WithSeismic MCP logo

WithSeismic MCP

by dougwithseismic

A production-ready MCP server template for hosting your own AI tools and prompts. It's built for developers who want to expose their tools to AI models without the infrastructure headaches.

View on GitHub

Last updated: N/A

What is WithSeismic MCP?

The MCP server provides two ways to expose your tools to AI models: Remote Server Mode (SSE) for production deployments and Local Mode (stdio) for development and testing. It allows developers to build and host their own tools that AI models can interact with, whether remotely or locally.

How to use WithSeismic MCP?

You can deploy the server remotely using the 'Deploy on Railway' button or set it up locally using pnpm install && pnpm dev. Two modes are available: Standard mode (stdio) for local development and SSE (Server-Sent Events) mode for remote connections.

Key features of WithSeismic MCP

  • Tools: Executable functions that models can call

  • Prompts: Template-based message generators

  • Auto-Discovery: Automatic registration of your components

  • Type Safety: Full TypeScript support throughout

Use cases of WithSeismic MCP

  • AI Tool Development

  • Teams & Organizations needing shared AI applications

  • Individual Developers seeking a quick-start MCP setup

  • API Providers exposing services to AI models

FAQ from WithSeismic MCP

What is an MCP server?

An MCP (Model Context Protocol) server facilitates communication between AI models and external tools, allowing models to invoke functions and access data.

What is Remote Server Mode (SSE)?

Remote Server Mode (SSE) is for production deployments, supporting multiple simultaneous connections and easy deployment to platforms like Railway.

What is Local Mode (stdio)?

Local Mode (stdio) is for local development and testing, enabling direct stdio communication for fast iteration and debugging.

How are tools and prompts registered?

Tools and prompts are automatically discovered and registered by the system upon import, simplifying the development process.

What kind of error handling is included?

The system includes robust error handling with type validation via Zod schemas, execution error wrapping, and detailed error messages for debugging.