How to Use the Hiro.fm MCP in LlamaIndex

Q: How do I index Hiro.fm audio metadata into LlamaIndex using the MCP Server?

Call listaudio using the McpToolSpec to retrieve your episode list. LlamaIndex converts this JSON output into document nodes, which you can then ingest into any vector database.

Q: Can LlamaIndex query engines check if a listener has Hiro.fm access?

Yes, the LlamaIndex engine calls getcontact to check active tags before answering user queries. This ensures your RAG application only displays private Hiro.fm details to authorized listeners.

Q: How does the Hiro.fm MCP Server prevent hallucinations in LlamaIndex?

By grounding the LLM in real-time data from listshows and listcontacts. The LlamaIndex agent relies on actual API payloads instead of guessing which private feeds exist.

Q: Can I build a conversational support agent for Hiro.fm using LlamaIndex?

You can build a FunctionAgent that uses grantaccess and revokeaccess to manage Hiro.fm feeds. The LlamaIndex agent queries your indexed customer records to make safe, context-backed permission changes.

Index private audio metadata and query listener access logs directly inside your LlamaIndex RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hiro.fm MCP to LlamaIndex

Create your Vinkius account to connect Hiro.fm 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 Hiro.fm with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Hiro.fm audio feeds with LlamaIndex

Use `list_audio` to extract your Hiro.fm episode catalog and index the metadata directly into your LlamaIndex vector store. This lets your LlamaIndex query engine find relevant private Hiro.fm episodes based on semantic user queries. The LlamaIndex agent calls `get_show` to pull context before running a search, ensuring your responses are grounded in actual Hiro.fm API data. This setup eliminates hallucinations by feeding real Hiro.fm show structures into your LlamaIndex context window.

Query listener access records via RAG

Use `list_contacts` to load your Hiro.fm listener database into a queryable LlamaIndex document store. Your LlamaIndex agent can then answer natural language questions about who has active access to your private Hiro.fm feeds. By calling `get_contact` on demand, the LlamaIndex agent retrieves specific tag histories to resolve Hiro.fm access issues. This MCP Server integration ensures your LlamaIndex support agent always works with real-time customer permission states in Hiro.fm.

Audit Hiro.fm permissions using LlamaIndex

Use `list_shows` alongside `list_tags` to map which user groups have access to which private Hiro.fm audio feeds inside LlamaIndex. LlamaIndex indexes these relationships so you can search for anomalies or unauthorized access patterns in your Hiro.fm listener base. If the LlamaIndex system detects an unassigned user, it can trigger `grant_access` or `revoke_access` to correct the Hiro.fm permissions. This keeps your private Hiro.fm audio distribution secure without requiring manual spreadsheet audits inside your LlamaIndex pipeline.

Setup guide

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

Call `list_audio` using the McpToolSpec to retrieve your episode list. LlamaIndex converts this JSON output into document nodes, which you can then ingest into any vector database.

Yes, the LlamaIndex engine calls `get_contact` to check active tags before answering user queries. This ensures your RAG application only displays private Hiro.fm details to authorized listeners.

By grounding the LLM in real-time data from `list_shows` and `list_contacts`. The LlamaIndex agent relies on actual API payloads instead of guessing which private feeds exist.

You can build a FunctionAgent that uses `grant_access` and `revoke_access` to manage Hiro.fm feeds. The LlamaIndex agent queries your indexed customer records to make safe, context-backed permission changes.

No, the server handles raw MP3 URLs securely via ephemeral tokens, meaning no direct audio file links are exposed to LlamaIndex. Only text-based metadata retrieved from `get_show` is indexed, preserving your content security.

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