extract_overtureLABSCO SUMMARY
Check `ml_ready` before trusting the ML tools — they answer either way.
The neural solver-selection tools return a flag saying whether the model files were actually found, and the quick-start walks you through verifying it. That is a good design: the failure is visible rather than silent. The other thing to note is the engine split — the external rust-optimizer is a separate cargo install, and the README's own comparison table puts it well ahead of the internal engine on both speed and route length, so it is worth installing before drawing conclusions about quality.
What it is
A Rust route-optimisation engine with an MCP server built in. The pipeline runs from raw map data to an optimised route: extract a road network from Overture, OSM or PMTiles, compile it into a compact binary format, then solve either the Chinese Postman Problem — covering every street — or a Vehicle Routing Problem across a set of stops. Several solvers are available, and ML models can pick between them.
What you get
- Pipeline tools including
extract_overturefor road data,compilefor the binary map, andoptimizefor a CPP solve v2rmp_rust_optimizeruses the external optimiser, which the README reports as faster and producing shorter routes than the internal enginevrp_solvefor vehicle routing, with greedy, Clarke-Wright, sweep, two-opt, OR-Tools and neural solverspartitionsplits a graph into zones;haversine_distancecomputes point-to-point distance;list_r2_bucketlists stored artefacts- Three ML tools —
predict_solver,predict_qualityandtune_hyperparams— which report anml_readyflag so you can tell whether the models actually loaded pipelineandget_valhalla_matrixneed internet access — the repository's regression harness skips both offline, and in production they need outbound HTTPS- A CLI covering the same ground, plus
serveto start the MCP server
Requirements
Install with cargo install v2rmp, then point your client at the rmpca command with the serve argument. For better CPP results also cargo install rust-optimizer. The ML tools need a build with the ml feature and the model files present — predict_solver, predict_quality and tune_hyperparams report ml_ready as False when the weights are missing, which is the signal to train or copy them. No account and no key; the server speaks JSON-RPC over stdin.
Setup effort
One command — cargo install v2rmp
USE CASES
01
Planning a route that covers every street in an area
Extract the road network for a bounding box, compile it, and solve the Chinese Postman problem over it.
02
Routing a fleet across a set of stops
Solve the vehicle routing problem with the solver that fits the instance.
03
Choosing a solver without guessing
Ask the model which solver suits this instance and what quality to expect before running it.
04
Breaking a large area into workable zones
Partition the graph first, then solve each zone separately.
13 tools
Listed in project docs. Your client may show a different list.
compileoptimizev2rmp_rust_optimizervrp_solvepartitionlist_r2_buckethaversine_distancepipelinepredict_solverpredict_qualitytune_hyperparamsget_valhalla_matrixBEFORE YOU INSTALL
What to know first
Tools you get
13 tools named in the project's documentation.
Requires
rmpca on PATH
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"rmpca": {
"command": "rmpca",
"args": [
"serve"
]
}
}
}cargo
TERMINAL
cargo install v2rmp
