FDEP MCP Server

A Static Code Analysis Model Context Protocol (MCP) server delivering 40+ comprehensive analysis tools for enterprise-scale Haskell codebases. Seamlessly integrates with MCP-compatible AI tools and clients to provide real-time code intelligence and architectural insights.

🔌 MCP Protocol Compliant | 🏗️ 40+ Analysis Tools | ⚡ Real-time Queries

✨ MCP Server Features

📊 40+ Comprehensive Analysis Tools

• Module Analysis: 7 tools for module structure and dependencies

• Function Analysis: 8 tools for call graphs and complexity metrics

• Type System: 6 tools for type relationships and usage patterns

• Class Analysis: 3 tools for typeclass and instance analysis

• Import Analysis: 4 tools for dependency visualization

• Advanced Queries: 4 tools for complex JSON-based code queries

• Pattern Analysis: 5 tools for code pattern detection

• Source Location: 3 tools for location-based analysis

• Enhanced Analysis: 3 tools for advanced structural analysis

Related MCP server: OrgBrain MCP Server

🚀 Quick Start

Prerequisites

• Python 3.13+

• UV package manager

• PostgreSQL database (must be running)

• FDEP output from Spider plugin (for comprehensive analysis)

Database Setup

Before installation, ensure PostgreSQL is running and create the required database:

# Start PostgreSQL (if not already running)
# On macOS with Homebrew:
brew services start postgresql

# On Ubuntu/Debian:
sudo systemctl start postgresql

# Create the database
createdb code_as_data # this should match with you $DB_NAME value in .env file (DEFAULT: code_as_data)

Installation

# Clone the repository
git clone https://github.com/juspay/fdep-mcp-server.git
cd fdep_mcp

# Install globally with UV (recommended)
uv tool install .

# OR install globally with pipx
# pipx install .

# OR system-wide installation
# pip install .vi 

Database Setup and Data Import

Important: Complete this step before using the MCP server with any client.

fdep-mcp-server --setup --verbose

This command will:

• Initialize the PostgreSQL database schema

• Import and process your FDEP data (if FDEP_PATH is configured)

• Set up all necessary indexes and relationships

Note: The first run takes time as it processes large FDEP datasets.

Configure Environment

cp .env.example .env
# Edit .env with your database settings and FDEP_PATH

🔌 MCP Client Configuration

After installation, configure your preferred MCP client to connect to the FDEP server:

Claude Code

Add to your ~/.claude/settings.json:

{
  "mcpServers": {
    "fdepAnalyzer": {
      "command": "fdep-mcp-server",
      "args": [],
      "env": {
        "FDEP_PATH": "/path/to/your/fdep/output"
      }
    }
  }
}

Note: The first time running the server takes time as it imports and processes the FDEP data.

Cursor

Add to your Cursor settings (Cmd/Ctrl + , → Extensions → MCP):

{
  "mcp.servers": {
    "fdepAnalyzer": {
      "command": "fdep-mcp-server",
      "args": [],
      "env": {
        "FDEP_PATH": "/path/to/your/fdep/output",
        "LOG_LEVEL": "INFO"
      }
    }
  }
}

Note: The first time running the server takes time as it imports and processes the FDEP data.

VS Code

Install the MCP extension and add to settings.json:

{
  "mcp.servers": [
    {
      "name": "fdepAnalyzer",
      "command": "fdep-mcp-server", 
      "args": [],
      "env": {
        "FDEP_PATH": "/path/to/your/fdep/output"
      }
    }
  ]
}

Note: The first time running the server takes time as it imports and processes the FDEP data.

Cline

Add to your Cline configuration:

{
  "mcpServers": {
    "fdepAnalyzer": {
      "command": "fdep-mcp-server",
      "args": [],
      "env": {
        "FDEP_PATH": "/path/to/your/fdep/output"
      }
    }
  }
}

Note: The first time running the server takes time as it imports and processes the FDEP data.

Continue.dev

Add to your .continue/config.json:

{
  "mcpServers": [
    {
      "name": "fdepAnalyzer",
      "command": "fdep-mcp-server",
      "args": [],
      "env": {
        "FDEP_PATH": "/path/to/your/fdep/output"
      }
    }
  ]
}

Note: The first time running the server takes time as it imports and processes the FDEP data.

Generic MCP Client

For any MCP-compatible client:

{
  "server_name": "fdepAnalyzer",
  "command": "fdep-mcp-server",
  "args": [],
  "environment": {
    "FDEP_PATH": "/path/to/your/fdep/output",
    "DB_HOST": "localhost",
    "DB_NAME": "code_as_data",
    "LOG_LEVEL": "INFO"
  }
}

Note: The first time running the server takes time as it imports and processes the FDEP data.

Environment Variables for All Clients

# Required
FDEP_PATH=/path/to/your/fdep/output

# Database (if different from defaults)
DB_HOST=localhost
DB_PORT=5432
DB_NAME=code_as_data
DB_USER=postgres
DB_PASSWORD=postgres

# Optional
LOG_LEVEL=INFO
DEV_MODE=false

Verify Connection

After configuring your client, verify the connection:

1. Start your MCP client

2. Look for "fdepAnalyzer" in available tools/servers

3. Test with a simple query: list_modules(limit=5)

4. You should see your Haskell modules listed

🛠️ MCP Tools Available (40+ Total)

📁 Module Analysis (7 tools)

⚡ Function Analysis (8 tools)

🏗️ Type System Analysis (6 tools)

📚 Class Analysis (3 tools)

📦 Import Analysis (4 tools)

🔍 Advanced Queries (4 tools)

🎯 Pattern Analysis (5 tools)

📍 Source Location (3 tools)

🔬 Enhanced Analysis (3 tools)

🔍 Example Queries

Basic Analysis

# Search for validation functions
search_functions(pattern="validation", limit=10)

# Get details about main functions  
get_function_details(function_name="main")

# Find most called functions
get_most_called_functions(limit=20)

# List modules in a specific area
list_modules(limit=50)

Advanced Analysis

# Get function call hierarchy
get_function_call_graph(function_name="processData", depth=3)

# Analyze type dependencies
get_type_dependencies(type_name="User", include_dependents=true)

# Find cross-module function calls
find_cross_module_calls(source_module="Services", target_module="Database")

# Complex JSON query
execute_advanced_query({
  "type": "function",
  "conditions": [
    {"field": "name", "operator": "like", "value": "%Handler%"}
  ],
  "limit": 50
})

Architectural Analysis

# Module dependency analysis
get_module_dependencies(module_name="Core.Services", include_dependents=true)

# Import relationship graph
get_import_graph(root_module="Main", depth=3)

# Complexity analysis
analyze_function_complexity(module_name="BusinessLogic", min_complexity=5)

# Comprehensive statistics
get_code_statistics(include_details=true)

⚙️ Configuration

Environment Variables (.env)

# Database
DB_USER=postgres
DB_PASSWORD=postgres  
DB_HOST=localhost
DB_PORT=5432
DB_NAME=code_as_data

# FDEP Data Source
FDEP_PATH=/path/to/your/fdep/output

# Logging
LOG_LEVEL=INFO

Spider Plugin Integration

For Haskell projects using GHC 9.2.8:

1. Add Spider flake input

2. Configure cabal with fdep and fieldInspector plugins

3. Run socket server during build

4. Generate FDEP output for analysis

Tool Distribution

• 📁 Module Analysis: 7 tools

• ⚡ Function Analysis: 8 tools

• 🏗️ Type System: 6 tools

• 📚 Class Analysis: 3 tools

• 📦 Import Analysis: 4 tools

• 🔍 Advanced Queries: 4 tools

• 🎯 Pattern Analysis: 5 tools

• 📍 Source Location: 3 tools

• 🔬 Enhanced Analysis: 3 tools