mcpcost

io.ausdata/aihw-mcp

aihw-mcp

Is the io.ausdata/aihw-mcp MCP server down? No. It answered initialize and tools/list in the probe of 2026-10-30.

Query the AIHW in plain English — mortality, cancer, health spend, hospital wait times.

alive probed 2026-11-15 · unchanged since 2026-10-30

6tools
4.6ktokens in Claude Opus 5.5
2.3 %of Claude's 200k window
1.8×the median server
9.8 sto initialize
25 msto list tools
Run it
uvx aihw-mcp@0.4.24 (stdio, probed in a container with the network off)
Host
pypi.org
Reports itself as
aihw-mcp 3.4.11
Capabilities
experimental, extensions, logging, prompts, resources, tools
Instructions
none
Of a 1M window
0.5 % of a 1M context window
Count
4.6k tokens in Claude Opus 5.5, exact, measured 2026-10-16. With the Claude Code prefix mcp__…__ on each tool name: 4.7k. The o200k_base estimate is 2.6k. Counted again when the tool definitions change. Method.
Repository
https://github.com/Bigred97/aihw-mcp
Website
https://ausdata.io
Registry
active, updated 2026-08-15 · registry entry

Most expensive tools

The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.77×.

Tool≈ Claude tokenso200k estimateShare of this server
get_data1 29973528 %
latest1 11763224 %
top_n1 11062824 %
search_datasets51629211 %
describe_dataset44425110 %

Compare this server with others.

More servers

Other registry entries on pypi.org, the ones next to this name; all of them.

Servers that mention mortality or hospital.

Badge for the README

mcpcost: alive

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Atom feed

A mail when this server changes

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.

For the publisher