How to Use the MediaWiki MCP in LangChain

Q: What happens if a search returns too many results?

The searchpages tool returns a paginated list of matches. Your agent should be prompted to process these in batches or narrow down the query parameters.

Feed live wiki data directly into your LangChain reasoning loops and write page updates based on chain outputs.

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 LangChain

Create your Vinkius account to connect MediaWiki to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain MediaWiki search queries with LangChain

This MediaWiki MCP Server lets your LangChain agent run full-text searches across your wiki using `search_pages` and then instantly fetch contents with `get_page_revisions`. The agent takes the search results, passes them through your prompt template, and determines if a page requires modification. Once the chain decides on an edit, it requests a CSRF token using `get_tokens` and writes the update directly via `edit_page`. You can trace this entire multi-step decision process in LangSmith to see exactly how the agent formulated its wiki updates.

Map category structures in LangChain

This MediaWiki toolset enables your LangChain chains to traverse complex category hierarchies using `list_category_members` and `get_page_categories`. Your agent reads the category tree, identifies missing links, and plans directory structures without human intervention. By feeding these category lists into a routing chain, the agent decides which branch of your LangChain pipeline should handle the document. This approach replaces hardcoded MediaWiki API scripts with dynamic, context-aware content sorting inside LangChain.

Track wiki changes in LangChain loops

This MediaWiki MCP Server integration feeds recent edits straight into your LangChain agentic workflows using `list_recent_changes`. The agent monitors this real-time MediaWiki feed to trigger specific downstream tasks, like notifying Slack or updating a vector database when a page changes. It retrieves the exact metadata with `get_page_info` and checks who made the modification using `get_user_info`. You get a completely automated monitoring loop that connects MediaWiki activity directly to your custom LangChain chains.

Setup guide

Set up MediaWiki MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes MediaWiki tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "mediawiki-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent MediaWiki transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You configure the credentials as environment variables when launching the server. The LangChain agent accesses these credentials implicitly by calling `get_tokens` to authorize write actions like page edits.

Yes, the agent executes writes by chaining two tools. It first requests a CSRF token using `get_tokens`, then passes that token directly into the `edit_page` payload.

Use LangSmith to trace the execution of your agent. You will see the exact inputs, outputs, and latency for tools like `get_page_revisions` or `search_pages` in your run logs.

The `search_pages` tool returns a paginated list of matches. Your agent should be prompted to process these in batches or narrow down the query parameters.

Your CSRF tokens and wiki page content remain entirely within your local execution environment or secure Vinkius sandbox. No authentication data or raw wiki text is sent to external third-party 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