Last updated
March 16, 2026
MCP profile
Github Aryanduntley Aifp
Database-driven FP enforcement and project management for AI-maintained codebases
Developer ToolsPackagePythonOpen SourceExternal
Visibility
Public
ByRegistry
About This MCP Server
The server communicates over stdio using the Model Context Protocol. It resolves aifp_core.db (the directive database) relative to its own installation — no environment variables needed.
Once connected, the AI calls aifp_run() on every interaction (guided by the system prompt). Project state is stored in .aifp-project/ in your working directory, created automatically when you initialize a project.
Every AIFP project has a completion path:
Once project_completion_check passes, the project is done. No endless feature creep.
Capabilities
Comprehensive MCP tools — Full CRUD for 4 SQLite databases, covering project management, FP directives, user preferences, and custom automation directivesPure functional enforcement — AI writes FP-compliant code by default (pure functions, immutability, no OOP)Database-driven persistent memory — Project state survives across sessions; no context lossDirective-based workflows — Deterministic trunk → branches → fallback execution patternsFinite completion paths — Projects have defined stages, milestones, and tasks; work converges toward completionTwo use cases — Regular software development (Use Case 1) or custom directive automation (Use Case 2)User preference learning — AI adapts to coding style via per-directive key-value overridesGit integration — FP-powered branch management and conflict resolutionMinimal dependencies — One runtime package (watchdog), custom JSON-RPC server uses stdlib onlyCost-conscious design — All tracking/analytics features disabled by default
Tools & Endpoints
Example Workflow
• Programmatically creates .aifp-project/ directory, databases, blueprint template
Why Use Github Aryanduntley Aifp?
- Comprehensive MCP tools — Full CRUD for 4 SQLite databases, covering project management, FP directives, user preferences, and custom automation directives
- Pure functional enforcement — AI writes FP-compliant code by default (pure functions, immutability, no OOP)
- Database-driven persistent memory — Project state survives across sessions; no context loss
- Directive-based workflows — Deterministic trunk → branches → fallback execution patterns
- Finite completion paths — Projects have defined stages, milestones, and tasks; work converges toward completion
- Two use cases — Regular software development (Use Case 1) or custom directive automation (Use Case 2)
- User preference learning — AI adapts to coding style via per-directive key-value overrides
- Git integration — FP-powered branch management and conflict resolution
- Minimal dependencies — One runtime package (watchdog), custom JSON-RPC server uses stdlib only
- Cost-conscious design — All tracking/analytics features disabled by default
Specifications
Status
live
Industry
Developer Tools
Category
General
Server type
Package
Language
Python
License
Open Source
Verified
Yes
Requirements
- • Python 3.11+ (required for type hint syntax used throughout)
Hosting
Hosting Options
- Package
API
Integrate this server into your application. Choose a connection method below.
1
Install
Install command
Python
pip install aifp2
Configure
Configuration
json
{
"mcpServers": {
"aifp": {
"command": "python3",
"args": ["-m", "aifp"],
"env": {}
}
}
}Performance
Usage
Quick Reference
- Name
- Github Aryanduntley Aifp
- Function
- Database-driven FP enforcement and project management for AI-maintained codebases
- Transport
- Package
- Language
- Python
- Install
- pip install aifp
- Source
- External (Registry)
- License
- Open Source
Get started
Ready to integrate this MCP server?
Book a demo to see how this server fits your workflow, or explore the full catalog.