explanations
This commit is contained in:
@@ -8,6 +8,8 @@ icon: lucide/library
|
||||
|
||||
The platform is implemented as a resource-first MCP system with an integrated static documentation surface. The same methodology content powers both MCP resources and the published docs site.
|
||||
|
||||
An MCP server is a runtime that exposes machine-readable resources and tools through stable interfaces so AI clients can discover and consume context consistently. Here, the server's role is intentionally narrow: publish canonical methodology documents as resources, keep discovery predictable through a catalog layer, and serve the same source material as pre-built static documentation.
|
||||
|
||||
The system is complete in three layers:
|
||||
|
||||
1. Canonical methodology is maintained in Markdown skill documents.
|
||||
|
||||
@@ -4,6 +4,12 @@ icon: lucide/rocket
|
||||
|
||||
# Get started
|
||||
|
||||
## What this MCP server is
|
||||
|
||||
An MCP server is a service that gives AI clients a stable way to discover and read capabilities through defined contracts. In practice, it exposes named resources and optional tools so clients can request context reliably instead of depending on ad-hoc prompts.
|
||||
|
||||
This server is designed to publish software methodology as canonical Markdown resources, with a small catalog for discovery, and to serve the same content as a static docs site. The intent is one source of truth for both humans and agents.
|
||||
|
||||
## Quick start
|
||||
|
||||
Install dependencies first:
|
||||
|
||||
Reference in New Issue
Block a user