Skip to main content

MCP server exposing Indian financial and government APIs — GSTIN, IFSC, PAN, UPI, pincode, HSN/SAC — for AI agents. Zero auth. Offline-first.

Project description

mcp-india-stack

PyPI version License: MIT CI

MCP server exposing Indian financial and government APIs for AI agents. Zero auth. Offline-first.

Install

pip install mcp-india-stack

Run

mcp-india-stack

or

python -m mcp_india_stack

Tools

Lookup Tools

Validation Tools

Tax Calculators (FY2025-26)

Additional Tools

Prompt Workflows

Resources

  • india://status — Version, DB connectivity, and runtime flags
  • india://changelog — Structured changelog resource

Data Freshness

Datasets are bundled with the package for offline-first operation. An optional auto-update mechanism fetches the latest versions from jsDelivr CDN in the background.

  • Auto-update is non-blocking — stale data triggers a background refresh; the current request uses existing data.
  • Opt out — set MCP_INDIA_STACK_NO_AUTO_UPDATE=1 environment variable to disable all update checks.
  • Manual refresh — run mcp-india-stack --refresh-all to synchronously refresh all datasets from CDN.
  • Cache location — platform-specific via platformdirs (e.g., ~/.cache/mcp-india-stack on Linux).

Bundled Data Size

This package bundles static datasets for offline-first workflows.

  • IFSC dataset (Razorpay releases)
  • India pincode dataset (GeoNames IN postal dump, CC-BY)
  • HSN/SAC master (GST tutorial workbook transformed to CSV)
  • State codes and curated UPI handles

Expected install footprint includes approximately 10-11MB compressed static data.

Limitations

  • GSTIN validation checks format and checksum, not active GSTN status.
  • PAN validation is structural; PAN check character is not publicly algorithmic.
  • HSN/SAC rates are static references and may vary by conditions/notifications.
  • All tax calculations are estimates for FY2025-26. Actual liability may differ — consult a CA.
  • Aadhaar, Voter ID, DL, Passport, CIN, DIN validators are format-only — they do not verify active status with issuing authorities.

Legal and Attribution

See NOTICES for dataset attribution and licensing details.

Launch Notes

This repository is release-ready for GitHub launch with:

  • 0.3.0 package metadata and changelog coverage
  • A complete MCP server-card under docs/.well-known/mcp/server-card.json
  • Local setup and publishing steps in SETUP.md
  • Contribution guidance and versioning policy in CONTRIBUTING.md

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

mcp_india_stack-0.3.0.tar.gz (10.1 MB view details)

Uploaded Source

Built Distribution

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

mcp_india_stack-0.3.0-py3-none-any.whl (10.1 MB view details)

Uploaded Python 3

File details

Details for the file mcp_india_stack-0.3.0.tar.gz.

File metadata

  • Download URL: mcp_india_stack-0.3.0.tar.gz
  • Upload date:
  • Size: 10.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for mcp_india_stack-0.3.0.tar.gz
Algorithm Hash digest
SHA256 0e21237c50c5afd6c22ff6c65e30469a37a1796384b61d7dde2847fd5cf45258
MD5 d29d1751758a2364f57d02c607dfe1e7
BLAKE2b-256 47d00966b260579bd09f3e04357be6d90865957b9ddefa2e0b1db24b73e806af

See more details on using hashes here.

Provenance

The following attestation bundles were made for mcp_india_stack-0.3.0.tar.gz:

Publisher: publish.yml on rehan1020/MCP-India-Stack

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file mcp_india_stack-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: mcp_india_stack-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 10.1 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for mcp_india_stack-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b90328104e826d33fcc80fc19e3102644277b3e5129e5c716ace3fa38da3aac4
MD5 9cce6d30a8ade89c06c386f0ac041db0
BLAKE2b-256 0ce1476ce38c3f509ace18a181df492a45e74ea1f89a3ca4888eda2d63d8ec26

See more details on using hashes here.

Provenance

The following attestation bundles were made for mcp_india_stack-0.3.0-py3-none-any.whl:

Publisher: publish.yml on rehan1020/MCP-India-Stack

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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