
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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.