Loading ToolBench

Reading the current corpus…

trucksim-mcp MCP server · D · ToolBench

trucksim-mcp

An MCP server exposing Euro Truck Simulator 2 / American Truck Simulator telemetry and driving analytics to any AI harness.

<=2025-11-25STDIO9 tools

51/100

Definition Quality60

Protocol Readiness47

Supportability38

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

Strong naming and descriptions across all 9 tools. All tools follow verb_noun pattern (get_*, list_*) and have clear, contextual descriptions (avg 180 chars, within 10-1024 baseline). All tools are READ_ONLY with proper ToolAnnotations. Critical gap: NO input schemas visible in source code, all 9 tools show Input: {} with no parameter definitions. This is a hard blocker for schema scoring. Error handling via @tool_errors decorator provides generic recovery guidance but lacks categorization (retryable vs fatal). Output structure inferred from descriptions but not formally documented.

Tools (9)

check_speedingread onlysource verified57/100

Are you speeding right now, and by how much over the posted limit?

get_active_jobread onlysource verified60/100

The current delivery job: cargo, route, pay, deadline, and on-time status.

get_eco_scoreread onlysource verified60/100

A 0-100 driving score for this session, with the factors dragging it down.

get_fuel_statusread onlysource verified60/100

Fuel level, consumption, estimated range, and whether it's enough to reach the routed destination.

get_navigationread onlysource verified60/100

Routing status: distance and ETA to the destination, posted limit, and whether you're currently speeding.

get_rest_advisorread onlysource verified60/100

Fatigue guidance: how long you've been driving, and whether a break is needed.

get_trip_summaryread onlysource verified60/100

Rolling trip totals since the server started: distance, time, speeds, fuel, events.

Issues (5)

CRITICALtool ↗

All 9 tools have Input: {} with no visible parameter schemas. This blocks LLM parameter inference and validation.

get_truck_stateget_navigationget_fuel_statusget_active_jobcheck_speedingget_eco_scoreget_trip_summaryget_rest_advisorlist_recent_events

HIGHresponse-shaper ↗

Output schemas not documented. Descriptions mention returned fields (speed, gear, fuel, etc.) but no formal schema definition. LLMs cannot plan downstream calls without knowing return structure.

get_truck_stateget_navigationget_fuel_statusget_active_jobget_eco_scoreget_trip_summarylist_recent_events

HIGHrecovery-guide ↗

Error handling via @tool_errors decorator returns generic 'Error reading telemetry: {exc}. Check TRUCKSIM_SOURCE configuration.' No error categorization (retryable vs user-fixable vs fatal) or recovery guidance beyond config check.

Recommendations

Add explicit JSON Schema input definitions to all 9 tools. Even parameterless tools should declare 'properties: {}, required: []' for clarity.
Document output schemas for each tool. E.g., get_truck_state returns {speed_kph: number, speed_limit_kph: number, engine_on: boolean, gear: integer, rpm: number, fuel_liters: number, ...}. Use JSON Schema or TypedDict annotations.
Enhance error handling: categorize exceptions as retryable (connection timeout → 'Retry in 5s'), user-fixable (game not running → 'Start the game'), or fatal (invalid config → 'Fix TRUCKSIM_SOURCE'). Return structured error objects with code, message, and recovery hint.
Add pagination to list_recent_events: accept limit (1-100, default 20) and offset/cursor parameters. Return {events: [...], total_count: N, has_more: bool}.
Document output field names and types in tool descriptions. E.g., 'Returns eco_score (0-100 integer) and factors (array of {name, impact_percent})' so LLMs know what to extract.

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

51/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	D	51	<=2025-11-25	v2