bhoonidhi-mcp

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).

Tools

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):

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: