Toolrush Mcp banner
dhava-gautama dhava-gautama

Toolrush Mcp

Development community

Description

Kill the tool-call tax in any MCP agent harness: fast read/search, warm persistent shell, batched calls. Go port of OnlyTerp/toolrush.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

ToolRush-MCP

[![ci](https://github.com/dhava-gautama/toolrush-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/dhava-gautama/toolrush-mcp/actions/workflows/ci.yml) [![Release](https://img.shields.io/github/v/release/dhava-gautama/toolrush-mcp)](https://github.com/dhava-gautama/toolrush-mcp/releases/latest) [![Go Report Card](https://goreportcard.com/badge/github.com/dhava-gautama/toolrush-mcp)](https://goreportcard.com/report/github.com/dhava-gautama/toolrush-mcp) [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)

**Kill the tool-call tax — in any agent harness.** A fast local tool server for [Kimi Code CLI](https://www.kimi.com/code), [Codex CLI](https://github.com/openai/codex), [Claude Code](https://docs.anthropic.com/en/docs/claude-code), and anything else that speaks the Model Context Protocol.

A universal port of [ToolRush](https://github.com/OnlyTerp/toolrush) (a Hermes Agent plugin, Windows/MSYS-only) — same lanes, same fail-closed philosophy, shipped as one static Go binary instead of harness-specific monkeypatching.

What you get

Tool What it does
fast_read In-process file read: line-number gutter, offset/limit paging, negative offset = tail, binary sniff, BOM strip, >64MB files stream the window. Line-level mtime cache — page turns are cache hits
batch_read 1–16 reads through one tool call, input order, whole-batch validated before anything runs (serial by design — measured faster than pooling on page-cache-fast storage)
fast_search Direct rg transport — real .gitignore, real regex grammar. Pure-Go walk fallback when rg is absent. context=N (0–5) adds N lines of gutter around each hit: L-line before, L+line after
batch_search 1–16 searches through one call, fanned out across goroutines — each op spawns its own rg process, so the batch wall time approaches the slowest op, not the sum. Input order, whole-batch validated, per-op failures isolated