How to Use the MediaWiki MCP in LlamaIndex

Q: How do I index a specific MediaWiki category with LlamaIndex using the MCP Server?

Use listcategorymembers to get all page titles within that category. Your LlamaIndex pipeline then loops through these titles, fetches their content with getpagerevisions, and inserts them into your vector store.

Q: How does this MediaWiki MCP Server integration prevent LlamaIndex hallucinations?

It acts as a live data retriever. By using searchpages and getpagerevisions, the agent grounds its answers in your actual wiki content instead of guessing.

Q: Can I inspect the site configuration before indexing?

Yes, you can run getsiteinfo to retrieve general wiki settings. This helps your agent understand namespaces and limits before starting a bulk crawl.

Index live wiki articles into your LlamaIndex vector store to build RAG systems that never hallucinate.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MediaWiki MCP to LlamaIndex

Create your Vinkius account to connect MediaWiki 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 MediaWiki with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed MediaWiki pages into LlamaIndex RAG

This MediaWiki MCP Server pulls raw text from your wiki using `get_page_revisions` and parses it directly into LlamaIndex Document objects. Your agent indexes these documents into a vector database, creating a searchable knowledge base of your internal wiki. Instead of relying on static file dumps, your RAG pipeline queries live wiki data on demand. The agent searches for relevant pages using `search_pages` before retrieving the full text, ensuring your index stays current.

Build indexes from categories

This MediaWiki toolset lets your LlamaIndex pipeline structure its index based on wiki taxonomy using `list_category_members` and `get_page_categories`. Your agent crawls specific categories to build targeted vector indexes for different departments. It reads the internal links using `get_page_links` to understand how articles relate to each other. This physical structure translates directly into a hierarchical retriever in LlamaIndex, improving search accuracy.

Track recent edits for index updates

This MediaWiki MCP Server connection helps you keep your LlamaIndex vector store synchronized by monitoring edits with `list_recent_changes`. The agent identifies which pages have changed since the last indexing run. It retrieves basic page metadata using `get_page_info` to determine if a full re-index is necessary. This targeted update mechanism prevents you from wasting API rate limits on unchanged pages.

Setup guide

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

Use `list_category_members` to get all page titles within that category. Your LlamaIndex pipeline then loops through these titles, fetches their content with `get_page_revisions`, and inserts them into your vector store.

Yes, if your agent determines an update is needed, it calls `get_tokens` to fetch a CSRF token. It then writes the generated answer back to the wiki using `edit_page`.

It acts as a live data retriever. By using `search_pages` and `get_page_revisions`, the agent grounds its answers in your actual wiki content instead of guessing.

Yes, you can run `get_site_info` to retrieve general wiki settings. This helps your agent understand namespaces and limits before starting a bulk crawl.

The raw page text and category lists fetched by this MCP Server are processed locally in your LlamaIndex application. Your wiki data is only sent to your designated vector database.

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