# io.github.sathya-sankaran/bharatlas-mcp (npm · bharatlas-mcp)

Query India's open geo data, and author collect maps: register a link, moderate, publish.

- Trust score: 61/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-21

## Components

- npm · `bharatlas-mcp`: 61/100 (this document), [markdown](https://verifymcp.io/servers/sathya-sankaran-bharatlas-mcp/bharatlas-mcp.md), [page](https://verifymcp.io/servers/sathya-sankaran-bharatlas-mcp/bharatlas-mcp)

## Channel facts

- Registry: `npm`
- Package: `bharatlas-mcp`
- Version: `1.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-21.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 95 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3158 tokens (~185/item across 17 items; 17 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 67% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add sathya-sankaran-bharatlas-mcp -- npx -y bharatlas-mcp
```

### Codex

```bash
codex mcp add sathya-sankaran-bharatlas-mcp -- npx -y bharatlas-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sathya-sankaran-bharatlas-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "bharatlas-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sathya-sankaran-bharatlas-mcp --command npx --arg -y --arg bharatlas-mcp
```

### Hermes

```yaml
mcp_servers:
  sathya-sankaran-bharatlas-mcp:
    command: "npx"
    args: ["-y", "bharatlas-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "sathya-sankaran-bharatlas-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "bharatlas-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-21 (score 61, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-08-20 (score 46)

First indexed and scored.

## MCP tools (17)

### `list_layers` (~204 tokens)

List available geo layers. Use to discover what data bharatlas has. Returns layer IDs, names, row counts, categories, and download formats. Filter by category (boundaries, city-wards, environment, water, agriculture, transport, etc.), admin level (state, district, block, village, etc.), source, or text search.

Input parameters:

- `category` (string): Filter by category: boundaries, city-wards, people, environment, water, agriculture, transport, infrastructure, health-edu
- `level` (string): Filter by admin level: state, district, subdistrict, block, village, etc.
- `limit` (number): Max results (default 20)
- `offset` (number): Skip N results for pagination
- `q` (string): Text search across layer IDs, sources, and descriptions
- `source` (string): Filter by data source: LGD, SOI, Bhuvan, OpenCity, DataMeet, etc.

### `get_layer_schema` (~73 tokens)

Get column names, types, and sample values for a layer. Use BEFORE querying to discover what columns exist and what values they contain. Essential for knowing the right column names for filters.

Input parameters:

- `layer_id` (string, required): Layer ID (e.g. lgd_states, airports, soi_forests, wards_chennai)

### `query_layer` (~225 tokens)

Query a layer's data with filters and grouping. Reads the parquet file at runtime. Supports: select specific columns, filter by column values, group by a column to get counts. Use get_layer_schema first to discover column names. Examples: 'airports in Karnataka' -> where: {state: 'KA'}, 'forest types' -> group_by: 'type', 'health facilities in Bihar' -> where: {state: 'BIHAR'}, select: ['name', 'type'].

Input parameters:

- `group_by` (string): Column to group by. Returns {value: count} instead of rows.
- `include_centroid` (boolean): Include _lat/_lng centroid coordinates (defaults to true). Set false to exclude.
- `layer_id` (string, required): Layer ID to query
- `limit` (number): Max rows (default 100, max 1000)
- `select` (array): Column names to return. Omit for all non-geometry columns.
- `where` (object): Filter conditions as {column: value} pairs. Case-insensitive matching.

### `locate` (~129 tokens)

Given a latitude/longitude, find which administrative boundaries, zones, and regions contain that point. Returns state, district, subdistrict, block, parliament/assembly constituency, pincode, seismic zone, high court jurisdiction, and more. The 'where am I?' tool. Also accepts specific layer IDs to check.

Input parameters:

- `lat` (number, required): Latitude (6 to 38, India bounding box)
- `layers` (array): Specific layer IDs to check (default: 12 essential layers covering all admin levels + zones)
- `lng` (number, required): Longitude (68 to 98, India bounding box)

### `nearby` (~167 tokens)

Find features from a layer that are near a given point. Samples a grid of points around the center and checks which hit the target layer via locate. Generic: works for any layer type (polygons, points, lines) without needing coordinate columns. Example: 'reservoirs near Bengaluru' -> layer_id: 'wris_reservoirs', lat: 12.97, lng: 77.59, radius_km: 50.

Input parameters:

- `lat` (number, required): Center point latitude
- `layer_id` (string, required): Layer to search for nearby features
- `limit` (number): Max results (default 20)
- `lng` (number, required): Center point longitude
- `radius_km` (number): Search radius in kilometres (default 25, max 200)

### `list_categories` (~16 tokens)

List all data categories with layer counts.

### `get_layer_detail` (~56 tokens)

Get full metadata for a single layer: download URLs (parquet, pmtiles, geojson, kml, shapefile), attribution, license, feature count, and level metadata.

Input parameters:

- `layer_id` (string, required): Layer ID

### `list_submissions` (~90 tokens)

List community-submitted geo layers. These are user-contributed datasets under open licenses. Filter by category or search by name.

Input parameters:

- `category` (string): Filter by category
- `limit` (number): Max results (default 20)
- `offset` (number): Pagination offset
- `q` (string): Search name and description
- `sort` (string): Sort order (default: recent)

### `register_map` (~118 tokens)

Register a collect map so this server can act on it. Paste the whole share link (e.g. https://collect.bharatlas.com/c/<id>/admin#<token>). The token in the #fragment sets your scope: admin = full control, collect = add points, view = read published. New maps are created online at collect.bharatlas.com first (no account or key needed); this registers one you already made.

Input parameters:

- `link` (string, required): a collect.bharatlas.com share link with the token in the #fragment

### `list_my_maps` (~26 tokens)

List the collect maps you have registered here (local store), each with its scope.

### `get_map` (~43 tokens)

A collect map's metadata + record counts, plus a link to open it in collect. Any registered scope.

Input parameters:

- `id` (string, required): the map (collection) id

### `get_records` (~69 tokens)

A collect map's records as a GeoJSON FeatureCollection — for reading, analysis, or backup/export. view and collect scope return published points; admin can also read pending/rejected via status.

Input parameters:

- `id` (string, required)
- `status` (string): admin only: pending | published | rejected

### `moderate_record` (~62 tokens)

Approve or reject one pending point (needs the admin link). Pass the map id it belongs to.

Input parameters:

- `id` (string, required): the map (collection) id
- `reason` (string)
- `record_id` (string, required)
- `status` (required)

### `import_points` (~96 tokens)

Bulk-import points you already hold into a collect map (needs the admin link). NOT for synthetic data. Requires a named source + rights confirmation; each row lands with that source as its provenance.

Input parameters:

- `id` (string, required)
- `records` (array, required): GeoJSON-like {geometry, properties}
- `rights_confirmed` (boolean, required): you have the right to publish this under the map's licence
- `source` (string, required)

### `edit_map` (~102 tokens)

Edit a collect map's settings: name/description/purpose/category/data_year/basemap (needs the admin link). Licence can only change while the map has no records.

Input parameters:

- `basemap` (string)
- `category` (string)
- `data_year` (integer|null)
- `description` (string)
- `id` (string, required)
- `license` (string)
- `name` (string)
- `purpose` (string)

### `publish` (~50 tokens)

Bake a collect map's approved points into a bharatlas catalog submission (needs the admin link). Once published it is queryable via list_submissions / query_layer / locate above.

Input parameters:

- `id` (string, required)

### `create_map` (~184 tokens)

Optional: create a collect map programmatically. Most maps are made online at collect.bharatlas.com (no key needed) — prefer that and register_map the link. This path needs COLLECT_API_KEY (the request-only anti-abuse gate) and auto-registers the new admin link.

Input parameters:

- `basemap`
- `category` (string)
- `data_year` (integer)
- `description` (string)
- `fields` (array, required): the form for each record (see collect.bharatlas.com/schema/v1.json)
- `geometry` (array, required): what contributors may add
- `license` (string): open licence id; default CC-BY-4.0
- `moderation` (boolean): default true — points wait for approval
- `name` (string, required): 3-120 chars
- `purpose` (string, required): shown to contributors

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/sathya-sankaran-bharatlas-mcp/bharatlas-mcp#diagnostics

## Score history

- 2026-08-21: 61
- 2026-08-20: 46

## Links

- npm package: https://www.npmjs.com/package/bharatlas-mcp
- Socket report: https://socket.dev/npm/package/bharatlas-mcp
- Changelog RSS feed: https://verifymcp.io/servers/sathya-sankaran-bharatlas-mcp/bharatlas-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/sathya-sankaran-bharatlas-mcp/bharatlas-mcp.json
- HTML version of this page: https://verifymcp.io/servers/sathya-sankaran-bharatlas-mcp/bharatlas-mcp