MCPgee
MCPgee
MCPgeeMCPgee

Adal CLI

v1.0.0•Coding Agents•stable

The self-evolving coding agent that learns from your entire team and codebase. Less syncing. Less waiting. Deliver at the speed of thought.

adalagentaiai-agentsclaude
Share:
74
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Adal CLI?

Adal CLI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to self-evolving coding agent that learns from your entire team and codebase. less syncing. less waiting. deliver at the speed of thought.

The self-evolving coding agent that learns from your entire team and codebase. Less syncing. Less waiting. Deliver at the speed of thought.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • The self-evolving coding agent that learns from your entire

Use Cases

Self-evolving AI agent that learns from your codebase and team
Fast code delivery with continuous learning
SylphAI-Inc

Maintainer

LicenseMIT
Languagecss
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx adal-cli

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Adal CLI

Adal CLI is a self-evolving AI coding agent built by SylphAI that learns from your codebase and team patterns to accelerate engineering and research tasks directly from the terminal. It integrates with Claude, Gemini, and other LLM backends to provide agentic code generation, refactoring, and multi-step task execution that improves over time as it ingests more context from your repository. Teams use it to reduce coordination overhead and deliver code faster by letting the agent accumulate shared knowledge from the entire engineering organization.

Prerequisites

  • Node.js 20 or higher installed
  • npm install -g @sylphai/adal-cli
  • An LLM API key (Anthropic, Google Gemini, or other supported provider) configured in the environment
  • An MCP-compatible client such as Claude Desktop or Claude Code if using the MCP integration
1

Install Adal CLI globally

Install the CLI tool via npm. Node.js 20 or higher is required.

npm install -g @sylphai/adal-cli
2

Verify the installation

Run the adal command to confirm the binary is available and check the version.

adal --version
adal
3

Configure your LLM API key

Set your preferred LLM provider's API key as an environment variable. Adal CLI supports Anthropic Claude, Google Gemini, and others.

# For Anthropic Claude:
export ANTHROPIC_API_KEY=your_anthropic_key

# For Google Gemini:
export GOOGLE_API_KEY=your_google_key
4

Initialize Adal in your project

Navigate to your project directory and run adal to start the agent. It will index your codebase and begin building its internal knowledge base.

cd /path/to/your/project
adal
5

Configure as an MCP server

To use Adal as an MCP tool server within Claude Desktop or another MCP client, add it to your configuration file.

{
  "mcpServers": {
    "adal": {
      "command": "npx",
      "args": ["adal-cli"],
      "env": {
        "ANTHROPIC_API_KEY": "your_anthropic_key"
      }
    }
  }
}

Adal CLI Examples

Client configuration

Add to claude_desktop_config.json to run Adal CLI as an MCP server subprocess.

{
  "mcpServers": {
    "adal": {
      "command": "npx",
      "args": ["adal-cli"],
      "env": {
        "ANTHROPIC_API_KEY": "your_anthropic_key"
      }
    }
  }
}

Prompts to try

Use these prompts in the terminal or through your MCP client to leverage Adal's codebase-aware coding agent.

- "Refactor the authentication module to use JWT tokens instead of session cookies, following the patterns already used in this codebase"
- "Find all places where we're using the deprecated fetchData function and replace them with the new API client"
- "Add unit tests for the UserService class using the same testing patterns as the existing test files"
- "Explain how data flows from the API endpoint to the database in the order processing feature"

Troubleshooting Adal CLI

adal command not found after npm install

Ensure npm's global bin directory is on your PATH. Run 'npm bin -g' to find it and add it to your shell profile (e.g., export PATH="$(npm bin -g):$PATH" in ~/.zshrc or ~/.bashrc).

The agent does not seem to remember patterns from previous sessions

Adal builds its knowledge base incrementally. Run it consistently within the same project directory. Check the docs at docs.sylph.ai for guidance on persisting the agent's memory store between sessions.

LLM API calls fail with authentication errors

Verify the relevant API key environment variable is exported in the same shell session where you run adal. For Claude Desktop integration, add the key explicitly in the env block of the MCP server config in claude_desktop_config.json.

Frequently Asked Questions about Adal CLI

What is Adal CLI?

Adal CLI is a Model Context Protocol (MCP) server that self-evolving coding agent that learns from your entire team and codebase. less syncing. less waiting. deliver at the speed of thought. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Adal CLI?

Follow the installation instructions on the Adal CLI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Adal CLI?

Adal CLI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Adal CLI free to use?

Yes, Adal CLI is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Adal CLI Alternatives — Similar Coding Agents Servers

Looking for alternatives to Adal CLI? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.

Dify

★ 142.2k

Production-ready platform for agentic workflow development.

Ruflo

★ 54.0k

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat

Goose

★ 45.7k

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Antigravity Awesome Skills

★ 38.3k

Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.

AgentScope

★ 25.5k

Build and run agents you can see, understand and trust.

Serena

★ 24.5k

A coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Coding AgentsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "adal-cli": { "command": "npx", "args": ["-y", "adal-cli"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Adal CLI?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides