An MCP server giving AI agents access to Indian fintech utilities โ IFSC, PAN, GSTIN, pincodes, mutual fund NAV, UPI VPAs, and INR formatting.
Project description
๐ฎ๐ณ BharatPay MCP
An MCP server that gives any AI agent โ Claude Desktop, Cursor, Windsurf โ instant access to Indian fintech utilities. IFSC bank lookups, PAN/GSTIN validation with checksums, mutual fund NAVs, UPI VPA identification, pincode lookups, and Indian-style INR formatting. Seven tools. Zero auth. Zero cost. Designed to complement Razorpay's official MCP server โ they handle execution, BharatPay handles validation and lookups.
๐ฅ Demo coming soon ยท ๐ฆ Install: pip install -e . from source (PyPI publish in progress)
Why this exists
Razorpay shipped an official MCP server in early 2025 for executing payment operations โ creating orders, capturing payments, refunding. It's excellent.
But every Indian fintech project also needs a layer below that: validation and enrichment. Is this PAN's format correct? Does this GSTIN's mod-36 checksum verify? What bank does this IFSC code belong to? What's the PSP behind user@oksbi? What's today's NAV for Parag Parikh Flexi Cap?
Currently, an AI agent has to either hallucinate these answers or call seven different APIs with seven different auth schemes. BharatPay collapses all of it into a single MCP server an agent can install in 30 seconds.
Position-wise: BharatPay sits next to Razorpay's MCP, not in competition with it. They handle transactions; we handle validation. Use both together for a complete Indian-fintech AI stack.
Demo
Claude Desktop autonomously calling lookup_ifsc for an Indian bank lookup:
What's in the box
| Tool | Input | What it returns |
|---|---|---|
lookup_ifsc |
KKBK0000261 |
Bank, branch, address, MICR/SWIFT, supported rails (NEFT/RTGS/IMPS/UPI). Source: Razorpay's open IFSC API. |
validate_pan |
AABCT3518Q |
Format check, entity type (Individual/Company/HUF/Trust/...) decoded from the 4th character. |
validate_gstin |
29AABCT1332L1ZS |
Format + mod-36 checksum verification, embedded state and PAN extraction. |
lookup_pincode |
302001 |
District, state, all post offices. Source: India Post API. |
get_mutual_fund_nav |
parag parikh flexi cap or 122639 |
Latest NAV from AMFI's daily file. Fuzzy name search or exact code lookup. Cached for 6h. |
validate_upi_vpa |
angelina@oksbi |
PSP identification (Google Pay/PhonePe/Paytm/...) and underlying bank from the handle suffix. |
format_inr |
100000 or 29500 (paise mode) |
โน1,00,000 (Indian comma style) + word form (1 Lakh, 1.5 Crore, etc.). |
Architecture
โโโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโโโโโ
โ AI Agent โ MCP / stdio โ BharatPay MCP โ
โ (Claude / Cursor) โ โโโโโโโโโโโโโโโโโ> โ (this server) โ
โโโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโฌโโโโโโโโโโโโ
โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ โ โ
โโโโโโโโผโโโโโโโ โโโโโโโโโโโโผโโโโโโโโโโ โโโโโโโโโโผโโโโโโโโโ
โ Pure-logic โ โ Live HTTP APIs โ โ Cached file โ
โ validators โ โ (no auth, no cost) โ โ (refreshed 6h)โ
โโโโโโโโโโโโโโโค โโโโโโโโโโโโโโโโโโโโโโค โโโโโโโโโโโโโโโโโโโค
โ PAN โ โ ifsc.razorpay.com โ โ AMFI NAVAll.txt โ
โ GSTIN+mod36 โ โ postalpincode.in โ โ (~6 MB, ~30K โ
โ UPI VPA โ โ โ โ schemes) โ
โ INR format โ โ โ โ โ
โโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโ
Design notes worth calling out:
- Validators are pure functions. PAN, GSTIN, UPI, and INR run entirely offline โ zero network, zero failures from API outages. The mod-36 GSTIN checksum is implemented from the GSTN spec (verified self-consistent: see
tests/test_validators.py::test_gstin_checksum_self_consistent). - Network tools are async. IFSC and pincode lookups use
httpx.AsyncClientso the MCP server can handle parallel tool calls without blocking. - AMFI data is cached, not re-fetched per call. A single 6 MB file covers all ~30,000 Indian mutual fund schemes; refreshing it on every NAV query would be wasteful and slow. Cache TTL: 6 hours.
- Tool descriptions are LLM-tuned. Each tool's docstring is written for the model to read โ explicit input formats, examples, and what it returns. This is what determines whether an agent successfully picks the right tool.
- No data leaves your machine for offline tools. PAN/GSTIN/UPI/INR validation never touches the network. Useful for compliance-sensitive contexts.
Install
Option 1: pip (recommended)
pip install bharatpay-mcp
Then add to ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or the Windows equivalent:
{
"mcpServers": {
"bharatpay": {
"command": "python",
"args": ["-m", "bharatpay_mcp"]
}
}
}
Restart Claude Desktop. Look for the ๐ icon โ bharatpay should be listed.
Option 2: From source
git clone https://github.com/angelina10504/bharatpay-mcp
cd bharatpay-mcp
pip install -e .
For Cursor
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"bharatpay": {
"command": "python",
"args": ["-m", "bharatpay_mcp"]
}
}
}
Try it
Once connected, try these prompts in Claude Desktop:
"Look up IFSC code KKBK0000261 and tell me what payment rails it supports."
"Is
29AAGCB7407Q1ZNa valid GSTIN? If so, what state is the entity registered in?"
"What's today's NAV for Parag Parikh Flexi Cap regular growth?"
"My friend's UPI ID is
priya@oksbiโ which app does she use?"
"Format โน12,00,000 in Indian style and tell me what it would be in paise."
The agent will autonomously pick the right tool. You'll see the tool call and its structured JSON response inline.
Tests
pip install -e ".[dev]"
pytest tests/ -v
17 unit tests cover all offline validators including a self-consistency test for the GSTIN mod-36 checksum.
What's next (V2)
validate_aadhaar(number)โ Verhoeff checksum (offline, no UIDAI API needed)get_holiday_calendar()โ RBI bank holidays (settlement-day awareness)stock_quote(symbol)โ NSE/BSE live quotes forRELIANCE.NS-style tickerstax_slab_calculator(income, regime)โ Old vs new regime estimation- Bundle as
npx @bharatpay/mcpfor zero-install distribution
Open an issue on GitHub if you want any of these prioritized.
A note on "AI-first India"
When Razorpay launched their MCP server, they framed it as "designed for an AI-first world." That framing is right โ but transactions are only half the picture. Half the engineering effort in any Indian fintech goes into validation, enrichment, and lookups that an AI agent can't reliably hallucinate. That's the gap BharatPay fills.
If you're building AI tools for Indian fintech and you find a utility missing, open an issue or send a PR.
License
MIT โ see LICENSE. All upstream APIs (Razorpay IFSC, India Post, AMFI) are themselves free and publicly available under their respective terms.
Built by Angelina Gupta ยท April 2026 ยท For the Razorpay AI Engineer application
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file bharatpay_mcp-0.1.0.tar.gz.
File metadata
- Download URL: bharatpay_mcp-0.1.0.tar.gz
- Upload date:
- Size: 354.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e7caa4283314d8466366d088d1f90c3a586f0ebad2e65b19865f50fdba9a59f2
|
|
| MD5 |
1a5f1dfbbde1f5d381457ca2bcaf0c45
|
|
| BLAKE2b-256 |
7e73e4002a1e21c90ee9151bd2d55a52f8a7ab8b91bd86826c841f1afbbb3d65
|
File details
Details for the file bharatpay_mcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: bharatpay_mcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 18.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f5c9b4725c2ebe292564e1e45585dec5db03c2ddad928d319e5c46073df7a62f
|
|
| MD5 |
e95e3c169acd2f1350995830f3d9f72b
|
|
| BLAKE2b-256 |
01eaf48af637bb1b28381a759b786b37418f5d7bf213b73d4ff33432f2119d55
|