Mcp Availability Server — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp Availability Server (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A small Model Context Protocol (MCP) server written in TypeScript. It exposes two tools that an MCP-capable client (such as Claude Desktop or Claude Code) can discover and call:
The server communicates over stdio, the transport MCP clients use to launch and talk to a local server process. The tool logic is self-contained so the server runs anywhere with no API keys or external services.
I build production AI systems that use tool-calling and orchestration (a conversational agent on the Anthropic API, and a phone voice agent on Telnyx). This repo is a clean, minimal example of authoring an MCP server: defining tools with typed input schemas, returning structured content, and serving them over the MCP stdio transport.
npm install
npm run buildnpm start
# or
node build/index.jsThe server runs on stdio and logs availability-server: MCP server running on stdio to stderr.
Add this to your Claude Desktop MCP config (claude_desktop_config.json):
{
"mcpServers": {
"availability": {
"command": "node",
"args": ["/absolute/path/to/mcp-availability-server/build/index.js"]
}
}
}Restart Claude Desktop, and the two tools will be available in conversation.
check_availability| Input | Type | Description |
|---|---|---|
date | string (YYYY-MM-DD) | The date to check. Weekends return no slots. |
format_call_summary| Input | Type | Description |
|---|---|---|
caller | string | Caller name or number |
intent | string | What the caller wanted |
next_action | string | The agreed next step |
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.