Skip to main content

MCP server for Indian pharma regulatory data (CDSCO approvals + NPPA pricing)

Project description

india-rx-mcp

An MCP (Model Context Protocol) server for Indian pharma regulatory data — CDSCO drug approvals and NPPA ceiling-price data — for any MCP-compatible LLM client (Claude Desktop, Cursor, Cline, Continue).

Built by a pharma market analyst, for pharma market analysts.

Why this exists

Multiple MCP servers exist for US pharma (openFDA, Orange Book, ClinicalTrials.gov). None exist for Indian pharma. Indian regulatory data is overwhelmingly scrape-not-API, which is exactly why no one has done it. This server fills the gap.

What it gives you

7 tools that map directly to analyst questions:

Question Tool
"What did Sun Pharma get approved in 2026?" cdsco_sponsor_pipeline *
"What's new in oncology this month?" search_cdsco_approvals
"What's the ceiling price for atorvastatin 10mg?" get_nppa_ceiling_price
"Any recent antibiotic price changes?" list_nppa_price_changes *
"Tell me about the latest CDSCO approval for [drug]" get_cdsco_approval
"What's new in CDSCO approvals?" list_recent_cdsco_approvals
"Which formulations are NPPA-controlled in cardiology?" search_nppa_scheduled_formulations

* denotes a v1 limitation — see Limitations below.

2 browseable resources:

  • cdsco://catalog/approved-drugs — full CDSCO catalog as one document
  • nppa://catalog/scheduled-formulations — full NPPA ceiling-price list

3 pre-built analyst workflow prompts:

  • competitor_briefing(sponsor) — written brief on a company's regulatory footprint
  • therapeutic_area_landscape(therapeutic_area, since_months=12) — landscape view of a TA
  • monthly_market_update() — digest of recent approvals and price changes

Install (Claude Desktop)

Add to your Claude Desktop config (%APPDATA%\Claude\claude_desktop_config.json on Windows, ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "india-rx": {
      "command": "uvx",
      "args": ["india-rx-mcp"]
    }
  }
}

Restart Claude Desktop. First launch will scrape and cache CDSCO + NPPA data in the background (5-10 minutes). After that, queries are <100ms.

See docs/claude-desktop-setup.md for the full setup including PAT-style alternatives.

CLI

india-rx-mcp version       # print version
india-rx-mcp status        # show cache status (counts + last refresh per source)
india-rx-mcp refresh       # force refresh from gov.in
india-rx-mcp refresh --source cdsco   # refresh just CDSCO

Architecture

See docs/architecture.md.

Limitations (v1)

This is v0.1 — first public release. Known gaps you should know about before relying on the data:

  1. CDSCO sponsor data is missing. CDSCO publishes yearly approval PDFs with S.No / Drug Name / Indication / Date only — no sponsor column. So:
    • cdsco_sponsor_pipeline(...) returns empty for CDSCO-sourced data
    • search_cdsco_approvals(sponsor=...) filter won't match CDSCO data
    • Approval.sponsor is None for all CDSCO records
    • Planned for v1.1 (likely by parsing detailed approval letters or alternative CDSCO endpoints)
  2. NPPA data is from the 2022 Compendium of Prices (last published comprehensive compilation). Quarterly WPI revisions since then aren't in v1. Adding WPI-revision notification parsing is planned for v1.2.
  3. list_nppa_price_changes(...) returns empty in v1. The compendium is a snapshot. Price-change tracking requires either comparing successive compendiums or parsing WPI revision notifications — both planned for v1.2.
  4. therapeutic_area on NPPA is best-effort substring match on drug name (NPPA formulations don't carry indication metadata). For richer TA filtering use search_cdsco_approvals(therapeutic_area=...), which has a built-in keyword-expansion map.
  5. Patents, CTRI clinical trials, FDA cross-reference: out of scope for v1.

Roadmap

  • v1.1: CDSCO sponsor data; CTRI clinical trials integration
  • v1.2: WPI revision parsing for live price changes; CDSCO ↔ FDA approval-timing comparison tool
  • v2.0: Indian Patent Office (inPASS) integration; optional hosted multi-tenant version

Contributing

This is a portfolio project but contributions are welcome. Open an issue describing what you want to add before sending a PR.

License

MIT. See LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

india_rx_mcp-0.1.1.tar.gz (2.8 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

india_rx_mcp-0.1.1-py3-none-any.whl (1.3 MB view details)

Uploaded Python 3

File details

Details for the file india_rx_mcp-0.1.1.tar.gz.

File metadata

  • Download URL: india_rx_mcp-0.1.1.tar.gz
  • Upload date:
  • Size: 2.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.14 {"installer":{"name":"uv","version":"0.11.14","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for india_rx_mcp-0.1.1.tar.gz
Algorithm Hash digest
SHA256 18bd84762c403e8efe0ee3616a08edbe502d75893e888c6940522a1205108be5
MD5 6c21129f87e618e00a5e4e664fbe84c4
BLAKE2b-256 52386ca694a51962ab3e4a8b11719499252550411f2b4d64da43e8d4c26b61ba

See more details on using hashes here.

File details

Details for the file india_rx_mcp-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: india_rx_mcp-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 1.3 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.14 {"installer":{"name":"uv","version":"0.11.14","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for india_rx_mcp-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 478dfe4443e240bbd0821f259126aa833fc87bf303b22e0ab00d5fdd4075c753
MD5 862d1e3c988f3aee6041a47bee33c508
BLAKE2b-256 a743abd3887ef41e771e8788cb7e481b520779d47e2f706da12f93012f046415

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page