How to Use the MediaWiki MCP in Vercel AI SDK

Q: How do I configure the MediaWiki MCP Server with the Vercel AI SDK?

Install the @ai-sdk/mcp package and set up the client using createMCPClient. Pass the Vinkius URL to the transport option and call mcpClient.tools() to register the tools.

Q: Can I use the Vercel AI SDK to edit MediaWiki pages?

Yes, you can write edits. The agent uses gettokens to acquire a CSRF token, then calls editpage to update the target wiki page.

Q: Can I restrict which MediaWiki tools my Vercel AI SDK app can access?

Yes, you can filter the array returned by mcpClient.tools() before passing them to your generation function. This prevents the model from calling tools like createaccount if you only want read-only access.

Feed live MediaWiki page updates and search results directly into your React UI using the Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect MediaWiki to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render MediaWiki search results live in Vercel AI SDK

Our `search_pages` and `get_page_info` tools let you pull raw wiki data directly into your edge-rendered frontend. Your agent uses these endpoints to locate articles and grab metadata without hitting slow backend proxies. Because the Vercel AI SDK supports real-time streaming, users see wiki text populate their screens instantly. You avoid the typical loading spinners by feeding the JSON output from `list_all_pages` straight into the UI thread.

Perform instant wiki edits via this MCP Server

The `edit_page` and `get_tokens` tools allow your web app to write updates back to your corporate knowledge base. To make edits, the server grabs a CSRF token and commits the new markdown in one fluid motion. This MCP Server runs inside Vinkius's secure sandboxed environment, meaning your edge functions stay lightweight. Your Vercel AI SDK agents can draft, verify, and publish revisions without managing heavy third-party libraries.

Track recent edits directly inside your React components

Using `list_recent_changes` and `get_page_revisions`, you can build a live dashboard that monitors wiki activity. The server fetches the latest edits and parses the metadata for immediate display. By combining these tools with the Vercel AI SDK, your app can automatically alert users when critical pages change. The entire pipeline runs on the edge, keeping your interface fast and highly responsive.

Setup guide

Set up MediaWiki MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all MediaWiki tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent MediaWiki transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install the `@ai-sdk/mcp` package and set up the client using `createMCPClient`. Pass the Vinkius URL to the transport option and call `mcpClient.tools()` to register the tools.

Yes, you can write edits. The agent uses `get_tokens` to acquire a CSRF token, then calls `edit_page` to update the target wiki page.

Vinkius hosts the server on optimized infrastructure, keeping response times low. Since the Vercel AI SDK streams the data as it arrives, you avoid hitting the standard edge execution limits.

Yes, you can filter the array returned by `mcpClient.tools()` before passing them to your generation function. This prevents the model from calling tools like `create_account` if you only want read-only access.

Your wiki passwords and CSRF tokens are never stored on your frontend or logged by Vinkius. The MCP Server processes these sensitive tokens in ephemeral V8 isolates, discarding them immediately after the edit completes.

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