Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Berlin pedestrian isochrones: streets reachable on foot in N minutes (walk/stroller/wheelchair).
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"isochrone": {
"command": "npx",
"args": [
"-y",
"isochrone-mcp"
]
}
}
}Run this in your terminal
claude mcp add isochrone -- npx -y isochrone-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"isochrone": {
"command": "npx",
"args": [
"-y",
"isochrone-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"isochrone": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"isochrone-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account capan, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.4) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Signoff
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Five gates that make an agent's 'done' provable: run them, read the verdict, audit the record.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Live: [iso.huseyincapan.dev](https://iso.huseyincapan.dev)
Click anywhere on the map and see the street network you can actually reach on foot within 15 minutes — coloured by arrival time, with mobility profiles that account for stairs and unpaved paths.
OSM data → PostGIS + pgRouting → Express → Leaflet.
Every isochrone map I could find answers with a filled polygon. That is wrong unless you are a pigeon: a polygon claims you can reach the middle of a block, cross a rail cutting, walk through a building. On the corner above, the same 15 minutes gives you 107.6 km of reachable streets; the hull drawn around them covers 3.28 km² and claims 30.4 km of street the walk cannot actually reach. This map draws the network.
pgr_drivingDistance walks the street graph from the vertex nearest your click until the time budget runs out, and returns every reachable edge with its arrival time. Those edges are grouped into 10 equal time bands and drawn directly.
Edge cost is length / speed in seconds, computed per request from the selected profile, so a profile is a few numbers rather than a schema change:
| profile | speed | stairs | unpaved |
|---|---|---|---|
walk | 1.4 m/s | half speed | normal |
stroller | 1.2 m/s | impassable | 0.6× |
wheelchair | 0.9 m/s | impassable | impassable |
These factors are estimates, not measurements — see *Known gaps*.
Answer a short questionnaire weighting seven everyday layers (dining, green space, playgrounds, groceries, health, kindergartens, schools) and the whole Berlin map re-ranks to show where *your* weighted 15-minute city actually is, as walk, bike or wheelchair.
The trick is that nothing is routed at question time: 21 full-city reachability surfaces (7 layers × 3 profiles, ~134,000 grid cells each) are precomputed offline, so re-ranking the city is one aggregate query. Stroller is deliberately absent here: its speed factors are uncalibrated estimates and must not be published as if measured.
The isochrone-mcp package lets any MCP client answer reachability questions against this API:
claude mcp add isochrone -- npx -y isochrone-mcp
One tool, reachable_area: origin + minutes + profile, optional target ("can I get there in time?"). Returns a prose summary and a map link, not coordinate soup. Details in mcp/.
52.515,13.400 reaches 13 nodes. Fix is a one-time pgr_connectedComponents table for the vertex lookup to join against.WALK and returns GeoJSON, so the walk profile could be calibrated against it. It has no stroller/wheelchair mode, so those stay unvalidated.Dev setup, deployment, city import and the ops notes live in docs/OPERATIONS.md.