Waldzell MCP Servers

This is a Turborepo-powered monorepo containing MCP (Model Context Protocol) servers for various AI assistant integrations.

What's inside?

Packages

• server-yelp-fusionai - MCP server for Yelp Fusion API
• server-typestyle - Google TypeScript Style Guide MCP server
• server-stochasticthinking - Stochastic thinking MCP server
• server-clear-thought - Sequentialthinking fork inspired by James Clear
• common - Shared utilities and types

Utilities

This monorepo uses Turborepo with Yarn 4 Workspaces.

• Turborepo — High-performance build system for monorepos
• Yarn 4 — Modern package management with PnP support
• Changesets — Managing versioning and changelogs
• GitHub Actions — Automated workflows
• Smithery — Deployment platform for MCP servers

Getting Started

Prerequisites

• Node.js 18 or higher
• Corepack enabled (corepack enable)

Installation

Clone the repository and install dependencies:

git clone https://github.com/waldzellai/mcp-servers.git
cd mcp-servers
yarn install

Development

To develop all packages:

yarn dev

Building

To build all packages:

yarn build

The build output will be in each package's dist/ directory.

Testing

yarn test

Linting

yarn lint

Deploying to Smithery

This repo is set up to easily deploy packages to Smithery:

# Deploy all packages
yarn deploy

# Deploy specific packages
yarn smithery:yelp-fusion
yarn smithery:typestyle
yarn smithery:stochastic
yarn smithery:clear-thought

Workflow

Adding a new feature

1. Create a new branch
2. Make your changes
3. Add a changeset (documents what's changed for version bumping):

   yarn changeset
   

4. Push your changes

Releasing new versions

We use Changesets to manage versions. Create a PR with your changes and Changesets will create a release PR that you can merge to release new versions.

For manual releases:

yarn publish-packages

Adding a New Package

1. Create a new directory in the packages directory
2. Initialize the package with yarn init
3. Add your source code
4. Update turbo.json pipeline if needed
5. Add a smithery.yaml file if you want to deploy to Smithery
6. Run yarn install at the root to update workspaces

Turborepo

Remote Caching

Turborepo can use a remote cache to share build artifacts across machines. To enable Remote Caching:

yarn dlx turbo login
yarn dlx turbo link

MCP Server Documentation

Each MCP server package in this monorepo has its own README with detailed documentation:

• Yelp Fusion MCP Server
• TypeStyle MCP Server
• Stochastic Thinking MCP Server
• Clear Thought MCP Server

License

All packages in this monorepo are licensed under the MIT License - see each package's LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit a pull request.