Loading ToolBench

Reading the current corpus…

intranet-dashboard MCP server · F · ToolBench

intranet-dashboard

github.com/eduardo-lezama/intranet-dashboard

A Flask-based home intranet dashboard that aggregates data from multiple services including weather, Pi-hole DNS statistics, Mealie recipes, Home Assistant energy consumption, SettleUp finances, shopping lists, and document management from a NAS.

<=2025-11-25STREAMABLE_HTTP17 tools

21/100

Definition Quality21

Protocol Readiness12

Supportability26

Spec posture

Inferred effective spec <=2025-11-25·current baseline 2026-07-28

Static source inference · medium confidence · detected: Logging

Deprecated protocol patterns detected

Summary

This is a Flask web dashboard, not an MCP server. No MCP protocol implementation detected. Tools are Flask routes, not MCP tool definitions with schemas. No input schemas visible in source code. Descriptions are minimal (10-50 chars, well below the 194-char baseline). No parameter type definitions, no output schemas documented, no error handling guidance. The server exposes HTTP endpoints but does not implement the MCP specification. Tool definitions are inferred from route handlers, not explicitly registered with MCP schemas.

Tools (17)

api_devicesread onlyauthsource verified20/100

Estados de dispositivos IoT desde Home Assistant (parallelized).

api_dnscryptread onlysource verified20/100

Health check de DNSCrypt-proxy via consulta DNS.

api_docs_structureread onlysource verified22/100

Estructura de carpetas y archivos del NAS. Salida: {"Categoria": [{"name": ..., "path": ...}, ...]}

api_energyread onlyauthsource verified18/100

Resumen de consumo eléctrico desde Home Assistant.

api_healthread onlysource verified17/100

Health check endpoint.

api_mealieread onlyauthsource verified22/100

Resumen de recetas y plan de comidas de hoy.

api_mealie_debugread onlyauthsource verified18/100

Debug endpoint para Mealie API.

Issues (5)

CRITICALtool ↗

Not an MCP server. This is a Flask web application, not an MCP-compliant tool server. No MCP protocol implementation, no tool registration via MCP, no schema definitions.

all

CRITICALconstrained-input ↗

Zero input schemas. No tool has a visible JSON Schema definition for inputs. All 17 tools score 0 on schema dimension. Cannot validate LLM-provided parameters.

all

CRITICALtool-description ↗

Minimal descriptions (10-50 chars). All tool descriptions fall far below the 194-char baseline. Examples: 'Estructura de carpetas...' (30 chars), 'Sirve archivos...' (20 chars). Descriptions lack WHEN to use, WHAT it returns, and prerequisites.

api_docs_structureserve_documentapi_energyapi_devicesapi_mealieapi_mealie_debugapi_piholeapi_statusapi_healthapi_menu_processorapi_dnscryptapi_settleupapi_settleup_debug_transactions

Recommendations

Implement MCP protocol: register tools via MCP's tool registration mechanism, not Flask routes. Use the MCP SDK for Python to expose tools with proper schemas.
Add JSON Schema definitions for all tool inputs. Every parameter must have type (string, integer, boolean, etc.), description (50-100 chars), and constraints (enum, pattern, min/max).
Expand tool descriptions to 100-200 chars. Include: what the tool does, when to call it (vs similar tools), what it returns, and any prerequisites. Example: 'Fetch current energy consumption from Home Assistant. Returns kWh used in last hour, daily total, and cost estimate. Call this before api_devices to correlate usage with active appliances.'
Document output schemas. For each tool, specify the response structure: field names, types, and what each field means. Example for api_energy: {consumption_kwh: number, cost_eur: number, timestamp: string (ISO 8601)}.
Add error handling guidance. When a tool fails (e.g., Home Assistant unreachable), return actionable errors: 'Home Assistant API timeout. Retry in 5s or check service health via api_status.' Do not return raw stack traces.

Spec posture evidence

Inferred effective spec: <=2025-11-25.

Relies on Logging (deprecated) - log to stderr or use OpenTelemetry

Score history

Overall score trend

First recorded score · v2 rubric

21/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	F	21	<=2025-11-25	v2