How to Use the MediaWiki MCP in AutoGen

Q: How do AutoGen agents negotiate a MediaWiki page edit using the MCP Server?

The drafting agent proposes a change based on getpagerevisions. The reviewer agent checks the proposal, and once they agree, the execution agent calls gettokens and editpage to apply the update.

Q: Can AutoGen agents create new MediaWiki user accounts?

Yes, an agent can use createaccount if it has the required token from gettokens. This is typically handled by an administrator agent in your setup.

Q: How do I register the MediaWiki MCP Server tools in AutoGen?

You register the tools using the mcpservertools adapter. This automatically maps the 13 tools to your AutoGen assistant agent's capabilities.

Q: How do agents handle rate limits on large wikis?

Your agents can use getsiteinfo to check API limits. You can instruct your coordinator agent to throttle requests if the wiki returns warnings.

Deploy teams of AutoGen agents that debate wiki changes and collaborate to edit pages securely.

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 AutoGen

Create your Vinkius account to connect MediaWiki to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate MediaWiki edits with AutoGen agents

This MediaWiki MCP Server allows a group of AutoGen agents to collaborate on wiki maintenance using `edit_page` and `get_tokens`. One agent drafts the update, a second agent reviews it against style guidelines, and a third agent executes the write. Before writing, the reviewing agent checks page history using `get_page_revisions` to avoid overwriting recent changes. This multi-agent consensus prevents formatting errors and keeps your wiki clean.

Multi-agent wiki auditing

This MediaWiki toolset provides AutoGen agents with the ability to audit your wiki for broken links and empty categories using `get_page_links` and `list_category_members`. The auditing agent flags issues and passes them to a writer agent. The writer agent uses `search_pages` to find the correct destination for broken links. They discuss the best fix in their chat thread before modifying the page.

Monitor recent changes collaboratively

This MediaWiki MCP Server integration feeds recent edits into an AutoGen conversation using `list_recent_changes`. A moderator agent screens these edits for vandalism or policy violations. If a suspicious edit is flagged, the agent retrieves user info via `get_user_info` and page metadata via `get_page_info`. The agents then debate whether to revert the edit or flag the user account.

Setup guide

Set up MediaWiki MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes MediaWiki tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="MediaWiki_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent MediaWiki data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="MediaWiki_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent MediaWiki data")
    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 AutoGen

The drafting agent proposes a change based on `get_page_revisions`. The reviewer agent checks the proposal, and once they agree, the execution agent calls `get_tokens` and `edit_page` to apply the update.

Yes, an agent can use `create_account` if it has the required token from `get_tokens`. This is typically handled by an administrator agent in your setup.

You register the tools using the `mcp_server_tools` adapter. This automatically maps the 13 tools to your AutoGen assistant agent's capabilities.

Your agents can use `get_site_info` to check API limits. You can instruct your coordinator agent to throttle requests if the wiki returns warnings.

The server handles CSRF tokens and user credentials within the secure V8 sandbox on Vinkius. Your edit logs and page history are only shared with the specific agents you configure.

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