
mediawiki-mcp-server
Model Context Protocol (MCP) server for MediaWiki
README
MediaWiki MCP Server
An MCP (Model Context Protocol) server that enables Large Language Model (LLM) clients to interact with any MediaWiki wiki.
Feature
Tools
🔐 Requires OAuth 2.0 token: Request from the
Special:OAuthConsumerRegistration/propose/oauth2
page on the wiki.
Name | Description |
---|---|
create-page 🔐 |
Create a new wiki page. |
get-file |
Returns the standard file object for a file page. |
get-page |
Returns the standard page object for a wiki page. |
get-page-history |
Returns information about the latest revisions to a wiki page. |
search-page |
Search wiki page titles and contents for the provided search terms. |
set-wiki |
Set the wiki to use for the current session. |
update-page 🔐 |
Update an existing wiki page. |
Environment variables
Name | Description |
---|---|
WIKI_SERVER |
Domain of the wiki (e.g. https://en.wikipedia.org ) |
ARTICLE_PATH |
Article path of the wiki (e.g. /wiki ) |
SCRIPT_PATH |
Script path of the wiki (e.g. /w ) |
OAUTH_TOKEN |
OAuth token from the OAuth extension |
Installation
<details><summary><b>Install via Smithery</b></summary>
To install MediaWiki MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @ProfessionalWiki/mediawiki-mcp-server --client claude
</details>
<details> <summary><b>Install in Claude Desktop</b></summary>
Follow the guide, use following configuration:
{
"mcpServers": {
"mediawiki-mcp-server": {
"command": "npx",
"args": [
"@professional-wiki/mediawiki-mcp-server@latest"
]
}
}
}
</details>
<details><summary><b>Install in VS Code</b></summary>
code --add-mcp '{"name":"mediawiki-mcp-server","command":"npx","args":["@professional-wiki/mediawiki-mcp-server@latest"]}'
</details>
<details> <summary><b>Install in Cursor</b></summary>
Go to Cursor Settings
-> MCP
-> Add new MCP Server
. Name to your liking, use command
type with the command npx @professional-wiki/mediawiki-mcp-server
. You can also verify config or add command like arguments via clicking Edit
.
{
"mcpServers": {
"mediawiki-mcp-server": {
"command": "npx",
"args": [
"@professional-wiki/mediawiki-mcp-server@latest"
]
}
}
}
</details>
<details> <summary><b>Install in Windsurf</b></summary>
Follow the guide, use following configuration:
{
"mcpServers": {
"mediawiki-mcp-server": {
"command": "npx",
"args": [
"@professional-wiki/mediawiki-mcp-server@latest"
]
}
}
}
</details>
Development
🐋 Develop with Docker: Replace the
npm run
part of the command withmake
(e.g.make dev
).
MCP Inspector
To start the development server and the MCP Inspector:
npm run dev
The command will build and start the MCP Proxy server locally at 6277
and the MCP Inspector client UI at http://localhost:6274
.
Test with MCP clients
To enable your MCP client to use this MediaWiki MCP Server for local development:
-
Register the MCP server in your client config (e.g.
claude_desktop_config.json
for Claude Desktop). An example config is provided atmcp.json
. -
Run the watch command so that the source will be compiled whenever there is a change:
npm run watch
Contributing
Contributions are welcome! Please feel free to submit a pull request or open an issue for bugs, feature requests, or suggestions.
License
This project is licensed under the GPL 2.0 License. See the LICENSE file for details.
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。