How to Use the Spiritme MCP in LlamaIndex

Q: How can Spiritme and LlamaIndex improve my corporate reporting?

You index the output of listvideos alongside other documents. This lets your agent answer complex questions by combining API data (video IDs) with internal reports, creating a single source of truth.

Q: What happens if I want to know about voice usage in LlamaIndex?

You index the results from listvoices and getvoice. Your agent can then answer specific questions like, 'Which voices are available in German?' or 'What is the bitrate of Voice Y?' based purely on the data.

Q: Does Spiritme handle video deletions when used with LlamaIndex?

Yes. You can index logs showing successful calls to deletevideo. This helps you track which content was removed and why, maintaining a searchable record of your content lifecycle.

Q: Is the data from Spiritme reliable when integrated with LlamaIndex?

The output is grounded in API calls. If checkspiritmestatus returns 'OK', you know the connection was live, and any indexed data derived from that point should be accurate.

Ground your AI with Spiritme data using LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Spiritme MCP to LlamaIndex

Create your Vinkius account to connect Spiritme to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Spiritme with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Query Past Video Data in LlamaIndex

The `list_videos` tool provides a record of all previously generated video IDs. When you index this output, your RAG application can answer questions like, 'What videos did we create last month?' without hallucinating or hitting rate limits. This capability is huge for compliance and auditing. You're not just running the API; you're turning the API into a searchable knowledge base that grounds every subsequent query in real data.

Retain Configuration Details with LlamaIndex

Use `get_template` and `list_templates` to capture specific configuration details. Instead of just remembering 'we used a template,' your index stores the actual template ID, its associated fields, and any constraints applied. This means when you query the system later, it returns concrete data points—like needing a certain type of avatar or voice—allowing for much better retrieval than simple chat history.

Track Changes with MCP Server

The `get_job_status` tool output is highly valuable index material. When you run a video generation job, the status changes (e.g., 'PENDING' to 'COMPLETE'). Indexing these state transitions allows your agent to answer, 'What was the last known status of Video X?' It turns real-time operational data into historical, queryable knowledge, which is exactly what LlamaIndex excels at.

Setup guide

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

You index the output of `list_videos` alongside other documents. This lets your agent answer complex questions by combining API data (video IDs) with internal reports, creating a single source of truth.

You index the results from `list_voices` and `get_voice`. Your agent can then answer specific questions like, 'Which voices are available in German?' or 'What is the bitrate of Voice Y?' based purely on the data.

Yes. You can index logs showing successful calls to `delete_video`. This helps you track which content was removed and why, maintaining a searchable record of your content lifecycle.

The output is grounded in API calls. If `check_spiritme_status` returns 'OK', you know the connection was live, and any indexed data derived from that point should be accurate.

This server touches video metadata (IDs), voice details, template configurations, and job status. All of these structured inputs become searchable knowledge chunks in your index.

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