frootai-mcp 3.4.0

FrootAI MCP Server — AI architecture knowledge + compute tools. Python implementation of the FAI Engine.

FrootAI

_{MCP Server (Python)}

From the Roots to the Fruits. It's simply Frootful.

An open ecosystem where Infra, Platform, and App teams build AI — Frootfully.

An open glue for the GenAI ecosystem, enabling deterministic and reliable AI solutions.

---

The Philosophy Behind FrootAI — The Essence of the FAI Engine

FrootAI is an intelligent way of packaging skills, knowledge, and the essential components of the GenAI ecosystem — all synced, not standalone. Infrastructure, platform, and application layers are woven together so that every piece understands and builds on the others. That's what "from the roots to the fruits" means: a fully connected ecosystem where Infra, Platform, and App teams build AI — Frootfully.

The FROOT Framework

FROOT = Foundations · Reasoning · Orchestration · Operations · Transformation

Layer	What You Learn
F	Tokens, models, glossary, Agentic OS
R	Prompts, RAG, grounding, deterministic AI
O	Semantic Kernel, agents, MCP, tools
O	Azure AI Foundry, GPU infra, Copilot ecosystem
T	Fine-tuning, responsible AI, production patterns

The FAI Ecosystem

---

Quick Start

Requirements: Python >= 3.10

pip install frootai-mcp

Run as MCP Server

frootai-mcp-py

Use in Python

from frootai_mcp import FrootAIMCP

server = FrootAIMCP()
result = server._search_knowledge({"query": "RAG architecture"})
print(result)

---

Connect to Your Agent

VS Code / GitHub Copilot .vscode/mcp.json:

{
  "servers": {
    "frootai": {
      "type": "stdio",
      "command": "frootai-mcp-py"
    }
  }
}

Claude Desktop / Cursor

{
  "mcpServers": {
    "frootai": {
      "command": "frootai-mcp-py"
    }
  }
}

---

MCP Tools

Static — bundled knowledge, works offline

• list_modules — browse FROOT knowledge modules by layer
• get_module — read any module in full
• lookup_term — AI/ML glossary lookup
• search_knowledge — full-text search across all modules
• get_architecture_pattern — architecture decision guides
• get_froot_overview — complete framework summary

Live — network-enabled, graceful offline fallback

• fetch_azure_docs — search Microsoft Learn for Azure docs
• fetch_external_mcp — discover MCP servers from public registries
• list_community_plays — browse solution plays from GitHub
• get_github_agentic_os — .github Agentic OS implementation guide

Agent Chain — build → review → tune

• agent_build — architecture guidance + code patterns
• agent_review — security, quality, compliance audit
• agent_tune — production readiness validation

Ecosystem — Azure AI intelligence

• get_model_catalog — Azure AI model catalog with pricing
• get_azure_pricing — monthly cost estimates for Azure services
• compare_models — side-by-side model comparison
• compare_plays — compare solution plays

Compute — real calculations, not just lookups

• estimate_cost — itemized Azure cost estimate per play + scale
• validate_config — validate configs against best practices
• generate_architecture_diagram — Mermaid architecture diagrams
• embedding_playground — cosine similarity between texts
• semantic_search_plays — semantic search across solution plays
• run_evaluation — quality scoring with configurable thresholds

---

What Ships Inside

• FROOT Knowledge Modules — Foundations, Reasoning, Orchestration, Operations, Transformation
• AI Glossary — comprehensive AI/ML term definitions
• Solution Plays — pre-tuned deployable AI solutions
• Architecture Decision Guides — RAG, agents, hosting, cost optimization

Same tools as the Node.js MCP server. The FrootAI ecosystem grows with every release.

---

Links

Resource	Link
Website	frootai.dev
Setup Guide	FAI Packages Setup
Python SDK	PyPI — frootai
Node MCP Server	npm — frootai-mcp
VS Code Extension	Marketplace
Docker Image	GitHub Container Registry
GitHub	frootai/frootai
Contact	[e-mail]

---

© 2026 FrootAI — MIT License

_{AI architecture · MCP · model-context-protocol · Python · Azure · RAG · agents · copilot · semantic-kernel · open-source · frootai}