Enables AI assistants to perform road routing, geocoding, distance matrices, and fleet optimization specifically for Southeast Asia.
Also known as justrouting/mcp, mcp
- Stars
- 1
- Tools
- 4
- Downloads, 30 days
- —
- Latest version
- 0.1.5
- Last commit
- Oct 22, 2026
- License
- MIT
What is JustRouting MCP?
JustRouting enables AI assistants to perform road routing, geocoding, distance matrices, and fleet optimization specifically for Southeast Asia. It exposes 4 tools, such as geocode, route, table.
Summary generated from the project's README
About JustRouting MCP server
JustRouting MCP provides specialized geospatial capabilities for AI assistants like Claude and Cursor, with a specific focus on the Southeast Asia region. It allows models to interact with road networks to perform tasks ranging from simple address lookups to complex logistics planning. Users can integrate this server into their local development environments via stdio after installing the prebuilt binary or building from source.
The server provides four distinct tools to handle different spatial requirements. The geocode tool converts addresses or landmarks into coordinates, while the route tool calculates driving paths, including options for motorcycle profiles and road exclusions like tolls or motorways. For comparative analysis, the table tool generates distance and travel-time matrices between multiple points. Finally, the optimize tool manages fleet logistics by assigning jobs to vehicles based on capacity, time windows, and priorities.
To use these features, developers must obtain an API key from JustRouting and configure it as an environment variable. The system supports multidimensional capacity constraints, such as weight and pallet counts, making it suitable for professional logistics workflows.
What you can do with it
- 1Convert addresses to coordinatesAn AI can transform a business name or street address into precise longitude and latitude values.
- 2Calculate specific driving routesA developer can request a driving route that specifically avoids toll roads or uses a motorcycle profile.
- 3Find the closest service providerThe assistant can determine which driver is nearest to a customer by comparing multiple locations in a matrix.
- 4Optimize fleet delivery schedulesAn AI can plan complex routes for multiple vehicles while considering job priorities and vehicle capacities.
Written from the project's README. Every use case is checked against a quote from it.
JustRouting MCP tools 4
Detected from the READMEgeocoderoutetableoptimize
| geocode | — | |
| route | — | |
| table | — | |
| optimize | — |
Configuration
JUSTROUTING_API_KEYRequiredSecretYour JustRouting API key (create one at https://justrouting.tech)
| Name | Description | |
|---|---|---|
| JUSTROUTING_API_KEY | Your JustRouting API key (create one at https://justrouting.tech) | RequiredSecret |
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubJustRouting MCP
Routing, geocoding, distance matrices, and vehicle routing for AI assistants — focused on Southeast Asia.
JustRouting MCP lets MCP-compatible AI assistants such as Claude and Cursor use JustRouting for road routing, geocoding, distance and travel-time comparison, and multi-vehicle route optimization.
Designed for Southeast Asia.
Quick Start
1. Install
macOS / Linux
curl -fsSL https://raw.githubusercontent.com/justrouting/mcp/main/install.sh | sh
The installer downloads the latest prebuilt binary for your platform and installs justrouting-mcp.
No Go installation is required.
From source
go install github.com/justrouting/mcp/cmd/justrouting-mcp@latest
Make sure justrouting-mcp is available in your PATH.
2. Set your API key
Get an API key from JustRouting, then set:
export JUSTROUTING_API_KEY="your-api-key"
3. Connect to Claude or Cursor
Add the following MCP server configuration:
{
"mcpServers": {
"justrouting": {
"command": "justrouting-mcp",
"env": {
"JUSTROUTING_API_KEY": "your-api-key"
}
}
}
}
The server communicates with MCP clients through stdio.
Tools
| Tool | Purpose |
|---|---|
geocode |
Place or address → coordinates |
route |
Calculate one route |
table |
Compare travel times or distances between multiple locations |
optimize |
Assign jobs to vehicles and order their stops |
The tools are intentionally separated by task:
route = calculate table = compare optimize = decide
geocode
Search for a place or address and convert it into coordinates.
Use it when the user provides:
- a place name
- a landmark
- a business
- a street address
- another location description
Do not use it when the user already provides coordinates.
Input
{
"name": "Marina Bay Sands",
"housenumber": "10",
"street": "Bayfront Avenue",
"postcode": "018956",
"city": "Singapore",
"country": "Singapore"
}
The available fields are:
name— place, landmark, or business namehousenumber— house or building numberstreet— street namepostcode— postal or ZIP codecity— city or localitycountry— countrylimit— maximum number of results, up to 10filters— optional search filters
Only provide fields that can be determined from the user's request. Do not invent missing address components.
Country and city can be useful for disambiguating common or abbreviated place names.
Output
{
"results": [
{
"longitude": 103.859,
"latitude": 1.2834,
"coordinates": "103.859,1.2834",
"formatted": "Marina Bay Sands, 10 Bayfront Avenue, 018956, Singapore",
"place_id": "51667b3e...",
"country_code": "sg",
"result_type": "building"
}
]
}
Results are ordered by relevance.
By default, the best matching result is returned. When multiple results are requested, choose the result that best matches the user's intended location.
The coordinates value is in longitude,latitude format and can be passed directly to route, table, or optimize.
If geocoding is used as part of a routing workflow, verify that the selected result matches the intended place before using its coordinates.
route
Calculate a driving route between two locations.
Use it when the user needs to:
- calculate driving distance
- estimate travel time
- get a route between two locations
- get route geometry
- understand which roads a route uses
- avoid specific road types
Input
{
"origin": "103.8198,1.3521",
"destination": "103.9915,1.3644"
}
Coordinates must use:
longitude,latitude
For example:
103.8198,1.3521
Optional motorcycle routing:
{
"origin": "103.8198,1.3521",
"destination": "103.9915,1.3644",
"profile": "motorcycle"
}
Use profile: "motorcycle" when the user explicitly asks for a motorcycle or motorbike route.
Otherwise, omit profile to use the default driving profile.
Avoid roads
Use exclude when the user explicitly asks to avoid a type of road.
Supported values:
tollmotorwayferry
Example:
{
"origin": "103.8198,1.3521",
"destination": "103.9915,1.3644",
"exclude": ["toll"]
}
Road avoidance is a preference, not a guarantee. The routing engine avoids the specified road type when a reasonable alternative exists.
Output
{
"distance_meters": 18500,
"duration_seconds": 1500,
"profile": "driving",
"origin": {
"input": "103.8198,1.3521",
"snapped": [103.8197, 1.3520],
"name": "Example Road",
"distance": 4.2
},
"destination": {
"input": "103.9915,1.3644",
"snapped": [103.9915, 1.3644],
"name": "Airport Boulevard",
"distance": 8.1
},
"geometry": "ka|`@_ceeEnAqB...",
"summary": {
"roads": ["East Coast Parkway"],
"tolls": false,
"ferry": false
}
}
distance_meters is the route distance in meters.
duration_seconds is the estimated travel duration in seconds.
geometry is a simplified encoded polyline that can be used to render the route on a map.
summary.roads lists the main roads used by the route.
summary.tolls indicates whether the route uses toll roads.
summary.ferry indicates whether the route includes a ferry crossing.
If the user provides place names or addresses instead of coordinates, call geocode first.
table
Calculate a distance and/or travel-time matrix between multiple locations.
Use it when the user needs to:
- find the nearest driver, vehicle, store, or facility
- compare several destinations
- compare multiple origin-destination pairs
- build a distance or travel-time matrix
Do not use it for a single route between two locations. Use route instead.
Input
{
"coordinates": [
"103.8391,1.2771",
"103.8590,1.2834",
"103.7986,1.2885"
],
"annotations": ["distance"]
}
Each coordinate has a stable zero-based index based on its position in the coordinates list.
Matrix rows correspond to sources.
Matrix columns correspond to destinations.
A matrix value at:
[row][column]
represents the route from that source to that destination.
For example:
durations[0][2]
is the travel time from source index 0 to destination index 2.
The sources and destinations returned by the tool contain the original coordinate indices so the matrix can be mapped back to the user's locations.
Nearest-driver example
For a question such as:
Which driver is closest to this customer?
Put the customer first:
coordinates[0] = customer
coordinates[1] = driver A
coordinates[2] = driver B
coordinates[3] = driver C
Then use the customer as the source and the drivers as destinations.
Read the corresponding matrix row and choose the smallest non-null distance or duration.
Selecting sources and destinations
source and destinations can restrict the matrix to specific coordinate indices.
For example:
{
"coordinates": [
"103.8391,1.2771",
"103.8590,1.2834",
"103.7986,1.2885"
],
"sources": [0],
"destinations": [1, 2]
}
This calculates routes from coordinate 0 to coordinates 1 and 2.
Annotations
Use:
"annotations": ["duration"]
for travel times.
Use:
"annotations": ["distance"]
for distances.
Use:
"annotations": ["duration", "distance"]
for both.
If omitted, both are returned.
Output
{
"code": "Ok",
"durations": [
[0, 1860, null],
[1850, 0, 2100],
[null, 2110, 0]
],
"distances": [
[0, 14200, null],
[14100, 0, 18400],
[null, 18200, 0]
],
"sources": [
{
"index": 0,
"name": "Duxton Road",
"location": [103.8391, 1.2771],
"distance": 12.3
}
],
"destinations": [
{
"index": 1,
"name": "Bayfront Avenue",
"location": [103.8590, 1.2834],
"distance": 8.4
}
]
}
durations are in seconds.
distances are in meters.
A matrix value of null means that the origin-destination pair is unreachable. Never interpret null as zero.
optimize
Assign jobs and shipments to vehicles and determine the order in which each vehicle should visit its stops.
Use it when the user needs to:
- assign multiple deliveries or pickups to vehicles
- plan routes for a fleet with amounts, capacity, skills, or time windows
- pair pickups with deliveries that one vehicle must serve in order
- determine the order of multiple stops
- optimize a multi-vehicle routing solution
Do not use it for a single route. Use route.
Do not use it only to compare distances between locations. Use table.
Input
{
"vehicles": [
{
"id": 1,
"start": "103.7923,1.3246",
"end": "103.7923,1.3246"
},
{
"id": 2,
"start": "103.8232,1.3241",
"end": "103.8232,1.3241"
}
],
"jobs": [
{
"id": 1,
"location": "103.7975,1.3104"
},
{
"id": 2,
"location": "103.7843,1.3149"
},
{
"id": 3,
"location": "103.7976,1.3198"
}
]
}
Each vehicle must have at least a start or an end.
For a round trip, set both to the same location:
{
"id": 1,
"start": "103.7923,1.3246",
"end": "103.7923,1.3246"
}
If start or end is omitted, the vehicle may start or end anywhere.
Each vehicle and job must have a unique id. Shipment pickup ids must be unique among pickups and delivery ids among deliveries. Break ids must be unique within their vehicle.
Locations must use:
longitude,latitude
A richer example with capacity, time windows and priorities:
{
"vehicles": [
{
"id": 1,
"start": "103.7923,1.3246",
"end": "103.7923,1.3246",
"capacity": [1000, 4],
"time_window": [0, 28800]
}
],
"jobs": [
{
"id": 1,
"location": "103.7975,1.3104",
"delivery": [100, 1],
"service": 300,
"time_windows": [[0, 14400]],
"priority": 80
}
],
"shipments": [
{
"pickup": {"id": 2, "location": "103.7843,1.3149", "service": 150},
"delivery": {"id": 3, "location": "103.7976,1.3198", "service": 150},
"amount": [50]
}
],
"options": {"g": true}
}
Vehicle profiles
Each vehicle can use its own routing profile.
For example:
{
"id": 1,
"profile": "motorcycle",
"start": "103.7923,1.3246",
"end": "103.7923,1.3246"
}
Use "motorcycle" when the user explicitly asks for a motorcycle or motorbike route.
Otherwise, omit profile to use the default driving profile.
Amounts and capacity
capacity on a vehicle and delivery, pickup and amount on tasks are multidimensional: one value per dimension.
{"capacity": [1000, 4]}
means 1000 kilograms and 4 pallets. Every such vector in one request must share the same length.
A vehicle serves a set of tasks only if its load never exceeds its capacity. Insufficient capacity is not an error: the task is moved to unassigned instead.
Skills
skills are integer capability tags. A task is served only by a vehicle that has all the task's skills. A task without skills can be served by any vehicle.
Time windows
A time window is an inclusive [start, end] pair in seconds. Use one clock for the whole request: either relative (for example [0, 14400] means within 4 hours of the planning start) or absolute UNIX timestamps. Early arrivals wait until the window opens. Tasks that cannot be reached in time are moved to unassigned.
Priority
priority is 0-100. When not everything fits, higher-priority tasks are kept and lower-priority ones are dropped.
Shipments
A shipment is a pickup and a delivery served in order by the same vehicle, with amount loaded at the pickup and unloaded at the delivery.
Breaks
A vehicle's breaks are rest periods with an id unique within the vehicle, optional time_windows, and a service duration in seconds.
Custom matrices
matrices supplies your own travel-time (durations), distance and cost matrices per profile ("car" or "motorcycle"). Use it only when the user supplies their own travel times; then location_index, start_index and end_index reference rows and columns instead of coordinates.
Route geometry
Set "options": {"g": true} to get an encoded polyline and distances back for every route. Use it when the user wants to draw the routes on a map.
Output
A simplified result looks like:
{
"summary": {
"cost": 2733,
"routes": 2,
"unassigned": 0,
"duration": 2733,
"delivery": [100, 1]
},
"routes": [
{
"vehicle": 1,
"cost": 1144,
"duration": 1144,
"geometry": "encoded_polyline",
"steps": [
{
"type": "start",
"location": [103.7923, 1.3246],
"arrival": 0
},
{
"type": "job",
"id": 2,
"job": 2,
"location": [103.7843, 1.3149],
"arrival": 269,
"duration": 269,
"load": [50]
},
{
"type": "end",
"location": [103.7923, 1.3246],
"arrival": 1144,
"duration": 1144
}
]
}
],
"unassigned": []
}
Read each route's steps in order to determine:
- which vehicle serves each task
- the order in which tasks are visited
- when each task is reached
pickup, delivery, and break steps may appear between the route's start and end steps. violations fields exist for API completeness and are always empty on the hosted API. geometry appears only with options.g.
Always check unassigned.
Do not assume that every task can be assigned to a vehicle.
If the user provides place names or addresses instead of coordinates, call geocode first for every location and use the selected coordinates in the optimization request.
Agent Workflows
JustRouting MCP is designed so that AI assistants can combine the tools into larger workflows.
Route between two places
For:
How long does it take to drive from Marina Bay Sands to Changi Airport?
The workflow is:
geocode → geocode → route
- Geocode the origin.
- Geocode the destination.
- Pass the resulting coordinates to
route.
If the user already provides coordinates, skip geocoding.
Find the nearest driver
For:
Which driver is closest to the customer?
The workflow is:
geocode × N → table
- Geocode the customer.
- Geocode each driver.
- Keep the locations in a fixed order.
- Use the customer as the source.
- Use the drivers as destinations.
- Compare the returned distances or durations.
Plan multiple vehicles
For:
I have two vans and six customers. Assign the customers to the vans and determine the stop order.
The workflow is:
geocode × N → optimize
- Geocode each vehicle's start/end location.
- Geocode every job location.
- Create one vehicle entry per vehicle.
- Create one job entry per customer.
- Call
optimize. - Read
routes[].stepsto determine each vehicle's itinerary. - Check
unassignedfor jobs that could not be served.
Coordinate Format
All routing tools use:
longitude,latitude
For example:
103.8198,1.3521
This is:
longitude = 103.8198
latitude = 1.3521
Do not reverse the order.
Claude
Add JustRouting MCP to your Claude MCP configuration:
{
"mcpServers": {
"justrouting": {
"command": "justrouting-mcp",
"env": {
"JUSTROUTING_API_KEY": "your-api-key"
}
}
}
}
Once connected, Claude can use the JustRouting tools directly.
Cursor
Add JustRouting MCP to your Cursor MCP configuration:
{
"mcpServers": {
"justrouting": {
"command": "justrouting-mcp",
"env": {
"JUSTROUTING_API_KEY": "your-api-key"
}
}
}
}
Once connected, Cursor can use the JustRouting tools directly.
Requirements
For prebuilt binaries:
- A JustRouting API key
For installation from source:
- Go 1.25+
The MCP server currently uses stdio transport.
Development
Clone the repository:
git clone https://github.com/justrouting/mcp.git
cd mcp
Install dependencies:
go mod download
Run tests:
go test ./...
Build:
go build -o justrouting-mcp ./cmd/justrouting-mcp
Run:
JUSTROUTING_API_KEY="YOUR-API-KEY" ./justrouting-mcp
Architecture
┌─────────────────────────────┐
│ MCP Client │
│ Claude / Cursor / AI │
└──────────────┬──────────────┘
│
│ MCP / stdio
▼
┌─────────────────────────────┐
│ justrouting-mcp │
│ │
│ geocode route │
│ table optimize │
└──────────────┬──────────────┘
│
│ Official Go Client
▼
┌─────────────────────────────┐
│ api.justrouting.tech │
└─────────────────────────────┘
The MCP server is intentionally thin.
It exposes JustRouting capabilities through MCP and uses the official JustRouting Go client for API communication.
Releases
Prebuilt binaries are published through GitHub Releases.
To create a release:
git tag v0.1.0
git push origin v0.1.0
GitHub Actions builds the binaries and publishes the release.
The one-line installer always installs the latest release.
Roadmap
The core routing capabilities are already available:
- Route calculation
- Geocoding
- Distance and travel-time matrix
- Vehicle routing optimization
Future improvements may include:
- Alternative routes
- Waypoints
- Streamable HTTP transport
- Remote MCP deployment
License
JustRouting MCP questions
What tools does JustRouting MCP provide?
It exposes 4 tools, including geocode, route, table, optimize.
What regions does JustRouting focus on?
The service is specifically designed for Southeast Asia.
Can I request motorcycle-specific routes?
Yes, you can use the motorcycle profile to get motorbike-specific routing.
How do I avoid certain types of roads?
You can use the exclude parameter to avoid tolls, motorways, or ferries.