routecraft
Routecraft is an MCP server that lets agents build and validate bicycle routes segment by segment using OpenStreetMap data, with weather, elevation, imagery, and export options.
README
Routecraft
Routecraft is a CLI for agents that build bicycle routes one road or path at a time.
The CLI shows connected choices and source evidence. The agent selects each segment. Routecraft validates every change and records an immutable revision.
Routecraft leaves road ranking and route decisions to the agent. It does not generate loops.
What Routecraft provides
- Road, path, surface, access, speed, control, and bicycle facility data from OpenStreetMap
- Connected route choices that keep each exact segment reference
- Weather, elevation, nearby places, and route comparison data
- Optional Google map, aerial, and Street View images
- Exact edits, hand-drawn connectors, and GPX or GeoJSON export with a Routecraft provenance file
- The same command contracts through a CLI and an MCP server
Source data can be incomplete. Routecraft reports unknown values and never labels a road as safe.
Requirements
Use Node.js 22 or newer.
Install from source
git clone https://github.com/quinnsprouse/routecraft.git
cd routecraft
npm install
npm run build
npm link
routecraft --version
Start an agent session
Create a separate workspace for each route.
export ROUTECRAFT_HOME="$(mktemp -d)"
routecraft guide next --json
Read result.actions from guide next. After a normal command, follow result.nextActions when that field exists.
Each executable action includes the next CLI and MCP calls with their expected results.
Load the bundled network when you want a local demo.
routecraft guide topic network --json
Run the command in result.bundledDemo.invoke.cli. Then run the returned route.create action and continue through result.nextActions.
Use a command guide before you need more options.
routecraft guide command route.append --json
routecraft guide command route.export --json
Agent skill
Routecraft includes a skill that matches the installed CLI version.
routecraft skills get core --json
routecraft skills get core --full --json
Register result.path with the agent host. Use result.content when the host accepts inline instructions.
MCP
Run routecraft mcp over standard input and output.
{
"mcpServers": {
"routecraft": {
"command": "routecraft",
"args": ["mcp"],
"env": {
"ROUTECRAFT_HOME": "/absolute/path/to/a/route-workspace"
}
}
}
}
Routecraft hides Google imagery commands until ROUTECRAFT_GOOGLE_MAPS_API_KEY exists. Run routecraft provider status --json to inspect the current setup.
Data sources
| Data | Source | Required setup |
|---|---|---|
| Roads, paths, surfaces, and access | OpenStreetMap and Overpass | None |
| Place lookup | Nominatim | Explicit public-service consent or a configured endpoint |
| Route weather | Open-Meteo | None for its public noncommercial endpoint |
| Segment elevation | USGS 3DEP | None |
| Map, aerial, and street images | Google Maps Platform | ROUTECRAFT_GOOGLE_MAPS_API_KEY |
Personal Strava and Ride with GPS data are not implemented.
Data license
Routecraft uses road and path data from OpenStreetMap contributors. OpenStreetMap licenses this data under the ODbL.
Develop
npm ci
npm run check
npm run package:smoke
See the architecture note for the module boundaries and project patterns.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.