trackmcp
Back to directory

Monorepo for Sylph Lab Model Context Protocol (MCP) tools and servers.

4 stars TypeScriptAI & Machine Learning Updated Aug 22, 2025
ailanguage-modelsmcpmodel-context-protocolmonorepotoolstypescript

Documentation


πŸš€ Overview

A comprehensive collection of modular tools designed for the Model Context Protocol (MCP), enabling AI agents to perform various operations efficiently.

The Problem:

code
Building MCP servers from scratch:
- Repetitive boilerplate code
- Inconsistent tool interfaces
- Scattered tool implementations
- No shared utilities or patterns

The Solution:

code
MCP Tools Monorepo:
- Modular tool architecture 🧩
- Consistent interfaces across tools 🎯
- Shared core utilities πŸ“¦
- MCP adaptors for easy integration ⚑

Result: Build MCP servers faster with reusable, well-tested tool components.


πŸ“¦ Packages

Core & Infrastructure

PackageDescriptionPurpose
tools-coreCore utilities and type definitionsBase framework for all tools
tools-adaptor-mcpMCP server integration adaptorConvert tools to MCP servers
tools-adaptor-vercelVercel platform adaptorDeploy tools on Vercel

Data Processing Tools

PackageDescriptionMCP Server
tools-jsonJSON parsing, validation, transformationβœ… tools-json-mcp
tools-xmlXML parsing and processingβœ… tools-xml-mcp
tools-base64Base64 encoding/decodingβœ… tools-base64-mcp
tools-pdfPDF text extractionβœ… tools-pdf-mcp

System & Network Tools

PackageDescriptionMCP Server
tools-filesystemFile operations (read, write, list, search)βœ… tools-filesystem-mcp
tools-netNetwork requests (fetch, IP info, DNS)βœ… tools-net-mcp
tools-fetch-mcpSpecialized fetch tool for MCPβœ… Standalone MCP
tools-hasherHashing utilities (MD5, SHA, etc.)βœ… tools-hasher-mcp

Specialized Tools

PackageDescriptionMCP Server
tools-ragRetrieval-Augmented Generation toolsβœ… tools-rag-mcp
tools-waitDelay and timing utilitiesβœ… tools-wait-mcp

Pattern: Most tools follow the `tools-{name}` + `tools-{name}-mcp` pattern, separating core logic from MCP server implementation.


🎯 Use Cases

AI Agent Development

Build powerful MCP servers for AI assistants:

  • File management - Read, write, search files
  • Web scraping - Fetch and process web content
  • Document processing - Extract text from PDFs
  • Data transformation - JSON/XML/Base64 operations

Rapid Prototyping

Quickly assemble MCP servers from pre-built tools:

  • Mix and match - Combine tools as needed
  • Consistent interfaces - Predictable tool behavior
  • Shared utilities - Less code duplication

Production Deployment

Deploy robust MCP servers:

  • Vercel adaptor - Serverless deployment
  • Turborepo - Optimized builds
  • Type-safe - Full TypeScript support

πŸš€ Quick Start

Prerequisites

  • Node.js - Latest LTS version (check `.nvmrc` if available)
  • pnpm - Version specified in `package.json` `packageManager` field

Installation

bash
# Clone the repository
git clone https://github.com/SylphxAI/tools.git
cd tools

# Install dependencies
pnpm install

Development Workflow

bash
# Build all packages
pnpm build

# Build continuously during development
pnpm build:watch

# Run linting
pnpm lint

# Run tests (build first)
pnpm test

πŸ› οΈ Tech Stack

ComponentTechnology
MonorepoTurborepo
Package Managerpnpm workspaces
LanguageTypeScript
Code QualityBiome (50x faster than ESLint)
TestingVitest
MCP ProtocolModel Context Protocol

πŸ’‘ Architecture

Tool Structure

Each tool follows a consistent pattern:

code
packages/
β”œβ”€β”€ tools-{name}/          # Core tool logic
β”‚   β”œβ”€β”€ src/
β”‚   β”‚   β”œβ”€β”€ index.ts       # Tool implementation
β”‚   β”‚   └── types.ts       # TypeScript types
β”‚   └── package.json
└── tools-{name}-mcp/      # MCP server wrapper
    β”œβ”€β”€ src/
    β”‚   └── index.ts       # MCP server entry
    └── package.json

Benefits

  • Separation of concerns - Core logic separate from MCP protocol
  • Reusability - Use tools outside of MCP context
  • Testability - Test core logic independently
  • Flexibility - Easy to create alternative adaptors

πŸ“– Package Details

Core Utilities

tools-core

typescript
import { defineTool } from '@sylphx/tools-core'

const myTool = defineTool({
  name: 'my-tool',
  description: 'Does something useful',
  schema: { /* Zod schema */ },
  execute: async (input) => { /* implementation */ }
})

MCP Adaptor

tools-adaptor-mcp

typescript
import { createMCPServer } from '@sylphx/tools-adaptor-mcp'
import { myTool } from '@sylphx/tools-mytool'

const server = createMCPServer({
  tools: [myTool],
  name: 'My MCP Server',
  version: '1.0.0'
})

πŸ”§ Development

Building Packages

bash
# Build all packages
pnpm build

# Build specific package
pnpm --filter @sylphx/tools-filesystem build

# Watch mode for development
pnpm build:watch

Code Quality

bash
# Lint all packages
pnpm lint

# Fix linting issues
pnpm lint:fix

# Format code
pnpm format

Testing

bash
# Run all tests
pnpm test

# Run tests for specific package
pnpm --filter @sylphx/tools-json test

# Watch mode
pnpm test:watch

πŸ“‹ Creating a New Tool

Step 1: Create Core Package

bash
# Create package directory
mkdir -p packages/tools-newtool/src

# Create package.json
cat > packages/tools-newtool/package.json  {
    // Implementation
    return { result: `Processed: ${input}` }
  }
})

Step 3: Create MCP Server

bash
# Create MCP package
mkdir -p packages/tools-newtool-mcp/src

# Create server
cat > packages/tools-newtool-mcp/src/index.ts 
  Modular. Reusable. Production-ready.
  
  The MCP toolkit that scales with your needs
  
   β€’
   β€’

Frequently asked questions

What is tools?

tools is Monorepo for Sylph Lab Model Context Protocol (MCP) tools and servers.

How do I install tools?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is tools open source?

Yes β€” it is hosted on GitHub at https://github.com/sylphlab/MCP and has 4 stars.

Related MCP tools

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP