mcpserver.lol
registry/agentfit
Connection check local install

agentfit

Token-aware message truncation: fit a chat history into your model's context budget.

Tools 4
GitHub stars 1
Installs / wk
Licence MIT
Transport stdio
Last checked never

Tools & capabilities

4 tools

Read from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.

agentfit from source
count_tokens from source
Estimate tokens in a string or chat-message array. Fast, dependency-free, within ~10-20% of true tokenizer counts on English prose. Pass a model name to pick the right per-family e…
fit_messages from source
Drop messages from the input array until the total is under maxTokens. Three strategies: drop-oldest (default), drop-middle, priority (uses each message\
list_estimators from source
List the built-in estimator families this server knows about. Useful for picking a model alias when the exact model name isn\