Skip to main content
Glama

bhoonidhi-mcp

PyPI MCP Registry License: MIT

An MCP server that lets an AI agent search, save, download, and cart satellite scenes from ISRO's Bhoonidhi Browse & Order portal (NRSC) in natural language. An agent can turn a sentence like "Sentinel-2 over Shillong last January" into a real search against the live portal, see honestly what is available to download, save a search to reuse later, preview what a download would fetch, and — once logged in — download open-access scenes or stage them to the cart.

It is a thin adapter over the bhoonidhi-downloader SDK — the same client the bhd CLI uses — so no portal logic is duplicated.

Status

Search and save with no login; download and cart with one. The tools reach the full archive of 41 satellite missions and 79 sensors, search the live portal, and save searches to reusable slugs — all without credentials. Downloading open-access scenes and staging scenes to the Bhoonidhi cart need a login, done out of band with bhd auth login (the server reuses that session).

Related MCP server: Google Earth Engine MCP Server

Tools

Tool

What it does

Login

list_archive

The vocabulary of satellites, sensors, and search tokens the portal supports, live from Bhoonidhi.

no

resolve_location

Turns a place name ("Loktak Lake") into a centroid and bounding box. Rejects inputs that are not place names.

no

search_scenes

Natural-language scene search over an area and date range. Resolves a casual satellite name to exact tokens, and reports each scene's availability (Ready / Archived / OnOrder / Priced). Stateless — nothing is saved.

no

preview_download

A dry run: shows what downloading the results would fetch, and what would be skipped, before anything is downloaded.

no

save_query

Persists a search (same arguments as search_scenes) to a reusable slug, so it can be downloaded or staged to the cart later.

no

list_queries

Lists saved queries as compact summaries: slug, name, date range, satellites, area, and availability.

no

show_query

Returns one saved query by slug, with its scenes.

no

remove_query

Deletes a saved query by slug.

no

auth_status

Reports whether a login is configured. Never handles a password or token.

no

download_query

Downloads a saved query's open-access scenes in the background, to a fixed server-configured root. Returns a job_id at once.

yes

download_status

One-off check of a background download by job_id: bytes downloaded, transfer rate, percent when the size is known, and per-scene detail.

no

download_wait

Blocks until a download finishes (or a capped timeout), then reports — the efficient primitive a background watcher loops on.

no

cart_add

Stages a saved query's scenes to the cart (routes each to ready / on-order / priced).

yes

cart_list

Lists scenes currently staged in the cart.

yes

cart_remove

Removes scenes from the cart.

yes

Availability matters: an OpenData scene is not necessarily staged for download. search_scenes and preview_download distinguish Ready (fetch it now) from Archived (open data, but may need a request on the portal first), so an agent does not over-promise.

Downloads run in the background, independent of the conversation: download_query returns a job_id at once and the transfer proceeds on its own. Check progress once with download_status — it reports bytes downloaded, a transfer rate, and a percent once the size is known — or follow a job to completion with download_wait, which blocks until it finishes (or a capped timeout) so an agent can delegate a background watcher and keep the conversation free instead of sleep-looping. A job lives only as long as the server process, so once a download proves large the status recommends running a standalone bhd query download <slug> command you own instead.

Install

The server is a Python package with a console entry point, bhoonidhi-mcp. The simplest way to run it is with uv — uvx fetches, builds, and launches it straight from the source, no clone or virtualenv needed:

uvx --from git+https://github.com/geovicco-dev/bhoonidhi-mcp bhoonidhi-mcp

The first run builds from source; later runs start from cache. The server speaks stdio and is launched by an MCP client — you point the client at that command.

Prefer a local checkout (for development)? Clone and uv sync, then use .venv/bin/bhoonidhi-mcp as the command instead:

git clone https://github.com/geovicco-dev/bhoonidhi-mcp
cd bhoonidhi-mcp
uv sync

Connecting a client

Every MCP client needs the same thing: the command to launch. Point it at uvx with the source and entry point as arguments.

Claude Desktop / Claude Code

claude_desktop_config.json (or claude mcp add):

{
  "mcpServers": {
    "bhoonidhi": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/geovicco-dev/bhoonidhi-mcp", "bhoonidhi-mcp"]
    }
  }
}

OpenCode

~/.config/opencode/opencode.json:

{
  "mcp": {
    "bhoonidhi": {
      "type": "local",
      "command": ["uvx", "--from", "git+https://github.com/geovicco-dev/bhoonidhi-mcp", "bhoonidhi-mcp"],
      "enabled": true
    }
  }
}

MCP Inspector (to try it without an agent)

npx @modelcontextprotocol/inspector uvx --from git+https://github.com/geovicco-dev/bhoonidhi-mcp bhoonidhi-mcp

Example

Ask an agent, in plain language:

"What Sentinel-2 scenes are over Shillong in January 2024, and how many can I actually download?"

The agent calls resolve_location for Shillong, then search_scenes, and answers from the result — for example, that all scenes are Archived (open data, but each may need a request on the portal before it will download), rather than claiming they are all ready.

Prompts to try

Copy these into any connected agent to get a feel for what it can do.

Discover the archive

  • "What satellites and sensors does Bhoonidhi have?"

  • "Which sensors does ResourceSat-2A carry, and at what resolution?"

  • "Does Bhoonidhi have any radar satellites?"

Search for scenes

  • "Find Sentinel-2 scenes over Shillong in January 2024."

  • "Show me Cartosat imagery within 20 km of Bengaluru in the first half of 2024."

  • "Any Sentinel-1 scenes over the Sundarbans in March 2024?"

  • "What Landsat-8 imagery covers Kaziranga National Park last winter?"

  • "Find MODIS scenes over the Rann of Kutch in December 2023."

Check what's available to download

  • "Of those Sentinel-2 scenes, how many can I actually download right now?"

  • "Which of these need to be ordered or paid for?"

Preview a download

  • "Preview what downloading those scenes would fetch."

Save a search to reuse

  • "Save that Sentinel-2 search so I can download it later."

  • "List my saved searches."

  • "Show me what's in the search I saved as <slug>."

  • "Delete the saved search <slug>."

Download and cart (needs a login — see below)

  • "Am I logged in to Bhoonidhi?"

  • "Download the open-data scenes from my saved search <slug>."

  • "How's that download going?"

  • "Download <slug> and let me know when it's done — I'll keep working."

  • "Add the priced scenes from <slug> to my cart."

  • "What's in my cart this week?"

Login (for downloads and cart)

Search, saved queries, and previews need no credentials. Downloading scenes and staging them to the cart do. Log in once, out of band — the server reuses the same session the bhd CLI writes:

bhd auth login

The MCP server never takes a username or password as a tool argument, and auth_status never returns your token. For a headless setup with no interactive login, you can instead set BHOONIDHI_USERNAME / BHOONIDHI_PASSWORD in the server's environment; the server reads them only to establish a session.

Configuration

Set as environment variables (all optional):

Variable

Default

Purpose

BHOONIDHI_MCP_GEOCODER_USER_AGENT

bhoonidhi-mcp/0.3

User-Agent sent to Nominatim (its usage policy asks for a descriptive one).

BHOONIDHI_MCP_FUZZY_THRESHOLD

88

Score (0–100) a satellite-name match must clear to be confident; below it, candidates are returned for the agent to confirm.

BHOONIDHI_MCP_MAX_RESULTS

50

Maximum scenes returned inline by search_scenes.

BHOONIDHI_MCP_DOWNLOAD_ROOT

~/Downloads

Allow-listed root every download writes under, as <root>/<slug>/. The agent cannot choose an arbitrary path.

BHOONIDHI_MCP_DOWNLOAD_PARALLEL

4

Parallel download workers.

BHOONIDHI_MCP_LARGE_DOWNLOAD_MB

500

Once a download's live byte total (or known size) passes this, the status flags it large and steers the agent to hand off or run a standalone command.

BHOONIDHI_USERNAME / BHOONIDHI_PASSWORD

(unset)

Optional headless login. Prefer bhd auth login; fill these out of band, never commit them.

Data usage and attribution

The imagery reached through this server belongs to ISRO/NRSC and is governed by the Bhoonidhi EULA, not by this project's MIT license — that license covers the code here, nothing else. What the EULA asks of you:

  • Use your own account. Downloads and cart actions authenticate with your own Bhoonidhi login, established out of band. The server never takes a password as a tool argument and never shares or bypasses a session.

  • Credit the source. Anything you publish from this data must carry the caption ISRO-IRS.

  • Don't resell the raw data. Scenes the portal marks as open data are free to use, publish, and build on. The original products just can't be redistributed commercially in their original form — derived and value-added products are fine.

  • Priced and on-order scenes go through the portal. This server never bypasses payment: priced and on-order scenes are only staged to the cart, and you complete any order and payment on Bhoonidhi.

Development

uv sync
uv run pytest        # test suite
uv run ruff check .  # lint

License

MIT — see LICENSE.

Available Tools

15 tools
auth_statusA

Report whether a Bhoonidhi login is configured for downloads and cart.

Never asks for or returns a password or token. If credentials are set in the server's environment (BHOONIDHI_USERNAME / BHOONIDHI_PASSWORD) it establishes the session so the answer matches what a download or cart action would find. Returns authenticated=True with the username when a usable session exists, or authenticated=False with guidance to log in ('bhd auth login' out of band, or set those environment variables). Call this before download or cart actions to tell the user if a login is needed.

Inputs: no named parameters.

cart_addA

Stage a saved query's scenes to the Bhoonidhi cart.

Give the slug from save_query or list_queries. Each scene is routed to the cart its access type needs (ready / on-order / priced); select narrows to specific scenes (1-based indices or scene IDs). Needs a login (see auth_status). Use this for on-order and priced scenes; priced ones still need purchasing on the portal afterwards. Returns counts of what was staged and what failed.

Inputs: slug (required), select.

cart_listA

List scenes currently staged in the Bhoonidhi cart.

Cart items are filed by the date they were added; with no window this shows today only, so pass since/until (ISO dates, e.g. "2026-08-10") or last (e.g. "1 week") to widen it. filter_by limits to a state: ready, archived, onorder, or priced. Needs a login (see auth_status).

Inputs: last, since, until, filter_by.

cart_removeA

Remove scenes from the Bhoonidhi cart.

Two ways to address rows: pass slug to index a saved query's scenes, or omit it and let select index the merged cart itself (the same row numbers cart_list shows under the same since/until/last/filter_by window). Needs a login (see auth_status).

Inputs: last, slug, since, until, +2 more.

download_queryA

Download a saved query's open-access scenes in the background.

Give the slug from save_query or list_queries. Downloads run to a fixed, server-configured root (BHOONIDHI_MCP_DOWNLOAD_ROOT, default ~/Downloads), under a per-slug folder — you cannot choose an arbitrary path. select narrows to specific scenes (1-based indices or full scene IDs); omit it for the whole query. force re-downloads files already present.

Needs a login (see auth_status). Priced and on-order scenes are skipped — stage those with cart_add instead. Returns immediately with a job_id: the download runs on its own and does NOT depend on this conversation, so never block by sleeping and re-polling. To follow it hands-free, delegate a background watcher that loops download_wait on the job_id and reports back, keeping you free to keep talking; the result's 'handoff' note says so. File sizes are unknown until each transfer starts (the portal reveals them only then); once a download proves large, download_status/download_wait flag it and 'large_download' offers a standalone command that outlives this session. Interrupted downloads restart from scratch (no resume support).

Inputs: slug (required), force, select.

download_statusA

Check a background download started by download_query (one-off).

Give the job_id from download_query. Returns the live state: running (with bytes_downloaded, mb_downloaded, rate_mb_s, percent when the total size is known, and per-scene detail), completed (with per-scene outcomes), or failed (with the error). Use this for a single progress check. To follow a job to completion without tying up the conversation, use download_wait from a delegated watcher instead. Jobs exist only while the server runs; an unknown id returns status="not_found".

Inputs: job_id (required).

download_waitA

Wait for a background download to finish, then report — for a watcher.

Give the job_id from download_query. Blocks inside the server and returns as soon as the download completes or fails, or after timeout_s (capped at 120s) with the latest progress if still running. This is the efficient way to follow a job: a delegated background watcher calls it in a loop and stops when status is "completed" or "failed", so the main conversation is never blocked on sleeps. Prefer this over repeated sleep+download_status. An unknown id returns status="not_found".

Inputs: job_id (required), timeout_s.

list_archiveA

List every satellite and sensor the Bhoonidhi portal supports.

Returns the vocabulary of valid satellites, sensors, and exact search tokens, with each product's resolution and date coverage. Call this to discover what can be searched. Set refresh=True to bypass the local cache.

Inputs: refresh.

list_queriesA

List every saved query as compact summaries.

Returns each saved query's slug, name, date range, satellites, area of interest, scene count, and a plain-English availability summary — but not the full scene lists (call show_query for one query's scenes). Use this to find the slug for a query the user saved earlier.

Inputs: no named parameters.

preview_downloadA

Dry-run a download for a search: show what would be fetched, no login.

Takes the same arguments as search_scenes, plus out_dir (where files would go) and force (preview re-downloading files already present). It runs the search and predicts, per scene, what a real download would do: would_download (staged, ready), may_404 (open data but archived — attempted but may fail until requested on the portal), already_here / already_elsewhere (a matching file exists), or skipped_on_order / skipped_priced (needs the portal).

Use this before telling a user to download, so they know how many scenes are actually fetchable. Nothing is downloaded and no login is used. File sizes are not known until a download starts (the portal exposes them only in the download response headers), and interrupted downloads cannot be resumed — both are stated in the result's disclaimers.

Inputs: end_date (required), satellite (required), start_date (required), lat, +10 more.

remove_queryA

Delete a saved query by slug.

Give the slug from save_query or list_queries. Removes the saved query from disk; the scenes themselves are unaffected. Returns status="not_found" if no query has that slug.

Inputs: slug (required).

resolve_locationA

Resolve a place name to a centroid and bounding box.

Turns a place like "Shillong" or "Loktak Lake" into latitude/longitude and a bounding box (minx, miny, maxx, maxy) that search_scenes can use as its area of interest. Returns found=False when the place can't be resolved.

Inputs: name (required).

save_queryA

Persist a search as a saved query and return a reusable slug.

Takes the same arguments as search_scenes, plus an optional name and description. Unlike search_scenes (which is stateless and leaves nothing behind), this saves the search on the portal so it can be acted on later: the returned slug is what downloading and cart staging key off. Call this once the user has confirmed a search returns the scenes they want, then hand the slug to the bhd CLI (download / cart) until those actions land in-server.

Returns status="ok" with the slug and the shaped saved query. If the satellite is ambiguous or the request is invalid, returns the same status="ambiguous_satellite" / "invalid_request" shapes as search_scenes, and saves nothing.

Inputs: end_date (required), satellite (required), start_date (required), lat, +10 more.

search_scenesA

Search Bhoonidhi scenes for a satellite over an area and date range.

The satellite may be a casual name ("Sentinel-2", "cartosat"); it is matched to the portal's exact tokens, and a constellation expands to all its platforms. Dates are ISO (YYYY-MM-DD). Give the area either as a bounding box (minx/maxx/miny/maxy) or a point with radius (lat/lon/radius_km) — typically from resolve_location. sensor narrows to one sensor on the matched satellite(s) (e.g. "SSAR", "LISS3"); product further narrows to one product under that sensor (e.g. "GCOV", "L2C-Chlorophyll") — see list_archive for the exact sensor/product names each satellite carries. The search is stateless and needs no login.

If the satellite name is ambiguous, returns status="ambiguous_satellite" with candidate names instead of guessing.

Each scene carries an "availability": Ready (downloadable now), Archived (open data but may need a portal request first), OnOrder (must be requested), or Priced (must be purchased). The result includes a plain-English "summary" of these counts and a "how_to_act" block. Tell the user clearly when scenes are Archived, OnOrder, or Priced and what each needs. This search is stateless: to act on these scenes, call save_query with the same arguments to persist them and get a , then download_query (open data) or cart_add (on-order / priced) on that slug — both need a login (see auth_status). Downloads cannot be resumed if interrupted (the portal has no range support).

Inputs: end_date (required), satellite (required), start_date (required), lat, +8 more.

show_queryA

Return one saved query by slug, with its scenes.

Give the slug from save_query or list_queries. Returns the full saved query: its selections, area of interest, date range, and shaped scenes with availability. Returns status="not_found" if no query has that slug.

Inputs: slug (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 15 tools

    Disambiguation5/5

    Each tool targets a distinct action or resource: search is separated from preview, save, download, and cart operations, and download_status vs download_wait are clearly one-off vs watcher. Even where arguments overlap, the descriptions draw explicit boundaries.

    Naming Consistency3/5

    Most query tools follow verb_noun (remove_query, search_scenes, list_queries), but cart_* uses noun-verb order (cart_add, cart_list) and auth_status/download_status/download_wait are noun-phrase style. Everything is snake_case and readable, but the naming pattern is mixed rather than uniform.

    Tool Count5/5

    15 tools is within the ideal range, and each tool covers a distinct stage of the archive-to-download/cart workflow. There is no apparent redundancy or padding.

    Completeness4/5

    The set covers discovery, geocoding, search, dry-run preview, saved-query lifecycle, auth status, download execution/monitoring, and cart management. Minor gaps like no in-server edit of saved queries, no active-download listing, and no direct archival request action are workarounds via the portal or CLI.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers