How to Use the Wikidata MCP in LlamaIndex

Q: How do I search items using Wikidata and LlamaIndex?

You use the searchitemsvector tool. The result of this vector lookup is then indexed by LlamaIndex, allowing you to query that specific item data semantically later on.

Q: What kind of data can LlamaIndex handle from Wikidata?

It handles structured statements and descriptions (getitemstatements, setitemdescription). By indexing this output, you create a unified knowledge base that mixes API facts with your own internal documents.

Build searchable knowledge bases grounded in Wikidata API data using LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wikidata MCP to LlamaIndex

Create your Vinkius account to connect Wikidata 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 Wikidata with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index search results for deep context

LlamaIndex takes the output from tools like `get_item_statements` and indexes them into your vector store. You don't just read data; you make it part of a searchable knowledge base. This means you can query past API sessions or configurations, getting answers grounded in actual Wikidata records instead of relying on hallucinations.

Perform hybrid searches for entities

You start by running vector lookups. Use `search_items_vector` and `search_properties_vector` to find relevant items or attributes based on semantics, not just keywords. These search results are then fed into the index, allowing your RAG application to combine live API data with static documents for comprehensive answers.

Run and interpret complex graph queries

The `execute_sparql` tool lets you pull raw data from Wikidata. By indexing this output, LlamaIndex allows your agent to search *about* the query results themselves. This is crucial for analyzing patterns across multiple runs. You can ask questions like, 'What common properties did all these SPARQL queries return?'

Setup guide

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

You use the `search_items_vector` tool. The result of this vector lookup is then indexed by LlamaIndex, allowing you to query that specific item data semantically later on.

It handles structured statements and descriptions (`get_item_statements`, `set_item_description`). By indexing this output, you create a unified knowledge base that mixes API facts with your own internal documents.

Yes. Since the tool outputs are indexed into the vector store, you can query past sessions' results. This lets you ground answers in actual API responses from previous runs against Wikidata.

It helps by making the raw data manageable and searchable. Instead of just retrieving a list, your agent gets an index that allows it to query relationships and facts across many different items or properties.

This server touches structured statements and item descriptions. The data type indexed belongs to the knowledge graph, giving your agent access to highly structured facts about entities.

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