How to Use the AssemblyAI MCP in LlamaIndex

Q: How do I load AssemblyAI tools into LlamaIndex?

Use BasicMCPClient to hit your Vinkius URL, then wrap it in McpToolSpec. Call totoollistasync() and hand the resulting array to your FunctionAgent.

Q: How do I filter which audio tools my agent can access?

Pass an allowedtools array when initializing the spec. You might restrict a public-facing bot to only read operations while keeping the deletion tools hidden.

Turn podcasts and meeting recordings into searchable vector stores by connecting LlamaIndex to this AssemblyAI integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AssemblyAI MCP to LlamaIndex

Create your Vinkius account to connect AssemblyAI 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 AssemblyAI with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index speech into LlamaIndex RAG.

The AssemblyAI MCP Server transforms raw media URLs into indexable knowledge instantly. Your application triggers `transcribe_audio` to process a recording, turning an hour-long meeting into structured text. Instead of just returning a string, LlamaIndex can ingest that output straight into a vector database. You query your past audio sessions the exact same way you query a text document.

Semantic chunking at the source.

Effective RAG depends heavily on how you split your source material. Rather than writing custom regex, your agent calls `get_transcript_paragraphs` to pull pre-chunked, context-aware blocks of speech. For dense technical discussions requiring pinpoint retrieval, `get_transcript_sentences` provides granular nodes for your index. The MCP integration maps these API outputs into searchable documents before you write a single embedding function.

Audit and maintain your audio base.

Keeping your vector store synced with your actual media archive requires active management. A background routine can run `list_transcripts` to cross-reference completed API jobs against your indexed documents. When a user deletes a recording from your system, the agent executes `delete_transcript` to mirror that state upstream. This keeps your RAG application grounded in reality without leaving ghost files sitting on external servers.

Setup guide

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

Use `BasicMCPClient` to hit your Vinkius URL, then wrap it in `McpToolSpec`. Call `to_tool_list_async()` and hand the resulting array to your `FunctionAgent`.

The agent decides when to fetch data based on user prompts. If someone asks about a specific meeting, the system runs the fetch tool and synthesizes an answer from the returned text.

The core tools extract the raw text, paragraphs, or sentences from the audio. You will need to parse the resulting JSON payload if you want to index specific speaker metadata alongside the dialogue.

Pass an `allowed_tools` array when initializing the spec. You might restrict a public-facing bot to only read operations while keeping the deletion tools hidden.

The Vinkius endpoint acts as an ephemeral bridge for your media URLs and text results. We process the API handshakes in a zero-trust sandbox, meaning your transcription chunks go straight from the provider to your vector store.

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