AL MCP Server
Provides AI assistants with complete visibility into AL dependencies and symbols by exposing compiled .app files through the Model Context Protocol, enabling smart object discovery, deep code analysis, and reference tracking for Business Central development.
README
AL MCP Server
Give AI assistants complete visibility into your AL dependencies and symbols.
What This Solves
AI coding assistants can't see compiled AL packages or understand Business Central object relationships. This creates a blind spot when helping with AL development.
The AL MCP Server bridges this gap by exposing your AL workspace's compiled symbols (.app files) directly to AI assistants through the Model Context Protocol.
Quick Start
Prerequisites
- Node.js 18+ (download)
- .NET SDK 8.0+ (download)
- Compiled AL packages (.app files in .alpackages directory)
Verify your setup:
dotnet --version # Should show 8.0 or higher
The AL MCP Server installs automatically via npx - no manual installation needed.
Configure Your AI Assistant
Claude Code (Recommended)
claude mcp add al-mcp-server -- npx al-mcp-server
Or via VS Code settings:
{
"claude.mcpServers": {
"al-symbols-mcp": {
"command": "npx",
"args": ["al-mcp-server"]
}
}
}
GitHub Copilot
Create .vscode/mcp.json in your workspace:
{
"servers": {
"al-symbols-mcp": {
"type": "stdio",
"command": "npx",
"args": ["al-mcp-server"]
}
}
}
Cursor IDE
Add to Cursor settings (Settings → Features → Model Context Protocol):
{
"al-symbols-mcp": {
"command": "npx",
"args": ["al-mcp-server"]
}
}
Continue (VS Code Extension)
Add to ~/.continue/config.json:
{
"mcpServers": {
"al-symbols-mcp": {
"command": "npx",
"args": ["al-mcp-server"]
}
}
}
Cody (Sourcegraph)
Add to VS Code settings:
{
"cody.mcpServers": {
"al-symbols-mcp": {
"command": "npx",
"args": ["al-mcp-server"]
}
}
}
Other MCP-Compatible Tools
Use these connection details:
- Command:
npx - Args:
["al-mcp-server"] - Type:
stdio
Test It Works
Ask your AI assistant:
Search for Customer table in my AL project
The server will auto-start and provide intelligent AL assistance!
Available Tools
The AL MCP Server provides 6 token-optimized tools for AL code analysis:
Core Query Tools
al_search_objects
- Search for AL objects by name, type, or wildcard pattern
- Filter by business domain (Sales, Finance, Inventory, etc.)
- Support for all AL object types (Table, Page, Codeunit, Report, etc.)
- Token-efficient summary mode enabled by default
al_get_object_definition
- Get detailed object information by ID or name
- Includes fields, procedures, properties, and keys
- Configurable detail level with field/procedure limits
- Summary mode for token efficiency
al_find_references
- Find all references to an object or field
- Track extensions, variables, parameters, return types
- Field-level reference tracking across all object types
- Optional context for detailed reference information
al_search_object_members
- Unified search for object child elements
- Search procedures, fields, controls, or dataitems
- Wildcard pattern matching support
- Pagination and detail level control
al_get_object_summary
- Get intelligent categorized overview of objects
- Organizes procedures by purpose (validation, posting, utilities, etc.)
- Identifies key entry points automatically
- Highly token-efficient categorized output
Package Management
al_packages
- Unified package management with action parameter
- Load: Auto-discover and load packages from project root
- List: Show all currently loaded packages
- Stats: Database statistics and object counts
Capabilities
Smart Object Discovery
- Search across all loaded AL packages simultaneously
- Wildcard pattern matching for flexible queries
- Filter by object type, package, or business domain
- Auto-discovery of .alpackages directories
Deep Code Analysis
- Complete object definitions with all metadata
- Procedure and field information with properties
- Page control structure analysis
- Report/query dataitem traversal
Reference Tracking
- Find all object references and dependencies
- Track object extensions and customizations
- Field-level usage analysis across pages, tables, reports
- Variable and parameter tracking in codeunits
Business Domain Intelligence
- Search by business area (Sales, Purchasing, Finance, Inventory, Manufacturing, Service)
- Pattern-based domain detection
- Cross-package domain analysis
Architecture
AL MCP Server
├── Symbol Extraction Layer
│ └── AL CLI integration for .app file parsing
├── Streaming Parser
│ └── Efficient handling of large symbol files (50MB+)
├── In-Memory Database
│ └── Optimized indices for sub-100ms queries
├── MCP Protocol Handler
│ └── JSON-RPC communication with AI assistants
└── Auto-Discovery Engine
└── Smart .alpackages directory detection
Performance Features:
- Lazy initialization - packages load on first request
- Streaming JSON parsing prevents memory issues
- Multiple optimized indices for O(1) lookups
- Version filtering uses latest package only
- Token-optimized responses reduce AI context usage
Requirements
Runtime:
- Node.js 18 or higher
- .NET SDK 8.0 or higher
- NuGet package source (nuget.org)
Project Structure:
- AL workspace with app.json
- Compiled .app packages in .alpackages directory
Supported AL Packages:
- Modern namespace-based packages
- Legacy non-namespace packages (PTEs)
- Business Central base application
- AppSource extensions
The server analyzes compiled AL symbols, not raw .al source files.
Troubleshooting
AL CLI not found
- The server auto-installs AL tools
- Requires .NET SDK 8.0 or higher
- Verify:
dotnet --version
NU1100 error
- Update to .NET SDK 8.0+
- Configure NuGet:
dotnet nuget add source https://api.nuget.org/v3/index.json -n nuget.org
No sources found
- Check NuGet sources:
dotnet nuget list source - Should include nuget.org
No packages found
- Ensure .app files exist in .alpackages directory
- Use
al_auto_discovertool to search for packages - Check that packages were compiled successfully
Server not responding
- Verify Node.js 18+ is installed
- Check AI assistant MCP configuration
- Review server logs in AI assistant output
Need Help?
Example Usage
Once configured, ask your AI assistant:
"Show me all Sales-related codeunits"
"Find all references to the Customer table"
"What procedures are in the Sales-Post codeunit?"
"Search for all pages that use the Item table"
"Give me a summary of the Gen. Journal-Post Batch codeunit"
The AI assistant will use the MCP tools to provide accurate, context-aware responses based on your actual AL packages.
Contributing
- Fork the repository
- Create a feature branch
- Write tests for changes
- Ensure all tests pass
- Submit a pull request
License
MIT License - see LICENSE file for details.
Transform AL development with AI assistants that truly understand your codebase.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.