About aipatterns-mcp-server
aipatterns-mcp-server makes Australian enterprise AI patterns, incidents, benchmarks, and regulatory changes available to AI assistants and developers. Its data comes from local pattern files and seed data, with no runtime database connection or network calls.
Key features
- 01Full-text pattern search
- 02Pattern details and implementation guidance
- 03Australian AI incident lookup
- 04Sector maturity benchmark lookup
- 05Regulatory change lookup
Use cases
- 01Research patterns for enterprise AI projects
- 02Review incidents and related regulatory outcomes
- 03Compare sector AI maturity scores
- 04Track Australian AI regulatory changes
MCP support
The MCP server exposes search and retrieval tools for patterns, Australian AI incidents, sector benchmarks, and regulatory changes.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
5Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| query | string | Yes | Search term to match against pattern title, description, or content |
| category | string | No | Optional category filter (e.g. agentic-ai, governance, security, rag, observability, compliance, human-in-the-loop) |
| maturity | string | No | Optional maturity filter (e.g. production, beta, experimental) |
Details
From the project READMEaipatterns.com.au MCP Server
A Model Context Protocol (MCP) server that exposes the aipatterns.com.au pattern library, AU AI incidents, sector benchmarks, and regulatory changes as tools callable by Claude, Cursor, GitHub Copilot, and other MCP-compatible AI assistants.
What it provides
| Tool | Description |
|---|---|
search_patterns | Full-text search across the pattern library (title, description, content) |
get_pattern | Retrieve full detail + implementation guidance for a specific pattern |
get_incidents | Notable Australian AI incidents with linked patterns and regulatory outcomes |
get_sector_benchmark | AU AI Maturity Index scores for banking, insurance, government, retail, healthcare, utilities |
get_regulatory_changes | APRA CPS 230, OAIC Privacy Act reform, ASIC INFO 183, TGA SaMD, and more |
No database connection or network calls are required at runtime — all data is served from the local pattern files and hardcoded seed data.
Published on npm as aipatterns-mcp-server — no clone or build step needed, npx fetches and runs it.
Add to Claude Desktop
Edit ~/.config/claude/claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"aipatterns": {
"command": "npx",
"args": ["-y", "aipatterns-mcp-server"]
}
}
}
Restart Claude Desktop.
Add to Cursor
Create or edit .cursor/mcp.json in your project root:
{
"mcpServers": {
"aipatterns": {
"command": "npx",
"args": ["-y", "aipatterns-mcp-server"]
}
}
}
Add to GitHub Copilot (VS Code MCP extension)
Add to your VS Code settings.json:
{
"mcp.servers": {
"aipatterns": {
"command": "npx",
"args": ["-y", "aipatterns-mcp-server"],
"transport": "stdio"
}
}
}
Running from source (development)
git clone https://github.com/uchit/aipatterns-mcp-server
cd aipatterns-mcp-server
npm install
npm run dev # runs via tsx (no build step needed)
npm run build # compile TS → JS for production use
Transport
stdio — the server reads JSON-RPC from stdin and writes responses to stdout. stderr is used for diagnostic messages only.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.