Msty Admin MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MSTY_HOST | No | Msty installation host | 127.0.0.1 |
| MSTY_AI_PORT | No | Local AI (Ollama) port | 11964 |
| MSTY_TIMEOUT | No | Service timeout in seconds | 10 |
| MSTY_MLX_PORT | No | MLX service port | 11973 |
| MSTY_VIBE_PORT | No | Vibe CLI Proxy port | 8317 |
| ANTHROPIC_API_KEY | No | Required for Bloom judge model (Phase 6) | |
| MSTY_LLAMACPP_PORT | No | LLaMA.cpp service port | 11454 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| detect_msty_installationA | Detect Msty installation and configuration paths. |
| read_msty_databaseC | Query Msty SQLite database directly. |
| list_configured_toolsB | List all Msty configured tools. |
| get_model_providersA | List available model providers. |
| analyse_msty_healthA | Get comprehensive Msty system health report. |
| get_server_statusB | Get MCP server status. |
| export_tool_configC | Export Msty tool configuration. |
| sync_claude_preferencesB | Sync Claude preferences with Msty. |
| generate_personaC | Generate AI persona configuration. |
| import_tool_configD | Import tool configuration. |
| get_service_statusC | Get status of all service backends. |
| list_available_modelsA | List all available models across services. |
| query_local_ai_serviceD | Query Local AI (Ollama) service. |
| chat_with_local_modelC | Chat with a Local AI (Ollama) model. |
| recommend_modelC | Get model recommendation. |
| list_mlx_modelsB | List MLX models. |
| chat_with_mlx_modelC | Chat with an MLX model. |
| list_llamacpp_modelsB | List LLaMA.cpp models. |
| chat_with_llamacpp_modelD | Chat with a LLaMA.cpp model. |
| get_vibe_proxy_statusB | Check Vibe CLI proxy status. |
| query_vibe_proxyD | Query Vibe CLI proxy. |
| get_model_performance_metricsC | Get model performance metrics. |
| analyse_conversation_patternsD | Analyze conversation patterns. |
| compare_model_responsesC | Compare responses from different models. |
| optimise_knowledge_stacksC | Suggest knowledge stack optimizations. |
| suggest_persona_improvementsC | Suggest persona improvements. |
| run_calibration_testD | Run calibration test on a model. |
| evaluate_response_qualityD | Evaluate response quality. |
| identify_handoff_triggersC | Identify handoff trigger patterns. |
| get_calibration_historyC | Get calibration history. |
| bloom_evaluate_modelC | Run Bloom behavioral evaluation on a model. |
| bloom_check_handoffC | Check if model should hand off to Claude. |
| bloom_get_historyC | Get Bloom evaluation history. |
| bloom_list_behaviorsA | List available Bloom behaviors. |
| bloom_get_thresholdsC | Get quality thresholds for a task category. |
| bloom_validate_modelC | Validate model for Bloom evaluation. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 36 tools
Every tool targets a distinct function or backend with clear descriptions, making it easy for an agent to select the correct one. Even similar chat tools are differentiated by model backend. No overlapping purposes detected.
Tool names follow a consistent verb_noun pattern with snake_case, and related tools share prefixes like 'bloom_' or 'list_'. The naming is predictable and aids in understanding tool relationships.
With 36 tools, the server has a high number of tools relative to typical MCP servers. While many are justified by the broad scope of admin tasks, the count exceeds the recommended range and may overwhelm agents.
The tool set covers a wide range of admin functions including health monitoring, model evaluation, chat, calibration, and configuration. However, it lacks full model lifecycle management (create/update/delete) which could be a gap for some use cases.