How to Use the Lyrics.ovh MCP in LlamaIndex

Q: How do I index song lyrics from Lyrics.ovh into LlamaIndex?

You run getlyrics to retrieve the text, then wrap the output in a LlamaIndex Document object. From there, your ingestion pipeline parses and indexes the lyrics into your vector database.

Q: Can LlamaIndex agents use Lyrics.ovh to run semantic search?

No, suggestsongs queries the live API for direct matches, but you can index those suggestions into LlamaIndex to enable semantic search over the results. This combines live API data with vector-based retrieval.

Q: Does this MCP Server support data filtering in LlamaIndex?

Yes, you can use the allowedtools filter to restrict your agent to only getlyrics or suggestsongs. This keeps your agent focused on music retrieval without exposing unnecessary tools.

Index live lyrics and track suggestions directly into your LlamaIndex vector store for semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lyrics.ovh MCP to LlamaIndex

Create your Vinkius account to connect Lyrics.ovh 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 Lyrics.ovh with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live lyrics directly into LlamaIndex

The `get_lyrics` tool pulls raw lyric text directly into your LlamaIndex data ingestion pipeline. Your pipeline indexes these song texts into a vector store, making the actual lyric content searchable via semantic queries. This turns static music data into a dynamic knowledge base. Your RAG application queries the indexed lyrics to find matches based on meaning rather than just exact keyword matches.

Build music-aware RAG with this MCP Server

This MCP Server connects your LlamaIndex query engines to real-time music metadata. By exposing `suggest_songs`, the server lets your index agent query the API to resolve missing context before generating an answer. The agent retrieves live suggestions and combines them with your local documents. This prevents hallucinations when users ask about obscure tracks or recent releases.

Query live song databases using McpToolSpec

The `suggest_songs` tool integrates into your LlamaIndex agent via the McpToolSpec class. Your agent calls this tool to search the live database whenever a user asks for song recommendations. You convert the server tools using the async tool list method. This lets your FunctionAgent call the music search functions asynchronously alongside your other indexing tools.

Setup guide

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

You run `get_lyrics` to retrieve the text, then wrap the output in a LlamaIndex Document object. From there, your ingestion pipeline parses and indexes the lyrics into your vector database.

No, `suggest_songs` queries the live API for direct matches, but you can index those suggestions into LlamaIndex to enable semantic search over the results. This combines live API data with vector-based retrieval.

You initialize the MCP client, pass it to McpToolSpec, and call the async tool list method. Then, pass the resulting tools directly to your LlamaIndex agent.

Yes, you can use the allowed_tools filter to restrict your agent to only `get_lyrics` or `suggest_songs`. This keeps your agent focused on music retrieval without exposing unnecessary tools.

Your artist names and song queries are processed ephemerally in a secure V8 isolate. Vinkius does not log or persist the lyric texts or search terms requested by your LlamaIndex pipeline.

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