F
licenseA
qualityC
maintenancePlans and optimizes last-mile delivery routes with capacity and time-window constraints, offering tools for managing deliveries, vehicles, routes, and what-if scenarios.
10
-
Fleet Route Optimizer
Server Details
Splits deliveries across vehicles and orders each route: time windows, capacities, road times. Free.
Ownership verified
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- Fleet Route Optimizer
TDQS
A4.1/5.0
Scored across 5 tools
Disambiguation4/5
Each tool maps to a distinct stage of the workflow: capability check, example discovery, example retrieval, solve, and async result polling. The only mild overlap is between list_route_examples and get_route_example, and check_request could be mistaken for input validation rather than a feasibility check, but the descriptions make the boundaries clear.
Naming Consistency4/5
All five names use snake_case verb_noun form (check_request, get_route_example, get_route_result, list_route_examples, optimize_routes), which is predictable. Minor deviation: 'check_request' describes a capability check rather than what its name literally suggests, and 'optimize_routes' is the only name without the 'route_' object prefix.
Tool Count5/5
Five tools is well-scoped for a route solver: one for feasibility, two for examples, one for solving, one for polling async jobs. Every tool earns its place and none appears redundant or ceremonial.
Completeness4/5
The core lifecycle (check fit -> get example -> solve -> retrieve async result) is fully covered, including the important async polling path. Gaps are minor: no job listing/cancellation, no standalone input validation or geocoding, and examples are read-only, but agents can work around these.
Available Tools
5 toolscheck_requestCheck if a routing request fitsARead-onlyInspect
Say in plain words what the user wants (e.g. 'two depots, 40 pickups and deliveries, 3 vans'). Returns whether this server can do it and, if not, the closest thing it can do. Fast, no solve. Call it first when unsure the tool fits.
| Name | Required | Description | Default |
|---|---|---|---|
| description | Yes | The user's routing problem in a sentence or two. |
get_route_exampleGet an example routing inputARead-onlyInspect
Return the full input of one example, in exactly the shape optimize_routes accepts. Edit it (depot, stops, vehicles, windows) to match the user's situation.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | es = Spanish labels. | |
| name | Yes |
get_route_resultGet a route resultARead-onlyInspect
Fetch the result of an optimize_routes job that returned status 'running'. Waits up to wait_seconds; call again while status is 'running'. Jobs expire 15 minutes after they finish.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes | ||
| wait_seconds | No |
list_route_examplesList example routing problemsARead-onlyInspect
List the built-in example routing problems. Use one to see a realistic input, or solve it as-is to show what the tool does.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
optimize_routesOptimize delivery routesARead-onlyInspect
Plan routes for one or more vehicles from one depot and return, per vehicle, the stop order with arrival times and load so far, plus stops that could not be served, totals, Google Maps links and warnings. Uses real road driving times. Solves take 10-60 s (more when many addresses must be looked up). Pass either example or the fields below. If the result has status 'running', call get_route_result with its job_id. Minimal example: {"depot": {"address": "1600 Pennsylvania Ave NW, Washington, DC 20500"}, "stops": [{"id": "Ana", "address": "..."}, {"id": "Bob", "lat": 38.9, "lon": -77.03, "window_open": "09:00", "window_close": "12:00", "service_minutes": 10}], "vehicles": 2}. Omitted: capacity = unlimited, no time windows, 1 vehicle, depot = the first stop, stops are dropped only when they cannot be served at all; every default applied is listed in the result's 'assumptions'. Call get_route_example for complete, realistic inputs.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | No | One sentence, in the user's own words, of what they are trying to do (e.g. 'plan tomorrow's deliveries for 3 vans'). Optional; helps improve the tool. | |
| depot | No | REQUIRED in practice: where every vehicle starts and ends, as an OBJECT with an address or lat+lon (a plain address string is also accepted and used as the address), e.g. {"address": "1 Main St, Springfield, IL 62701"} or {"lat": 41.4993, "lon": -81.6944}. If omitted, the first stop is used as the depot (reported in 'assumptions'). | |
| stops | No | The places to visit (not the depot). Each needs an address or lat+lon. | |
| country | No | Which geocoder reads the addresses: US (US Census, then OpenStreetMap) or OTHER (OpenStreetMap). Default US. | |
| example | No | Solve this built-in example instead of passing the fields below. | |
| vehicles | No | Either a number of identical vehicles (unlimited capacity), or one object per vehicle. | |
| parameters | No | Optional engine settings: SearchParametersTimeLimit (seconds, default 30, max 60), NoImprovementSeconds (20), RouteTimeLimit (minutes, default 1440), DroppedOrderCost (100000 = serve every stop that can be served), MinuteCost (1), LatePenaltyPerMinute (0 = windows are hard), MaxWaitMinutes (1440), MinimumDriveTime (5). | |
| wait_seconds | No | How long to wait for the solve inside this call (default 25). | |
| previous_routes | No | Re-optimize from existing routes: one list of stop ids (or 1-based stop numbers) per vehicle, in visiting order. The solver starts from these and improves them; new stops are fitted in. |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- Changed
optimize_routes2 fields changed- changed
Input schema / properties / depot / descriptionPrevious value: -"Where every vehicle starts and ends. Needs an address or lat+lon. If omitted, the first stop is used as the depot (reported in 'assumptions')."New value: +"REQUIRED in practice: where every vehicle starts and ends, as an OBJECT with an address or lat+lon (a plain address string is also accepted and used as the address), e.g. {\"address\": \"1 Main St, Springfield, IL 62701\"} or {\"lat\": 41.4993, \"lon\": -81.6944}. If omitted, the first stop is used as the depot (reported in 'assumptions')." - changed
Input schema / properties / depot / typePrevious value: -"object"New value: +[ + "object", + "string" +]
2 tool updates
- Added
check_request - Changed
optimize_routes2 fields changed- changed
Input schema / properties / depot / descriptionPrevious value: -"Where every vehicle starts and ends. Needs an address or lat+lon."New value: +"Where every vehicle starts and ends. Needs an address or lat+lon. If omitted, the first stop is used as the depot (reported in 'assumptions')." - added
Input schema / properties / goalAdded value: +{ + "description": "One sentence, in the user's own words, of what they are trying to do (e.g. 'plan tomorrow's deliveries for 3 vans'). Optional; helps improve the tool.", + "maxLength": 300, + "type": "string" +}
4 tool updates
- First observed
get_route_example - First observed
get_route_result - First observed
list_route_examples - First observed
optimize_routes
Related MCP Connectors
Agentic-AI route optimization for delivery fleets, capacity- and time-window-safe.
Plan vehicle routes, job assignments and load packing from stops, fleet and constraints.
Import orders, manage your fleet, and generate optimized last-mile delivery routes at scale.
Plans delivery routes for up to 25 US addresses and 5 drivers, with the stop order and a map.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceRoute optimization API for Brazil with tools for geocoding, distance matrices, isochrones, and advanced vehicle routing, supporting constraints like time windows, skills, and multi-profile fleets.62 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to submit asynchronous last-mile fleet optimizations that assign stops to vehicles and sequence routes from a depot, then retrieve status, summaries, ordered stop sequences, or unassigned ids. Supports hundreds to thousands of stops with optional weight, volume and time-window constraints, with results retained for 24 hours.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceAI-powered route optimization MCP server for heavy vehicles and logistics. Calculate truck-optimized routes, predict traffic congestion with LSTM neural networks, compute toll costs, fuel costs and CO2 emissions, find truck stops and check weather along any European route.MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.