How to Use the AssemblyAI MCP in LlamaIndex

Q: How do I connect the AssemblyAI MCP Server to LlamaIndex?

Install llama-index-tools-mcp. Create a BasicMCPClient with your Vinkius URL, wrap it in McpToolSpec, and pass the async tool list to your FunctionAgent.

Q: Can LlamaIndex search through AssemblyAI speaker data?

Yes. Your agent retrieves the dialogue structure via getspeakers and attaches it as node metadata. You can restrict RAG queries to specific speakers.

Q: Does LlamaIndex support AssemblyAI sentiment analysis?

You can pull mood data using getsentiments and index it alongside the text. This lets you query your vector store for angry customer calls or positive feedback segments.

Q: How do I handle large video files with LlamaIndex?

The agent submits the media via transcribeaudiourl. Once finished, it pulls getsummary to create a high-level index entry, then chunks the full transcript for deep retrieval.

Turn spoken audio into searchable vector data by connecting AssemblyAI to LlamaIndex via our managed MCP Server.

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 Audio with AssemblyAI

Your agent embeds raw audio transcripts directly into vector stores. A LlamaIndex agent calls `transcribe_audio_url` on a podcast feed over the MCP connection and pulls the full text via `get_transcript`. That text immediately becomes a Document object in your index. Your users then query their audio archives. They ask a question, and LlamaIndex runs a semantic search over the ingested transcripts. The system grounds the final answer in exact quotes from the original recording.

Semantic Search over Spoken Data

Topic metadata gives your audio transcripts exact search structure. You use the `get_chapters` and `get_topics` tools to generate tags for your RAG nodes. When LlamaIndex chunks the transcript, it attaches the exact topic labels to each segment. This makes retrieval incredibly precise. If a user searches for specific financial projections, the engine filters by the topic metadata before running the vector similarity search. You get accurate answers from hours of recorded meetings.

AssemblyAI MCP Server Integrations

Routine audio ingestion happens automatically with a FunctionAgent. It runs `list_transcripts` to find new files, extracts the speaker labels using `get_speakers`, and formats the dialogue for indexing. Once the data is safely embedded, the agent executes `delete_transcript` to clean up the backend. You build a self-updating, searchable knowledge base of voice data with minimal code.

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

Install `llama-index-tools-mcp`. Create a `BasicMCPClient` with your Vinkius URL, wrap it in `McpToolSpec`, and pass the async tool list to your `FunctionAgent`.

Yes. Your agent retrieves the dialogue structure via `get_speakers` and attaches it as node metadata. You can restrict RAG queries to specific speakers.

You can pull mood data using `get_sentiments` and index it alongside the text. This lets you query your vector store for angry customer calls or positive feedback segments.

The agent submits the media via `transcribe_audio_url`. Once finished, it pulls `get_summary` to create a high-level index entry, then chunks the full transcript for deep retrieval.

Your media files and transcript text flow through a stateless MCP connection. Vinkius requires only a single endpoint token to authenticate the request, ensuring your proprietary recordings never hit unauthorized disks.

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