
Security News
Lovable’s OJ Rewrites Vite’s Dev Server in Rust as AI Lowers the Cost of Forking Open Source
Lovable’s OJ rewrites Vite’s dev server in Rust, reducing memory use and preview times as AI lowers the cost of open source reimplementation.
Ground AI agents in open map data. MCP server for Overture Maps — compact answers, no API key. This launcher runs the Python server via `uvx placeroot` under the hood, so `npx placeroot` works out of the box.
Quick start · Tools · Reference · Benchmarks · Website
PlaceRoot grounds AI agents in open map data. It's an MCP server that answers spatial questions — what's nearby, what's in this neighborhood, how do I get there — from Overture Maps open data. No API key, no signup, no vendor platform.
An independent project by vibemapper.
route and isochrone walk an actual street graph built from Overture's transportation segments — not a straight-line guess — anywhere on Earth.find_places(..., within={"minutes": 15, "mode": "walk"}) keeps only results truly inside the street-graph walk/cycle/driveshed — not a radius that guesses at it, and not a second call to intersect a polygon yourself.This npm package is the Node launcher. The server itself is Python, distributed on PyPI; npx placeroot spawns uvx placeroot under the hood and passes through arguments, stdio, and the exit code, so it behaves exactly like running uvx placeroot directly.
Run it straight from PyPI or npm — no install step:
npx placeroot # stdio MCP server
npx placeroot --http # HTTP endpoint at http://127.0.0.1:8321/mcp
claude mcp add placeroot -- npx placeroot
Add to your claude_desktop_config.json:
{
"mcpServers": {
"placeroot": {
"command": "npx",
"args": ["placeroot"]
}
}
}
Same config as above wherever your client keeps its MCP server list. Prefer running the Python server directly? Use "command": "uvx", "args": ["placeroot"]. This package is a thin wrapper around exactly that.
{
"mcpServers": {
"placeroot": {
"command": "npx",
"args": ["placeroot"]
}
}
}
Then ask your agent something spatial:
"What's around downtown Palo Alto?" · "Compare these two neighborhoods for a bike shop." · "Plan my errands: pharmacy, hardware store, post office."
PATH — the launcher shells out to uvx. If it isn't installed, the command exits with install instructions rather than a stack trace. pip install uv works too.If you already use Python tooling, uvx placeroot skips this launcher entirely and is equivalent.
42 tools, grouped into four families — every answer fits in a couple of thousand tokens:
| Family | Tools | Answers questions like |
|---|---|---|
| 🔍 Search & identify | find_places, find_near, geocode, reverse_geocode, place_details, search_categories, warmup_city, … | What cafés are near this point? Coffee near the Eiffel Tower? |
| 📊 Area analysis | summarize_area, compare_areas, neighborhood_verdict, summarize_buildings, land_use_at, … | What's in this neighborhood, should I live here, and how does it differ from that one? |
| 🚴 Routing | route, from_to, isochrone, optimize_route, places_along_route, distance_matrix, travel_time_matrix | How far to walk from A to B? What's reachable in 15 minutes? Best order for 6 stops? |
| 🗺️ Geometry & maps | render_map, simplify_geometry | Show me this result as an interactive map |
It also ships seven workflow prompts (site selection, neighborhood comparison, errand planning, should I live here, get to know my city, verify listing claims, plan area visit) and three attachable resources — and a PLACEROOT_TOOLS setting to load only the tool profiles you need, cutting schema overhead by up to 95%.
📚 Full tool catalog, prompts, resources & configuration → docs/REFERENCE.md
Note: Open data has honest limits: no live traffic, no opening hours, no ratings or photos — what PlaceRoot deliberately doesn't do. For everything else about where things are and what's reachable from them, it answers without a key.
It's the only keyless MCP server doing real graph routing over global open map data — with every tool declaring proper MCP annotations so clients know which calls are read-only before prompting you. Stable GERS ids let agents hold onto places across turns; local caching makes repeat queries answer in milliseconds and keeps working offline; and the whole thing is self-hostable end to end.
How it stacks up against Mapbox MCP and Google Maps MCP: head-to-head benchmarks · token-efficiency numbers.
Full docs, the complete tool reference, and setup guides: placeroot.dev
MIT
FAQs
Ground AI agents in open map data. MCP server for Overture Maps — compact answers, no API key. This launcher runs the Python server via `uvx placeroot` under the hood, so `npx placeroot` works out of the box.
The npm package placeroot receives a total of 38 weekly downloads. As such, placeroot popularity was classified as not popular.
We found that placeroot demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.

Security News
Lovable’s OJ rewrites Vite’s dev server in Rust, reducing memory use and preview times as AI lowers the cost of open source reimplementation.

Security News
It has been one year since Shai-Hulud made its first appearance on npm.

Research
/Security News
Operators behind PolinRider used a compromised GitHub account to plant malware in four development versions of a Packagist package with 700,000+ downloads.