geo_analyze
shallowio.github.robit-man/mapsource · Verify this server
Answer a geometric question without moving the geometry through your context. Operands may be GeoJSON, a [lon, lat] pair, an Overpass result, or a result handle from geo_query or a previous analysis, and a large answer comes back as a handle in turn, so results chain: query an area, buffer a route, intersect the two, measure what is left. Operations are buffer, centroid, bbox, area, length, distance, intersect, union, difference, contains, intersects, nearest, simplify and convex. Overlay operations need areas, and say so rather than failing obscurely if you hand them a point. Two shapes that do not overlap return null, not an empty shape, so "they do not intersect" stays distinguishable from "they intersect in nothing". Set operation to pipeline to run several steps server-side in one call: each step names an op and args, any argument may reference an earlier step as $id, and only the step you ask for comes back. That is how a multi-part question stays one request — find the hospitals, find what is reachable in twenty minutes, keep the overlap, rank by distance — with the intermediate geometry never leaving the server. The whole graph is validated before any of it runs, and estimateOnly reports the cost first. Requires a subscription key.
1 trials · measured 27 days ago
geo_analyze scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against io.github.robit-man/mapsource, measured 11 Sept 2026 under methodology v0.2.0. Every measured component scored 100.
Component breakdown
| Component | Weight | Value |
|---|---|---|
| Reliability | 35% | not applicable |
| Schema integrity | 25% | 100.0 |
| Failure behaviour | 15% | not applicable |
| Latency | 15% | not applicable |
| Concurrency | 10% | not applicable |
Tool details
- Transport
- remote
- Credential class
- self-provisionable
- Input schema
- not declared
- Output schema
- not declared
- Side-effect classification
- unclassified
Score history
| Day | Score | Tier | Methodology |
|---|---|---|---|
| 2026-09-11 | 100.0 | shallow | v0.2.0 |
Probe evidence
| Probe | Outcomes |
|---|---|
| schema_integrity | pass: 1 |
Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.
Embed this score
Available for every tool, scored or not — not a verification perk. Always links back to this page.
[](https://vouch.tools/tools/98f5ec25-2530-4965-8f8d-80893d791347)