Msty Admin Mcp

Msty Admin MCP

AI-Powered Administration for Msty Studio Desktop 2.4.0+

An MCP (Model Context Protocol) server that transforms Claude into an intelligent system administrator for Msty Studio Desktop. Query databases, manage configurations, orchestrate local AI models, and build tiered AI workflows—all through natural conversation.

[](https://github.com/DBSS/msty-admin-mcp/releases) [](LICENSE) [](https://python.org) [](https://apple.com) [](https://msty.ai) [](tests/) [](src/)

> v10.0.0 - Ultimate AI Orchestration release with 224 tools! New features include Intelligent Context Management, Model Ensembles with Voting, Prompt Engineering Lab, Knowledge Graph Builder, Response Quality Analytics, Conversation Branching, Model Capability Profiler, Smart Retry with Circuit Breakers, Export & Publishing Suite, and Sentiment Analytics.

---

About This Fork

👋 Hey! I'm Dmitri K from DigitalKredit.

I picked up this project when it had 24 tools designed for an older Msty Studio architecture with a separate "Sidecar" service that no longer exists in Msty 2.4.0+.

What I did:

• 🔧 Rewrote the codebase for Msty 2.4.0+ (services now built into main app)
• 🏗️ Refactored into a clean modular architecture (40+ modules)
• 📈 Expanded from 24 tools to 224 fully functional tools
• ✅ Added comprehensive testing (262 passing tests)
• 🚀 Built major new features: AI agent swarms, intelligent routing, cascade execution, semantic caching, cost intelligence, context management, model ensembles, knowledge graphs, sentiment analytics, and more

This fork is actively maintained and tested against Msty Studio 2.4.0+.

---

What's New in v10.0.0

Intelligence & Quality Tools - 60 New Tools Across 10 New Phases

| Phase | Tools | Description | |-------|-------|-------------| | Phase 36: Context Management | 6 | Token budget management, smart summarization, context optimization | | Phase 37: Model Ensembles | 7 | Multi-model queries, voting, response blending, disagreement detection | | Phase 38: Prompt Engineering Lab | 8 | Prompt scoring, optimization, A/B variations, technique library | | Phase 39: Knowledge Graphs | 6 | Entity extraction, relationship mapping, graph visualization | | Phase 40: Quality Analytics | 5 | Response scoring, hallucination detection, fact checking | | Phase 41: Conversation Branching | 6 | Branch creation, comparison, merging, replay with modifications | | Phase 42: Capability Profiler | 6 | Model benchmarking, capability matrix, gap analysis | | Phase 43: Smart Retry | 5 | Circuit breakers, exponential backoff, failure analysis | | Phase 44: Export Suite | 6 | Multi-format export, templates, scheduled publishing | | Phase 45: Sentiment Analytics | 5 | Sentiment tracking, frustration detection, satisfaction reports |

New Modules (v10.0.0)

| Module | Purpose | |--------|---------| | context_management.py | Intelligent context window optimization | | model_ensemble.py | Multi-model query coordination | | prompt_lab.py | Prompt engineering experimentation | | knowledge_graph.py | Entity and relationship extraction | | quality_analytics.py | Response quality assessment | | conversation_branching.py | Alternative conversation paths | | capability_profiler.py | Model capability testing | | smart_retry.py | Resilient retry with fallbacks | | export_suite.py | Multi-format export system | | sentiment_analytics.py | Conversation sentiment analysis | | server_extensions_v4.py | Extension registration v4 |

Key Features (v10.0.0)

🧠 Model Ensembles - Query multiple models and combine their responses:

ensemble_create "My Ensemble" "qwen3-30b,llama3.1-70b,mistral-large"
ensemble_query my_ensemble "Complex analysis question"

📊 Knowledge Graphs - Extract entities and relationships from conversations:

kg_build "Project Knowledge" "conversation text here..."
kg_visualize my_graph_id "mermaid"  # Get visualization data

🎯 Smart Retry - Automatic fallback with circuit breakers:

retry_policy_configure "production" max_retries=3 strategy="exponential_backoff"
retry_execute "primary_model" "prompt" policy_id="production"

📈 Sentiment Analytics - Track user satisfaction and detect frustration:

sent_frustration messages sensitivity="high"
sent_satisfaction days=30  # Generate satisfaction report

---

What's in v9.0.0

Advanced AI Orchestration - 42 New Tools Across 10 New Phases

| Phase | Tools | Description | |-------|-------|-------------| | Phase 26: Intelligent Auto-Router | 4 | Zero-config task classification and model routing | | Phase 27: Autonomous Agent Swarm | 5 | Spawn specialized AI agents working in parallel | | Phase 28: Background Agents | 7 | Persistent monitoring agents (Code Sentinel, Doc Keeper) | | Phase 29: Semantic Response Cache | 5 | Embedding-based similarity caching for cost savings | | Phase 30: Predictive Model Loading | 3 | Usage pattern analysis for model pre-warming | | Phase 31: Conversation Archaeology | 5 | Deep search, decision extraction, timeline building | | Phase 32: A/B Testing Framework | 5 | Model comparison experiments with statistical analysis | | Phase 33: Cascade Execution | 4 | Confidence-based model escalation (fast→balanced→capable→expert) | | Phase 34: Cost Intelligence | 7 | Token tracking, budget alerts, local vs cloud comparison | | Phase 35: Persona Fusion | 6 | Dynamically combine personas for complex tasks |

New Modules (v9.0.0)

| Module | Purpose | |--------|---------| | smart_router.py | Intelligent task classification and model routing | | agent_swarm.py | Multi-agent orchestration with parallel execution | | background_agents.py | Long-running monitoring agents with alerts | | semantic_cache.py | Embedding-based response caching | | predictive_loader.py | Usage pattern learning and prediction | | conversation_archaeology.py | Deep conversation search and analysis | | ab_testing.py | A/B experiment framework | | cascade.py | Tiered model execution with confidence | | cost_intelligence.py | Cost tracking and optimization | | persona_fusion.py | Dynamic persona combination | | server_extensions_v3.py | Extension registration v3 |

Key Features

🤖 Agent Swarm - Spawn specialized agents (Code, Research, Writing, Analysis) that work in parallel and synthesize results:

swarm_spawn "Build a comprehensive analysis of this codebase"

🎯 Cascade Execution - Start with fast models, escalate to capable ones only when needed:

cascade_smart "Complex reasoning task requiring detailed analysis"

💰 Cost Intelligence - Track spending, compare local vs cloud, get optimization tips:

cost_compare_local_cloud  # Shows 95%+ savings using local models

🔮 Predictive Loading - Learn your usage patterns and pre-warm models:

predict_session_start  # "Based on history, you typically code at 9am"

---

What's in v8.0.0

36 New Tools Across 10 New Phases

| Phase | Tools | Description | |-------|-------|-------------| | Phase 16: Shadow Personas | 5 | Multi-perspective conversation analysis | | Phase 17: Workspaces | 4 | Workspace management and data isolation | | Phase 18: Real-Time Web | 3 | Web search, URL fetch, YouTube transcripts | | Phase 19: Chat Management | 4 | Export, clone, branch, merge conversations | | Phase 20: Folder Organization | 4 | Conversation folder management | | Phase 21: PII Scrubbing | 3 | 13 PII patterns, GDPR/HIPAA compliance | | Phase 22: Embedding Visualization | 4 | Document clustering and similarity | | Phase 23: Health Dashboard | 3 | Service monitoring and alerts | | Phase 24: Configuration Profiles | 4 | Save/load/compare configurations | | Phase 25: Automated Maintenance | 3 | Cleanup, optimization, health scoring |

New Modules (v8.0.0)

| Module | Purpose | |--------|---------| | shadow_personas.py | Shadow persona integration | | workspaces.py | Workspace management | | realtime_data.py | Web/YouTube integration | | chat_management.py | Chat operations | | folders.py | Folder organization | | pii_tools.py | PII detection and scrubbing | | embeddings.py | Embedding visualization | | dashboard.py | Health monitoring | | profiles.py | Configuration profiles | | maintenance.py | Automated maintenance | | server_extensions_v2.py | Extension registration v2 |

Comprehensive Testing

• 130+ unit tests covering all modules
• PII pattern detection validated
• Cosine similarity mathematical tests
• Maintenance dry-run verification

---

What's in v7.0.0

35 Tools Across 6 Phases

| Phase | Tools | Description | |-------|-------|-------------| | Phase 10: Knowledge Stacks | 5 | RAG system management - list, search, analyze | | Phase 11: Model Management | 6 | Download/delete models, find duplicates, storage analysis | | Phase 12: Claude↔Local Bridge | 5 | Intelligent model delegation, multi-model consensus | | Phase 13: Turnstile Workflows | 7 | 5 built-in automation templates, dry-run execution | | Phase 14: Live Context | 5 | Real-time system/datetime/Msty context for prompts | | Phase 15: Conversation Analytics | 5 | Usage patterns, content analysis, session metrics |

Enhanced Tagging System v2.0

• Context length awareness: long_context (100K+), very_long_context (250K+), massive_context (500K+)
• Quantization detection: fp16, 8bit, 6bit, 5bit, 4bit, 3bit
• Architecture tags: moe, mlx, gguf
• New size tier: massive (200B+ parameters)

Msty 2.4.0+ Service Support

| Service | Port | Description | |---------|------|-------------| | Local AI Service | 11964 | Ollama-compatible API | | MLX Service | 11973 | Apple Silicon optimized models | | LLaMA.cpp Service | 11454 | GGUF model support | | Vibe CLI Proxy | 8317 | Optional settings-managed proxy for linked CLI providers |

---

What is This?

Msty Admin MCP lets you manage your entire Msty Studio installation through Claude Desktop. Instead of clicking through menus or manually editing config files, just ask Claude:

> "Show me my Msty personas and suggest improvements"

> "Compare my local models on a coding task"

> "What models do I have available across all services?"

> "Benchmark my fastest model for coding tasks"

Claude handles the rest—querying databases, calling APIs, analysing results, and presenting actionable insights.

---

Quick Start

Prerequisites

• macOS (Apple Silicon recommended)
• Python 3.10+
• Msty Studio Desktop 2.4.0+ installed
• Claude Desktop with MCP support

Installation

# Clone the repository
git clone https://github.com/DBSS/msty-admin-mcp.git
cd msty-admin-mcp

# Create virtual environment
python -m venv .venv
source .venv/bin/activate

# Install dependencies
pip install -r requirements.txt

Claude Desktop Configuration

Important: Claude Desktop doesn't always respect the cwd setting, so we use a shell script launcher.

1. The repository includes run_msty_server.sh. Make sure it's executable:

``bash chmod +x run_msty_server.sh ``

1. Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

``json { "mcpServers": { "msty-admin": { "command": "/absolute/path/to/msty-admin-mcp/run_msty_server.sh", "env": { "MSTY_TIMEOUT": "30" } } } } ``

1. Restart Claude Desktop (Cmd+Q, then reopen)

1. You should see "msty-admin" in your available tools with 224 tools loaded.

---

Available Tools (224 Total)

Phase 1: Installation & Health (7 tools)

| Tool | Description | |------|-------------| | detect_msty_installation | Find Msty Studio, verify paths, check running status | | read_msty_database | Query conversations, personas, prompts, tools | | list_configured_tools | View MCP toolbox configuration | | get_model_providers | List AI providers and local models | | analyse_msty_health | Database integrity, storage, and local service status | | get_server_status | MCP server info and capabilities | | scan_database_locations | Find database files in common locations |

Phase 2: Configuration Management (4 tools)

| Tool | Description | |------|-------------| | export_tool_config | Export MCP configs for backup or sync | | import_tool_config | Validate and prepare tools for Msty import | | generate_persona | Create personas from templates (opus, coder, writer, minimal) | | sync_claude_preferences | Convert Claude Desktop preferences to Msty persona |

Phase 3: Local Model Integration (8 tools)

| Tool | Description | |------|-------------| | get_sidecar_status | Check core services plus optional Vibe CLI Proxy | | list_available_models | Query models from ALL services with breakdown | | query_local_ai_service | Direct low-level API access | | chat_with_local_model | Send messages with automatic metric tracking | | recommend_model | Hardware-aware model recommendations by use case | | list_model_tags | Get available tags for smart model selection | | find_model_by_tag | Find models matching specific tags | | get_cache_stats | View response cache statistics | | clear_cache | Clear cached responses |

Phase 4: Intelligence & Analytics (5 tools)

| Tool | Description | |------|-------------| | get_model_performance_metrics | Tokens/sec, latency, error rates over time | | analyse_conversation_patterns | Privacy-respecting usage analytics | | compare_model_responses | Same prompt to multiple models, compare quality/speed | | optimise_knowledge_stacks | Analyse and recommend improvements | | suggest_persona_improvements | AI-powered persona optimisation |

Phase 5: Calibration & Workflow (4 tools)

| Tool | Description | |------|-------------| | run_calibration_test | Test models across categories with quality scoring | | evaluate_response_quality | Score any response using heuristic evaluation | | identify_handoff_triggers | Track patterns that should escalate to Claude | | get_calibration_history | Historical results with trends and statistics |

Phase 6: Advanced Model Management (4 tools)

| Tool | Description | |------|-------------| | get_model_details | Comprehensive model info (context length, parameters, tags, capabilities) | | benchmark_model | Performance benchmarks at different context sizes (tokens/sec) | | list_local_model_files | List MLX and GGUF model files on disk with sizes | | estimate_model_requirements | Estimate memory/hardware requirements for a model |

Phase 7: Conversation Management (3 tools)

| Tool | Description | |------|-------------| | export_conversations | Export chat history in JSON, Markdown, or CSV format | | search_conversations | Search through conversations by keyword or title | | get_conversation_stats | Usage analytics: messages per day, model usage, session lengths |

Phase 8: Prompt Templates & Automation (4 tools)

| Tool | Description | |------|-------------| | create_prompt_template | Create reusable templates with {{variable}} placeholders | | list_prompt_templates | List all templates, optionally filtered by category | | run_prompt_template | Execute a template with variable substitutions | | smart_model_router | Auto-select the best model for a given task description |

Phase 9: Backup & System Management (3 tools)

| Tool | Description | |------|-------------| | backup_configuration | Create comprehensive backup of personas, prompts, templates, tools | | restore_configuration | Restore configuration from a backup file | | get_system_resources | CPU, memory, and disk usage relevant to AI inference |

---

Model Tagging System

Msty

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: DRVBSS
• Source: DRVBSS/msty-admin-mcp
• License: MIT

Install and usage instructions live in the source repository linked above.