How to Use the Awattar MCP in LlamaIndex

Q: How do I index Awattar market data into LlamaIndex?

You use the llama-index-tools-mcp package to initialize the basic client and wrap it in a McpToolSpec. This lets you convert the pricing tools into standard LlamaIndex tools that your query engine can run and index.

Q: Can a LlamaIndex agent compare historical Awattar rates with live data?

Yes, by indexing past getmarketdata outputs into a vector store and calling the live tool for current rates. The agent can run comparative queries to find out if today's peak hours match historical averages.

Q: How does the Awattar MCP server format YAML data for LlamaIndex?

The server uses getcurrentyaml to output structured pricing statistics. LlamaIndex ingestion pipelines can read this text directly, splitting it into clean document nodes without extra parsing logic.

Q: Can I restrict which Awattar tools LlamaIndex can access?

Yes, you can use the allowedtools filter during tool specification setup. This allows you to expose only getmarketdata if you want to block the agent from reading the YAML config tool.

Index live EPEX Spot electricity prices from Awattar into LlamaIndex to query historical rate trends and automate smart home decisions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Awattar MCP to LlamaIndex

Create your Vinkius account to connect Awattar 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 Awattar with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Searchable Energy Knowledge Base

The `get_market_data` tool feeds hourly EPEX Spot prices directly into your LlamaIndex vector store for long-term semantic analysis. Instead of just reacting to immediate prices, your agent indexes daily rate changes to detect weekly pricing patterns. This MCP integration turns raw API outputs into searchable documents that your RAG pipeline can reference later. You can ask your agent when rates typically dip on weekends, and it will answer based on indexed Awattar data rather than guessing.

Query YAML Automation Configurations Directly

The `get_current_yaml` tool provides structured price stats that LlamaIndex parses into clean, queryable nodes. Your agent compares these real-time YAML blocks against your existing smart home configuration files to identify optimization gaps. Having this direct MCP server access means your agent can retrieve, index, and analyze current grid tariffs in a single step. You avoid writing custom scraping scripts because the model reads the structured YAML payload as a clean data source.

Ground LlamaIndex Decisions in Actual Market Data

Calling the `get_market_data` tool ensures your RAG pipeline uses live EPEX Spot figures rather than static, outdated training data. LlamaIndex queries the active endpoint every time a high-load automation runs to prevent expensive scheduling mistakes. This live validation protects your smart home setup from executing actions based on stale cache files. The MCP connection guarantees that your agent has immediate access to the 14:00 CET price updates as soon as they drop.

Setup guide

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

You use the `llama-index-tools-mcp` package to initialize the basic client and wrap it in a `McpToolSpec`. This lets you convert the pricing tools into standard LlamaIndex tools that your query engine can run and index.

Yes, by indexing past `get_market_data` outputs into a vector store and calling the live tool for current rates. The agent can run comparative queries to find out if today's peak hours match historical averages.

The server uses `get_current_yaml` to output structured pricing statistics. LlamaIndex ingestion pipelines can read this text directly, splitting it into clean document nodes without extra parsing logic.

Yes, you can use the `allowed_tools` filter during tool specification setup. This allows you to expose only `get_market_data` if you want to block the agent from reading the YAML config tool.

No, because this MCP server only reads public EPEX Spot market rates and local YAML formatting templates. Your indexed vector database remains local, and no private home automation details or pricing logs are uploaded to external servers.

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