your documentation using `list_knowledge_bases` and `list_articles`. Your pipeline pulls these articles, indexes them into a vector store, and uses them to answer customer questions. Grounding your responses in actual documentation prevents the model from making up answers. The agent queries this index first, ensuring every drafted message matches your official support guidelines.

Build semantic search indexes over customer accounts

The Pylon MCP Server exposes `list_accounts` and `get_account` to let LlamaIndex build a searchable index of your customer profiles. Your pipeline matches incoming tickets against this historical account data. Agents use this contextual index to understand which accounts are enterprise-tier. This enables automated, high-priority ticket routing based on actual account value instead of basic keyword matching.

Query past support threads to ground new replies

Your agent calls `get_issue_messages` to retrieve historical ticket conversations and index them on the fly. LlamaIndex uses this real-time index to find similar past issues and resolutions. When a new ticket arrives, the agent runs a semantic query against this conversation index. It then uses `reply_to_issue` to send a highly accurate response based on how your team solved the problem last time.

Setup guide

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

You start by calling `list_articles` to fetch your documentation. Then, load these documents into a LlamaIndex VectorStoreIndex to enable semantic search and natural language queries over your support base.

Yes, the agent can use `update_issue` or `reply_to_issue` based on its reasoning loop. The LlamaIndex FunctionAgent evaluates the query, retrieves context from your index, and then executes the write tool.

You use the MCP tool spec to expose `list_accounts` to your agent. The pipeline calls this tool, extracts the customer metadata, and injects it directly into the LLM prompt context for personalized responses.

Yes, the agent calls tools like `get_issue` in real-time to fetch the latest state. This guarantees your pipeline never relies on stale ticket statuses or outdated message threads.

All data fetched via `get_issue` and `list_accounts` is processed in memory during the LlamaIndex query lifecycle. Vinkius runs this MCP Server in an ephemeral sandbox, ensuring your support tickets and account records are never written to persistent disk.

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