mcpcost

io.github.dstrupl/vardoger

vardoger

Personalize AI coding assistants by analyzing local conversation history. Runs on your machine.

alive probed 2026-10-14

9tools
4.1ktokens in Claude Opus 5.5
4.2ktokens in Claude Code
2.1 %of a 200k context window
2.4ko200k_base estimate
2.0 sto initialize
5 msto list tools
Run it
uvx vardoger==0.4.0 (stdio, probed in a container with the network off)
Host
pypi.org
Reports itself as
vardoger 0.4.0
Capabilities
experimental, prompts, resources, tools
Instructions
none
Claude count
Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
Repository
https://github.com/dstrupl/vardoger
Registry
active, updated 2026-09-27 · registry entry
Reachable
1 of the last 1 probe

Most expensive tools

ToolTokens (o200k)Share of this server
vardoger_write54722 %
vardoger_import40016 %
vardoger_feedback27211 %
vardoger_preview25210 %
vardoger_compare2219 %

Badge and feed

mcpcost: alive

[![mcpcost](https://mcpcost.ulehla.dev/badge/io.github.dstrupl/vardoger.svg)](https://mcpcost.ulehla.dev/s/io.github.dstrupl/vardoger)

An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.