io.github.nickjlamb/studydiff

studydiff

Is the io.github.nickjlamb/studydiff MCP server down? No. It answered initialize and tools/list in the probe of 2026-10-30.

Explain why two scientific papers disagree, every claim grounded in a verbatim source quote.

alive probed 2026-11-14 · unchanged since 2026-10-30

3tools

1.2ktokens in Claude Opus 5.5

0.6 %of Claude's 200k window

0.5×the median server

196 msto initialize

6 msto list tools

Run it: npx -y studydiff-mcp@0.2.0 (stdio, probed in a container with the network off)
Host: npmjs.com
Reports itself as: studydiff 0.1.0
Capabilities: tools
Instructions: none
Of a 1M window: 0.1 % of a 1M context window
Count: 1.2k tokens in Claude Opus 5.5, exact, measured 2026-10-16. With the Claude Code prefix mcp__…__ on each tool name: 1.2k. The o200k_base estimate is 730. Counted again when the tool definitions change. Method.
Repository: https://github.com/nickjlamb/studydiff
Registry: active, updated 2026-07-13 · registry entry

Most expensive tools

The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.66×.

Tool	≈ Claude tokens	o200k estimate	Share of this server
compare_studies	777	467	64 %
compare_example	341	205	28 %
list_examples	97	58	8 %

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

Servers that mention scientific or disagree.

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

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