Database-driven FP enforcement and project management for AI-maintained codebases
Database-driven FP enforcement and project management for AI-maintained codebases. That is what the aifp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
Traditional programming paradigms were designed for humans. AIMFP is optimized for AI-human collaboration:
aimfp on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The server publishes 14 tools. What each one is for:
Database — driven project management** (persistent state, instant context retrieval)Directive — based AI guidance** (deterministic workflows, automated compliance)Example — Building a web server, calculator library, data processordirectives — All FP, project, and user preference directives (workflows, keywords, thresholds)helper_functions — Database, file, Git, and FP utilities organized across multiple registry filesdirective_helpers — Many-to-many junction table mapping directives to their helper functions with execution metadatacategories — Directive groupings (purity, immutability, task management, etc.)directive_flow — Status-driven directive navigation and routingTool — All helpers are exposed as MCP tools (AI calls directly via MCP)Sub — helper** (is_sub_helper = TRUE): Internal utility called by other helpers only (not exposed to AI)Production — Users query aimfp_core.db (pre-populated), NOT JSON filesproject — High-level metadata (name, purpose, goals, status, user_directives_status, last_known_git_hash)Configuration is passed through the environment: PYTHONPATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
This sits in the database access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Aifp's toolset — Database, Directive, Example and 11 more — is a fair guide to whether it matches your workflow. It is maintained by aryanduntley; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Database | driven project management** (persistent state, instant context retrieval) |
| Directive | based AI guidance** (deterministic workflows, automated compliance) |
| Example | Building a web server, calculator library, data processor |
| directives | All FP, project, and user preference directives (workflows, keywords, thresholds) |
| helper_functions | Database, file, Git, and FP utilities organized across multiple registry files |
| directive_helpers | **Many-to-many junction table** mapping directives to their helper functions with execution metadata |
| categories | Directive groupings (purity, immutability, task management, etc.) |
| directive_flow | Status-driven directive navigation and routing |
| Tool | All helpers are exposed as MCP tools (AI calls directly via MCP) |
| Sub | helper** (is_sub_helper = TRUE): Internal utility called by other helpers only (not exposed to AI) |
| Production | Users query aimfp_core.db (pre-populated), NOT JSON files |
| project | High-level metadata (name, purpose, goals, status, user_directives_status, last_known_git_hash) |
| notes | Runtime logging with optional directive context (source, severity, directive_name) |
| types | Algebraic data types (ADTs) |
{
"mcpServers": {
"aifp": {
"command": "uvx",
"args": ["aimfp"],
"env": {
"PYTHONPATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| PYTHONPATH | Filesystem location the server is allowed to use. | Optional |
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.