MCP Booster

Provides an integrated MCP server for intelligent planning, execution, validation, and persistent memory of development tasks.
  • javascript

2

GitHub Stars

javascript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "llm-booster-mcp-booster": {
      "command": "mcp-booster",
      "args": [
        "--api-key",
        "YOUR_API_KEY"
      ],
      "env": {
        "MCP_BOOSTER_API_KEY": "YOUR_API_KEY",
        "MCP_BOOSTER_LOG_LEVEL": "info"
      }
    }
  }
}

MCP-Booster brings truly intelligent, automated development assistance to your machine. It maintains full project context, plans and executes complex tasks, and continuously validates its own work so you can ship with confidence and speed.

How to use

You run MCP-Booster locally and connect your development workflow to a local MCP client. Start it to begin processing tasks, and use the Booster_Steps planning to decompose work into executable cards that run and validate themselves. The Booster_Analyser provides automatic quality checks of thought chains, and Booster_Storage keeps a structured history of decisions and changes so you can search and audit later. Use the Booster System to perform continuous reasoning with real-time confidence scoring to guide your next actions.

How to install

Prerequisites: you need Node.js version 18.0.0 or newer and npm version 8.0.0 or newer. MCP-Booster runs on Windows, macOS, and Linux.

  1. Install MCP-Booster globally.
npm install -g mcp-booster

Usage after installation

Start the local MCP-Booster service to connect your IDE or client. The power begins when you run the booster command, then you can observe results in your Cursor IDE or compatible environment.

  1. Start MCP-Booster.
mcp-booster

Available tools

Booster System

Core reasoning engine that performs continuous chain reasoning, evaluates multiple approaches, maintains real-time confidence scores, and guides execution with structured plans.

Booster_Analyser

Quality assurance component that automatically validates thought chains, detects gaps where more information is needed, and suggests improvements.

Booster_Storage

Corporate memory that stores all decisions with rich metadata and full history to enable instant search and auditability.

Booster_Steps

Elite planning module that decomposes complex tasks into executable, verifiable steps with automatic checks and sequential execution.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational