How to Use the Inworld AI MCP in LlamaIndex

Q: Can LlamaIndex index the metadata of my Inworld AI voice profiles?

Yes, you can query listvoices to get all voice metadata and insert it into a VectorStoreIndex. This lets your agent run semantic searches to select the perfect voice ID for synthesis.

Q: Does this MCP Server support real-time audio transcription in LlamaIndex?

Absolutely, you can use transcribeaudio to convert user voice inputs into text before sending them to your query engine. The index then searches against the transcribed text to find the right nodes.

Ground your LlamaIndex RAG pipelines in real-time voice configurations and dynamic character routers.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Inworld AI MCP to LlamaIndex

Create your Vinkius account to connect Inworld AI 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 Inworld AI with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index and search your custom voice profiles

Calling `list_voices` and `get_voice` lets LlamaIndex index your entire voice library directly into a vector store. Don't let your RAG agent guess which voice profile to use when responding to user queries. When a user asks for a specific tone, your query engine searches the index, finds the best match, and feeds the voice ID to `synthesize_speech_sync`. Grounded voice selections mean your agent always speaks in the exact tone your data dictates.

Semantic routing powered by LlamaIndex queries

Running `list_routers` and `get_router` lets your index act as a dynamic directory of your narrative assets. Managing multiple character profiles gets messy as your codebase grows, making structured retrieval through an MCP connection essential. Your query pipeline can automatically determine if a router needs a tweak, executing `update_router` to sync the character's background info with new documents loaded into your vector store. No manual code updates are required when your underlying files change.

Document-grounded voice synthesis workflows

Combining retrieval steps with `chat_completions` gives your documents a literal voice during active RAG queries. This MCP Server lets your pipeline retrieve text chunks, run them through the router, and synthesize the output. By calling `synthesize_speech_stream` right after the node post-processor step, you bypass intermediate text displays. Users hear the retrieved knowledge read back to them instantly.

Setup guide

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

Yes, you can query `list_voices` to get all voice metadata and insert it into a VectorStoreIndex. This lets your agent run semantic searches to select the perfect voice ID for synthesis.

You can build a pipeline that reads updated documents and calls `update_router` to refresh the router's prompt context. This keeps your character's knowledge base perfectly aligned with your local files.

Absolutely, you can use `transcribe_audio` to convert user voice inputs into text before sending them to your query engine. The index then searches against the transcribed text to find the right nodes.

You feed the response text from your query engine straight into `synthesize_speech_stream`. This streams the audio bytes back to your client, reducing the perceived latency of long RAG answers.

Your router settings and prompt text are isolated within the Vinkius secure V8 sandbox. No third-party services can access your configuration data, keeping your intellectual property completely locked down.

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