
Stimulus Docs MCP Server
An MCP server that provides access to up-to-date Stimulus JS documentation directly within Claude conversations and VS Code.
README
Stimulus Docs MCP Server
An MCP server to access up to date documentation for Stimulus JS.
⚠️ This is Experimental Software
This MCP is in early development. It may contain bugs, have limited functionality, or undergo breaking changes without notice. Use at your own risk and expect potential instability.
Building the MCP Server
Prerequisites
- Node.js: Minimum version 18.0.0 or higher
- npm: Comes bundled with Node.js
Build Instructions
- Clone this repository and navigate to the project directory
- Install dependencies:
npm install
- Build the project using the provided script:
npm run build
This will compile the TypeScript source code and create the executable in the build/
directory.
Usage
With Claude Desktop
- First, build the MCP server following the instructions above
- Follow the instructions at https://modelcontextprotocol.io/quickstart/user to add a new MCP server.
- Add the following configuration:
{
"mcpServers": {
"stimulus-docs": {
"command": "node",
"args": ["/path/to/your/stimulus-docs-mcp-server/build/index.js"],
"env": {}
}
}
}
- Replace
/path/to/your/stimulus-docs-mcp-server
with the actual path to this project - Restart Claude Desktop
- The Stimulus documentation tools should now be available in your Claude conversations
With VS Code
- Build the MCP server following the instructions above
- Follow the instructions at https://code.visualstudio.com/docs/copilot/chat/mcp-servers
- Using your preferred method based on the instructions above, configure the MCP server by pointing it to the built executable:
{ "stimulus-docs": { "type": "stdio", "command": "node", "args": [ "path/to/your/stimulus-docs-mcp-server" ] } }
- Replace
path/to/your/stimulus-docs-mcp-server
with the path to theindex.js
file built in step 1. - The Stimulus documentation will be accessible through the MCP client interface
Troubleshooting
Claude
You may see the following errors when opening Claude after configuring the MCP:
MCP stimulus-docs: spawn node ENOENT (2)
Could not connect to MCP server stimulus-docs
MCP stimulus-docs: Server disconnected. For troubleshooting guidance [...]
This is because the path to the node
executable can not be found. If that's the case, instead of "command": "node"
use the complete path to the node. If you use mise
it may be something like:
"command": "/Users/<YOUR USER NAME/.local/share/mise/installs/node/20.18.3/bin/node
Documentation Source & Caching Strategy
This MCP server fetches the latest Stimulus documentation directly from the official stimulus-site repository on GitHub. To ensure optimal performance and reduce API calls, the server implements the following caching strategy:
How It Works
- Fresh Content Detection: The server checks the latest commit SHA and timestamp from the GitHub repository
- Cache Key Generation: A unique cache key is generated using the commit SHA (first 7 characters) and timestamp
- Caching: Documentation files are cached locally using the cache key as the folder structure
- Cache Validation: Before fetching from GitHub, the server checks if content is already cached for the current commit
- Fallback Strategy: If GitHub is unavailable, the server falls back to local documentation files
Cache Structure
cache/
{commit-sha}-{timestamp}/
handbook/
01_introduction.md
02_hello_stimulus.md
...
reference/
actions.md
targets.md
...
Benefits
- Always Up-to-Date: Content is automatically updated when the Stimulus repository changes
- Performance: Cached content loads instantly without network requests
- Reliability: Local fallback ensures the server works even when GitHub is unavailable
- Efficient: Only fetches new content when the repository has been updated
The local documentation files in src/docs/
serve as a backup and ensure the MCP server remains functional even without internet connectivity.
All credit for the documentation content goes to the Stimulus team and contributors.
Available Tools
This MCP server provides access to the complete Stimulus documentation, organized into:
Handbook:
- The Origin of Stimulus
- Introduction
- Hello Stimulus Tutorial
- Building Something Real
- Designing for Resilience
- Managing State
- Working with External Resources
- Installing Stimulus
Reference:
- Actions
- Controllers
- CSS Classes
- Lifecycle Callbacks
- Outlets
- Targets
- Using TypeScript
- Values
Each documentation section is available as a separate tool that can be called to retrieve the relevant content.
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。