Lightweight open-source visualiser for India admin boundaries — pick a layer, vi
Lightweight open-source visualiser for India admin boundaries — pick a layer, view, download parquet
active Production-safe Score 93/100 http no auth
At a glance
| Endpoint | https://bharatlas.com/mcp |
|---|---|
| Source | https://github.com/urbanmorph/geodata |
| Transport | http |
| Tools | 8 |
| Auth | none |
| First seen | 2026-08-18 20:53:40 |
| Last checked | 2026-11-17 21:54:06 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 98% |
| Latency p50 / p95 | 390 / 709 ms |
| Last successful check | 2026-11-17 21:54:06 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (8)
list_layers— List available geo layers. Use to discover what data bharatlas has. Returns layer IDs, names, row counts, categories, and download formats.get_layer_schema— Get column names, types, and sample values for a layer. Use BEFORE querying to discover what columns exist and what values they contain. Essquery_layer— Query a layer's data with filters and grouping. Reads the parquet file at runtime. Supports: select specific columns, filter by column valuelocate— Given a latitude/longitude, find which administrative boundaries, zones, and regions contain that point. Returns state, district, subdistricnearby— Find features from a layer that are near a given point, nearest first, within radius_km. Reads the layer's parquet bounding boxes and rankslist_categories— List all data categories with layer counts.get_layer_detail— Get full metadata for a single layer: download URLs (parquet, pmtiles, geojson, kml, shapefile), attribution, license, feature count, and lelist_submissions— List community-submitted geo layers. These are user-contributed datasets under open licenses. Filter by category or search by name.
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:54:06 | ✓ | ✓ | 312 ms | 90 | active |
| 2026-11-17 21:38:58 | ✓ | ✓ | 421 ms | 90 | active |
| 2026-11-17 21:23:45 | ✓ | ✓ | 430 ms | 90 | active |
| 2026-11-17 21:08:29 | ✓ | ✓ | 527 ms | 90 | active |
| 2026-11-17 20:53:26 | ✓ | ✓ | 308 ms | 90 | active |
| 2026-11-17 20:38:26 | ✓ | ✓ | 266 ms | 94 | active |
| 2026-11-17 20:23:22 | ✓ | ✓ | 558 ms | 90 | active |
| 2026-11-17 20:08:14 | ✓ | ✓ | 525 ms | 90 | active |
| 2026-11-17 19:52:23 | ✓ | ✓ | 459 ms | 90 | active |
| 2026-11-17 19:37:18 | ✓ | ✓ | 518 ms | 90 | active |
| 2026-11-17 19:22:04 | ✓ | ✓ | 483 ms | 90 | active |
| 2026-11-17 19:06:52 | ✓ | ✓ | 470 ms | 90 | active |
| 2026-11-17 18:51:39 | ✓ | ✓ | 492 ms | 90 | active |
| 2026-11-17 18:36:33 | ✓ | ✓ | 410 ms | 90 | active |
| 2026-11-17 18:21:29 | ✓ | ✓ | 397 ms | 90 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://bharatlas.com/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/bharatlas-com-mcp # JSON