Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/bigred97/ausdata-mcp-client/claude-mdgit clone --depth 1 https://github.com/Bigred97/ausdata-mcp-clientWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/bigred97/ausdata-mcp-client/claude-md)<a href="https://agentmods.dev/instructions/bigred97/ausdata-mcp-client/claude-md"><img src="https://agentmods.dev/badge/instructions/bigred97/ausdata-mcp-client/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01756 | $0.01756 |
| Opus 5 | $0.00878 | $0.00878 |
| Sonnet 5 | $0.00351 | $0.00351 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
ausdata-mcp-client CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ausdata-mcp — TypeScript MCP client
One-line value prop: public MCP server that routes AI-agent tool calls to the hosted ausdata.io REST API.
License: MIT. Distribution: public npm (when published).
CRITICAL — distinction from ausdata-mcp (Python)
This repo is NOT the private bundle. There are two related packages and they must never be conflated:
| Package | Language | Distribution | Purpose |
|---|---|---|---|
ausdata-mcp (Python, private) |
Python / FastMCP | Internal only — DO NOT PUBLISH | Direct sister-MCP imports, commercial moat, sold as enterprise self-host |
ausdata-mcp (TypeScript, THIS REPO) |
TypeScript / MCP SDK | Public npm under @ausdata org |
Routes to hosted API; free entry-point for AI agent devs |
If you find yourself reading from /Users/harry/Desktop/MCP Endpoint Creation/ausdata-mcp/, you are in the WRONG repo for this work. The private bundle lives there. This repo (ausdata-mcp-client/) is the public TypeScript client.
TypeScript + MCP SDK rationale
- TypeScript matches the audience: Claude Code / Cursor / Windsurf devs already have node + npm.
npx ausdata-mcpis friction-free. - The
@modelcontextprotocol/sdkTS implementation is the reference client; stays compatible with all transports. - HTTP routing only — zero parsing — keeps this client trivial to maintain. New endpoints in the REST API need a new tool file, that's it.
Architecture
src/
├── index.ts main() entry point
├── server.ts MCP Server bootstrap (stdio transport)
├── client.ts HTTP client → api.ausdata.io (override via AUSDATA_BASE_URL)
├── config.ts env var loading
├── tools/ one file per MCP tool
│ ├── index.ts registry (source of truth; 21 tools)
│ └── <one .ts file per tool> (search-datasets, list-datasets, describe,
│ get-data, health, real-wages, economic-dashboard, and 14 more)
└── lib/
├── errors.ts ApiError + mcpError + toMcpError
└── format.ts mcpJson — wrap any JSON in MCP content
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 116 lines · 1,756 tokens per session scan A a56396dd53ad
ausdata-mcp-client CLAUDE.md is an instructions file published in the GitHub repository Bigred97/ausdata-mcp-client (1 stars, last pushed 21d ago), licensed MIT. It adds 1,756 tokens to every session, about $0.0088 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
luxembourg-mcp CLAUDE.md
Instructions for amirdaraee/luxembourg-mcp, covering claude.md, commands, hard constraint: zero dependencies, architecture and adding or changing a tool touches five places.
sbb-opendata-mcp CLAUDE.md
Claude Code instructions for malkreide/sbb-opendata-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.
swiss-procurement-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-procurement-mcp, covering claude.md, teil 1 — portfolio-konventionen, vor der arbeit, tests and wenn etwas rot ist.
apra-mcp CLAUDE.md
Claude Code instructions for Bigred97/apra-mcp, covering apra-mcp, source, curated datasets (13), repo-specific module set and repo-specific gotchas.
abs-mcp CLAUDE.md
Claude Code instructions for Bigred97/abs-mcp, covering abs-mcp, source, curated datasets, repo-specific module set and repo-specific gotchas.
aihw-mcp CLAUDE.md
Claude Code instructions for Bigred97/aihw-mcp, covering aihw-mcp, source, curated datasets (8), repo-specific module set and repo-specific gotchas.