fleet-mcp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@fleet-mcp-server Which vehicles wasted the most fuel idling last week, and what did it cost?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
fleet-mcp-server
An MCP server that lets an AI assistant answer fleet telematics questions in plain language: which vehicles idle the most and what it costs, which engine faults need attention first, and which drivers need coaching.
Ask Claude "Which three vehicles wasted the most fuel idling last week, and what did it
cost us?" and it calls idling_report, gets structured data back, and answers with numbers.
All data is simulated. This is a personal project showing how I would put a natural-language layer over telematics data for a customer. It contains no employer or customer data.
Why I built it
In solutions engineering, the same fleet questions come up in almost every customer conversation, and the answer usually means someone building a report. MCP turns those questions into tool calls an assistant can make on its own. This repo is the smallest complete version of that pattern: a data layer, a tool layer, tests, and a client.
Related MCP server: factory-supervisor-mcp
Tools
Tool | What it answers |
| What is in the fleet, optionally by depot |
| Trips, distance, idle time, fuel economy and active faults for one vehicle |
| Idle-time ranking with the estimated fuel cost of that idling |
| Active engine fault codes, most severe first |
| 0-100 score per driver from harsh-driving events per 100 km |
| Latest trips for one vehicle |
Design
Claude / any MCP client
│ stdio (JSON-RPC)
▼
server.py thin tool layer: descriptions written for the model, input validation
▼
store.py plain functions returning dicts: all business logic, unit-tested without MCP
▼
data.py SQLite schema + seeded synthetic fleet (same seed, same fleet)Decisions worth calling out:
Logic is separate from the protocol.
store.pyknows nothing about MCP, so swapping SQLite for a live telematics API means replacing one module.Errors tell the model what to do next. An unknown vehicle id returns "Call list_vehicles to see valid ids", so the assistant recovers without the user.
Assumptions are returned with the answer.
idling_reportincludes the litres-per-hour and fuel price it used, so the number can be challenged.The data has a story. Every fifth vehicle is seeded as a heavy idler and each driver has a stable risk profile, so the tools have real outliers to find.
Read-only. No tool writes to the database.
Run it
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
pytest -q # unit tests + an end-to-end test over stdio
python examples/demo_client.py # call the tools with no LLM involvedThe database is created and seeded on first run. To regenerate it:
fleet-mcp-seed --db fleet.db --vehicles 15 --days 30 --seed 42.
Use it from Claude Desktop
Add this to claude_desktop_config.json, with the path to your virtualenv's Python:
{
"mcpServers": {
"fleet": {
"command": "/absolute/path/to/.venv/bin/python",
"args": ["-m", "fleet_mcp.server"],
"env": { "FLEET_DB": "/absolute/path/to/fleet.db" }
}
}
}Use it from Claude Code
claude mcp add fleet -- /absolute/path/to/.venv/bin/python -m fleet_mcp.serverQuestions to try
Which vehicles idle the most, and what is that costing at $1.75 a litre?
What should maintenance look at first this week?
Which drivers in the Toronto depot need coaching, and why?
Compare V005 with the rest of its depot.
Limits and next steps
Data is synthetic and time is frozen at a fixed reference date so results are reproducible.
The safety score is a simple, explainable rule, not an industry standard.
Next: a live-API adapter behind the
storeinterface, and HTTP transport with auth for multi-user deployments.
License
MIT
Available Tools
6 toolsactive_faultsB
Active engine fault codes across the fleet, most severe first. Optionally filter by severity: low, medium or high. Use this for maintenance triage.
Inputs: severity. Returns: result
driver_safety_scoresA
Driver safety scores (0-100, higher is safer) from harsh-driving and speeding events
per 100 km over the last days days. Returned lowest score first, so the drivers who
most need coaching come first.
Inputs: days. Returns: result
idling_reportA
Rank vehicles by engine idle time over the last days days and estimate what that
idling cost in fuel. Use this for questions about waste, fuel savings or idle outliers.
fuel_price is dollars per litre.
Inputs: days, limit, fuel_price.
list_vehiclesA
List vehicles in the fleet, optionally filtered by depot (Ottawa, Toronto, Montreal).
Inputs: depot. Returns: result
recent_tripsB
Most recent trips for one vehicle, newest first, with driver, distance, idle minutes, fuel and top speed.
Inputs: vehicle_id (required), limit. Returns: result
vehicle_summaryA
Usage summary for one vehicle over the last days days: trips, distance, idle time,
fuel, fuel economy, top speed and number of active fault codes.
Inputs: vehicle_id (required), days.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct analytical view: fleet inventory, per-vehicle summary, fleet idle ranking, fleet fault triage, driver safety ranking, and per-vehicle trip detail. Minor overlap exists because vehicle_summary includes idle, fault, and trip metrics that idling_report, active_faults, and recent_trips cover in more depth, but scope and granularity differences keep selection clear.
All names use snake_case and are readable, but the set mixes verb-led names (list_vehicles, recent_trips) with noun-phrase names (vehicle_summary, idling_report, active_faults, driver_safety_scores). The inconsistency is stylistic rather than confusing, so agents can still infer intent.
Six tools is a well-scoped set for a fleet analytics server, with no redundant filler. Each tool maps to a common reporting question.
The read-only analytics surface covers fleet inventory, per-vehicle utilization, idling cost, fault triage, driver safety, and recent trip detail, which are the core queries for this domain. Minor gaps remain, such as a fleet-wide utilization overview or driver/vehicle metadata and maintenance history, but agents can work around them with the existing summaries.
Maintenance
Related MCP Connectors
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Ask Claude, ChatGPT, or any MCP client about your game's players, retention, revenue, and win rates.
An AI concierge that turns static forms into adaptive AI conversations. From any MCP client.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables natural-language Q&A, human-approved actions, and dashboard generation over a data ontology via MCP.-
- FlicenseAqualityDmaintenanceEnables AI assistants to manage factory operations through MCP, providing tools for real-time telemetry, predictive maintenance, inventory forecasting, order estimation, and AI supervisor copilot capabilities.18-
- FlicenseNot gradedqualityCmaintenanceMCP server that exposes OneMap8 fleet tracking to AI clients, enabling natural-language queries about devices, positions, reports, geofences, drivers, and more. Includes 32 tools, permission scoping, and safety guardrails.-
- AlicenseAqualityDmaintenanceProvides telemetry, rule-based anomaly detection, and maintenance recommendations for a synthetic connected-vehicle fleet through five narrow MCP tools, enabling fleet monitoring and analysis without external APIs.5MIT