
Aifp
This connects Claude to a SQLite-backed system that enforces functional programming standards and tracks project structure for AI-maintained codebases. You get tools to query functions, files, and dependencies from a pre-indexed database instead of reparsing source code every session. The server exposes operations across four databases: a read-only core with FP directives and helper definitions, a mutable project database for files and task hierarchy, user preferences for opt-in tracking, and optional custom directive automation. Reach for this when you want persistent context across AI sessions and database-driven enforcement of pure functions, immutability, and explicit data flow. It's language-agnostic and designed around the idea that AI forgets between conversations but databases don't.
- tools
- 8
- transport
- STDIO
- last updated
- Feb 12, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
aimfp_runServes as a gateway and reminder, not an executor, telling the AI that AIMFP directives should be applied.
Serves as a gateway and reminder, not an executor, telling the AI that AIMFP directives should be applied.
No parameter schema in public metadata yet.
aimfp_initCreates the .aimfp-project/ directory with databases and blueprint template, registering project metadata.
Creates the .aimfp-project/ directory with databases and blueprint template, registering project metadata.
No parameter schema in public metadata yet.
aimfp_statusReturns project metadata, active milestone, current task, recent notes, and warnings.
Returns project metadata, active milestone, current task, recent notes, and warnings.
No parameter schema in public metadata yet.
reserve_fileReserves a file in project.db before writing, returning an id.
Reserves a file in project.db before writing, returning an id.
No parameter schema in public metadata yet.
reserve_functionReserves a function in project.db before writing, returning an id.
Reserves a function in project.db before writing, returning an id.
No parameter schema in public metadata yet.
finalize_fileFinalizes a file with its path and metadata after writing.
Finalizes a file with its path and metadata after writing.
No parameter schema in public metadata yet.
finalize_functionFinalizes a function with its name, purpose, parameters, and return metadata after writing.
Finalizes a function with its name, purpose, parameters, and return metadata after writing.
No parameter schema in public metadata yet.
get_claude_permissionsReturns the complete, current Claude Code allowlist generated live from the tool registry.
Returns the complete, current Claude Code allowlist generated live from the tool registry.
No parameter schema in public metadata yet.
Sponsors
Readme
AIMFP: AI Modular Functional Procedural Programming
A language-agnostic programming paradigm designed for AI-generated and AI-maintained codebases
Table of Contents
- What is AIMFP?
- Core Principles
- Architecture Overview
- Database Architecture
- How It Works
- Getting Started
- Platform Support
- Directives System
- Project Lifecycle
- Example Workflow
- Documentation
- Development
- Design Philosophy
- Features
- Usage Examples
- Privacy Policy
- Support
- License
What is AIMFP?
AIMFP (AI Modular Functional Procedural) is a programming paradigm that combines:
Details
- Repository
- github.com/aryanduntley/aifp
- Category
- Databases
- Package
aifp- Transport
- STDIO
- Registry
- MCP registry, active