mcpcost

io.github.nkalis/noodlelab

noodlelab

Is the noodlelab MCP server down? No. It answered initialize and tools/list in the probe of 2026-10-31.

Verifiable science: units, GUM uncertainty, requirements with margins and provenance on every run.

alive probed 2026-11-14 · unchanged since 2026-10-31

23tools
4.0ktokens in Claude Opus 5.5
2.0 %of Claude's 200k window
1.6×the median server
1.6 sto initialize
5 msto list tools
Run it
uvx noodlelab@0.8.1 (stdio, probed in a container with the network off)
Host
pypi.org
Reports itself as
noodlelab 0.8.1
Capabilities
tools
Instructions
303 characters
Of a 1M window
0.4 % of a 1M context window
Count
4.0k tokens in Claude Opus 5.5, exact, measured 2026-10-17. With the Claude Code prefix mcp__…__ on each tool name: 4.3k. The o200k_base estimate is 2.4k. Counted again when the tool definitions change. Method.
Website
https://nkalis.github.io/noodlelab/stable/agents/mcp.html
Registry
active, updated 2026-10-06 · registry entry

Most expensive tools

The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.67×.

Tool≈ Claude tokenso200k estimateShare of this server
edit_graph62337415 %
get_output3802289 %
reproduce2931767 %
save_graph2431466 %
install_plugin2281376 %

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 requirements or uncertainty.

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