How to Use the MediaWiki MCP in OpenAI Agents SDK

Q: How do I search for MediaWiki content using my OpenAI Agents SDK?

Use the searchpages tool directly within your agent loop. It performs a full-text search against the instance and returns the results for your agent to process.

Q: Can the OpenAI Agents SDK edit pages on my MediaWiki site?

Yes, but you must fetch a CSRF token first using gettokens. Once you have the token, pass it to editpage to commit your changes securely.

Connect your OpenAI Agents SDK to any MediaWiki instance to read pages and track recent edits with production-grade safety.

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 OpenAI Agents SDK

Create your Vinkius account to connect MediaWiki to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated page management with OpenAI Agents SDK

Your agent handles content updates by fetching the necessary credentials via `get_tokens` before executing changes. This ensures every `edit_page` call passes the required security checks without manual intervention. Production systems rely on these validated actions. By using `create_account` and other write tools, your agent maintains the wiki state while keeping your logs clean in the OpenAI dashboard.

Real-time data retrieval for your agent

Query your knowledge base using `search_pages` to pull relevant context into your agent's memory. You get exact matches back immediately, allowing the agent to synthesize information from multiple sources. Dig deeper into the structure by calling `get_page_links` or `get_page_categories`. These tools map out how your wiki is organized, giving the agent a clear view of the information hierarchy.

Tracking site activity via MCP Server tools

Monitor ongoing work by invoking `list_recent_changes` within your agent pipeline. This MCP Server provides a direct feed of activity, letting your agent respond to new edits as they occur. Verify site settings using `get_site_info` to ensure your agent operates under the correct wiki configuration. It's a straightforward way to keep your automation synchronized with the source.

Setup guide

Set up MediaWiki MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all MediaWiki tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives MediaWiki tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate MediaWiki tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="MediaWiki Agent",
            instructions="You have access to MediaWiki tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Use the `search_pages` tool directly within your agent loop. It performs a full-text search against the instance and returns the results for your agent to process.

Yes, but you must fetch a CSRF token first using `get_tokens`. Once you have the token, pass it to `edit_page` to commit your changes securely.

The server acts as a conduit between your client and the wiki. Your data remains on your infrastructure, and we don't store your credentials.

It targets standard API endpoints found in most modern wiki installations. As long as your site supports the core action API, the tools will work as expected.

Errors are returned as standard exceptions. You can catch these in your agent logic to retry calls or log failures for debugging.

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