What are the requirements for ZMCPTools?

ZMCPTools requires a compatible MCP client such as Claude Desktop, Claude Code, or Cursor. No additional environment variables are needed for basic setup.

Is ZMCPTools free to use?

Yes, ZMCPTools is open source and free to use. You can find the source code on GitHub.

What MCP clients support ZMCPTools?

ZMCPTools works with any MCP-compatible client including Claude Desktop (Anthropic's official desktop app), Claude Code (CLI tool), Cursor, and other editors with MCP support.

How do I configure ZMCPTools?

Configure ZMCPTools by adding it to your MCP client's config file. For Claude Desktop, edit claude_desktop_config.json and add the server configuration. See the Configuration section above for a ready-to-use example.

ZMCPTools MCP Server

Q: What tools does ZMCPTools provide?

agent_orchestration: Coordinates specialized agent teams for complex development workflows.. browser_automation: Performs web automation and AI-powered DOM analysis using Playwright.. vector_search: Performs semantic search across documentation using LanceDB..

Q: How do I install ZMCPTools?

Install ZMCPTools by running: pnpm add -g zmcp-tools && zmcp-tools install

Add it to Claude Code

Run this in a terminal.

Run in terminal

claude mcp add zmcptools -- npx zmcp-tools@latest install

README.md

Professional multi-agent orchestration platform for Claude Code

ZMCPTools

🚀 TypeScript MCP Tools for Claude Code - Professional multi-agent orchestration platform with 61 enhanced tools, documentation intelligence, and advanced automation capabilities.

⚠️ Important Setup Note

Before spawning agents, run this command once to enable proper agent permissions:

claude --dangerously-skip-permissions

Agents run on daemon threads and need this permission to execute properly.

✨ Key Features

🎯 Multi-Agent Orchestration

Architect-Led Coordination: AI architect automatically spawns and coordinates specialized agent teams
Intelligent Dependencies: Agents work in proper order (Backend → Frontend → Testing → Documentation)
Real-Time Communication: Agents collaborate through dedicated chat rooms with message broadcasting
Foundation Session Caching: 85-90% cost reduction through automatic shared context management
Professional Task Management: Create, assign, track, and monitor complex development workflows

🎨 TypeScript-First Architecture

Type-Safe MCP Server: Built with Zod schemas and strict TypeScript for reliability
Modern CLI Interface: Commander.js-powered CLI with structured command hierarchy
Development Ready: One-command setup with hot-reload development via tsx
Binary Distribution: Global access via claude-mcp-tools and claude-mcp-server commands
Professional Build System: tsup-based compilation with dual CLI/server binaries

🌐 Advanced Browser Automation

Playwright Integration: Professional web automation with session management
AI-Powered DOM Analysis: Intelligent page structure analysis and navigation
Screenshot Analysis: AI-driven visual page analysis with region focusing
Smart Session Management: Auto-cleanup, session persistence, and connection pooling
Legacy Support: Comprehensive tool migration with backward compatibility

📚 Documentation Intelligence & Vector Search

LanceDB Vector Database: Local, high-performance semantic search with multiple embedding providers
Intelligent Web Scraping: Multi-page documentation collection with automatic vectorization
Advanced Content Processing: Smart URL filtering, pattern matching, and content extraction
Job Management: Background worker system with status monitoring and job control
Documentation Sources: Track and manage multiple documentation repositories

🧠 Knowledge Graph & Memory Systems

Graph-Based Knowledge Storage: Entity-relationship modeling for cross-agent learning
Semantic Search: Vector-powered knowledge discovery and relationship traversal
Shared Memory: Persistent agent collaboration and insight sharing
Project Analysis: Comprehensive code structure analysis with symbol extraction
Smart File Operations: Pattern-based file operations with fuzzy matching

🚀 Quick Installation

Prerequisites

Node.js 18+: Required for TypeScript runtime and LanceDB native bindings
Claude Code CLI: Anthropic's Claude Code CLI
Package Manager: npm (included), yarn, pnpm, or bun

Production Installation (Recommended)

# Install globally first (recommended for WSL/Linux compatibility)
pnpm add -g zmcp-tools
# If requested, approve build scripts for native dependencies
pnpm approve-builds -g

# Then install MCP integration
zmcp-tools install

# Alternative: Direct installation (may have issues with Sharp in WSL)
npx zmcp-tools@latest install     # npm
yarn dlx zmcp-tools@latest install  # yarn  
bunx zmcp-tools@latest install      # bun

This automatically:

✅ Installs MCP server to ~/.mcptools/server/
✅ Configures Claude Code with claude mcp add --scope local (current directory only)
✅ Sets up project permissions and CLAUDE.md integration
✅ Initializes SQLite database for agent coordination
✅ Initializes LanceDB vector database for semantic search
✅ Creates 61 professional MCP tools ready for use

Development Installation

# Clone and setup development environment
git clone https://github.com/zachhandley/ZMCPTools
cd ZMCPTools

# Quick automated setup
pnpm install && pnpm run install:global

# Or manual setup
pnpm install              # Install dependencies
pnpm build               # Compile TypeScript  
pnpm link --global       # Create global symlink
zmcp-t

Tools (3)

agent_orchestrationCoordinates specialized agent teams for complex development workflows.

browser_automationPerforms web automation and AI-powered DOM analysis using Playwright.

vector_searchPerforms semantic search across documentation using LanceDB.

Configuration

claude_desktop_config.json

{"mcpServers": {"zmcptools": {"command": "npx", "args": ["-y", "zmcp-tools", "server"]}}}

Try it

→Coordinate an agent team to refactor the backend API and update the corresponding frontend components.

→Use browser automation to navigate to the documentation site and scrape the latest API reference.

→Search the local vector database for information regarding our project's authentication implementation.

→Analyze the current project structure and suggest improvements based on the knowledge graph.

Frequently Asked Questions

What are the key features of ZMCPTools?

Multi-agent orchestration with architect-led coordination. Advanced browser automation via Playwright integration. LanceDB-powered semantic search and vector database. Knowledge graph memory system for cross-agent learning. Foundation session caching for cost reduction.

What can I use ZMCPTools for?

Automating complex multi-step development workflows across frontend and backend. Performing intelligent documentation retrieval and semantic search for large codebases. Executing autonomous web scraping and visual analysis tasks. Maintaining persistent project knowledge through graph-based memory.

How do I install ZMCPTools?

Install ZMCPTools by running: pnpm add -g zmcp-tools && zmcp-tools install

What MCP clients work with ZMCPTools?

ZMCPTools works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep ZMCPTools docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.

Open Conare

View all ai-tools servers →