Skip to content
Agentmart
Submit a tool

Agentfit

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

Connector by MukundaKatta · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/mukundakatta-agentfit

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

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

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
2 read · 0 write · 1 delete
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Node.js package

Tools by what they do 3

Read from the source code; the running server may list different tools.

Read 2 · Look things up without changing anything.

  • count_tokens
  • list_estimators

Delete 1 · Delete, drop, revoke or wipe things.

  • fit_messages

Tools (3)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • count_tokens

    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 estimator (openai, anthropic, google, llama, default).

  • fit_messages

    Drop messages from the input array until the total is under maxTokens. Three strategies: drop-oldest (default), drop-middle, priority (uses each message's `priority` field). Always returns a structured result with token counts before and after; never throws across the wire.

  • list_estimators

    List the built-in estimator families this server knows about. Useful for picking a model alias when the exact model name isn't recognized.

Signals

Stars
1
Forks
0
Open issues
0
Weekly downloads
14
Last commit
Jun 13, 2026 (4 months ago)
Last release
Apr 27, 2026 (6 months ago)
Last package publish
Apr 27, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.MukundaKatta/agentfit
Version
0.1.0
Auth
No auth
Packages
npm @mukundakatta/agentfit-mcp
License
MIT
Repository
github.com/MukundaKatta/agentfit-mcp
Website
github.com/MukundaKatta/agentfit-mcp
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql

More from MukundaKatta

Cite this page

Agentfit MCP server. Agent Mart. https://agentmart.dev/connectors/mukundakatta-agentfit (last updated 2026-10-24)