// SCAN REPORT

Msty Admin MCP

36 tools. 8 can modify or destroy data without limits.

8 write tools that can modify data. Rate limits recommended.

Last updated: 12 Jun 2026

8 can modify or destroy data

28 read-only

36 tools total

Community server · catalogue entry verified 12/06/2026

How to control Msty Admin MCP ↓

TOOL MAP

What Msty Admin MCP exposes to your agents

Read (28) Write / Execute (8) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Msty Admin MCP tools

Execute · High bloom_evaluate_model This tool executes a behavioral evaluation workflow on a model, which is an active operation with side effects (e.g., generating evaluation logs, consuming computational resources, potentially modifying model state or ou Execute · High run_calibration_test This tool triggers an external operation (a calibration test) on a model, which is a computational/operational action that modifies system state and whose outcome depends on supplied arguments. Execute · High chat_with_llamacpp_model This tool triggers external model execution via the LLaMA.cpp runtime. Execute · High chat_with_local_model This tool executes a chat interaction with a local AI model via Ollama, triggering external computation whose effects depend on the prompt arguments.

8 of Msty Admin MCP's 36 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Msty Admin MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Msty Admin MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "sync_claude_preferences": {
    "limits": [
      {
        "counter": "sync_claude_preferences_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "identify_handoff_triggers": {
    "limits": [
      {
        "counter": "identify_handoff_triggers_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Msty Admin MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MSTY ADMIN →

Free to start. No card required.

FULL CATALOGUE

All 36 Msty Admin MCP tools

EXECUTE 5 tools

Execute bloom_evaluate_model Run Bloom behavioral evaluation on a model. Execute run_calibration_test Run calibration test on a model. Execute chat_with_llamacpp_model Chat with a LLaMA.cpp model. Execute chat_with_local_model Chat with a Local AI (Ollama) model. Execute chat_with_mlx_model Chat with an MLX model.

WRITE 3 tools

Write sync_claude_preferences Sync Claude preferences with Msty. Write generate_persona Generate AI persona configuration. Write import_tool_config Import tool configuration.

READ 28 tools

Read identify_handoff_triggers Identify handoff trigger patterns. Read analyse_conversation_patterns Analyze conversation patterns. Read analyse_msty_health Get comprehensive Msty system health report. Read bloom_check_handoff Check if model should hand off to Claude. Read bloom_get_history Get Bloom evaluation history. Read bloom_get_thresholds Get quality thresholds for a task category. Read bloom_list_behaviors List available Bloom behaviors. Read bloom_validate_model Validate model for Bloom evaluation. Read compare_model_responses Compare responses from different models. Read detect_msty_installation Detect Msty installation and configuration paths. Read evaluate_response_quality Evaluate response quality. Read get_calibration_history Get calibration history. Read get_model_performance_metrics Get model performance metrics. Read get_model_providers List available model providers. Read get_server_status Get MCP server status. Read get_service_status Get status of all service backends. Read get_vibe_proxy_status Check Vibe CLI proxy status. Read list_available_models List all available models across services. Read list_configured_tools List all Msty configured tools. Read list_llamacpp_models List LLaMA.cpp models. Read list_mlx_models List MLX models. Read optimise_knowledge_stacks Suggest knowledge stack optimizations. Read query_local_ai_service Query Local AI (Ollama) service. Read query_vibe_proxy Query Vibe CLI proxy. Read read_msty_database Query Msty SQLite database directly. Read recommend_model Get model recommendation. Read suggest_persona_improvements Suggest persona improvements. Read export_tool_config Export Msty tool configuration.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Msty Admin MCP

How do I prevent bulk modifications through Msty Admin MCP? +

The Msty Admin MCP server has 3 write tools including sync_claude_preferences, generate_persona, import_tool_config. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Msty Admin MCP.

How many tools does the Msty Admin MCP server expose? +

36 tools across 3 categories: Execute, Read, Write. 28 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Msty Admin MCP? +

Register the Msty Admin MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Msty Admin MCP tool call.

Deterministic rules across all 36 Msty Admin MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MSTY ADMIN →

Free to start. No card required.

36 Msty Admin MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.