About Eco Policy MCP
Eco Policy MCP is an MCP server for Indian financial data and calculations, intended for MCP clients that need tax, mutual-fund, RBI-rate, or NSE-market information. Successful responses include source, date, and reference details to support traceability.
Key features
- 01GST breakdown, extraction, and tax calculations
- 02Estimate and compare income-tax regimes
- 03Find fund NAVs, history, and returns
- 04Retrieve RBI rates and NSE market data
- 05Include provenance in successful responses
Use cases
- 01Break down GST invoice amounts
- 02Compare estimates for income-tax regimes
- 03Review fund NAVs and simulate SIPs
- 04Check RBI rates or NSE market data
MCP support
The server exposes tools for Indian GST, income tax, mutual funds, RBI, and NSE data, along with resources and prompts to MCP clients. Successful responses include source, date, and reference details.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
17Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| amount | number | Yes | Taxable base amount in INR. |
| intra_state | boolean | Yes | True if supplier and place of supply are in the same state. |
| rate_percent | number | Yes | GST slab rate - one of 0.25, 3, 5, 12, 18, 28. |
Details
From the project READMEeco-policy-mcp
An MCP server for Indian finance data — mutual-fund NAVs, GST & income-tax calculators, RBI policy rates and NSE market data — built for any MCP client (Claude, Cursor, Gemini CLI, VS Code, Cline, custom agents...), not just one.
Every successful response carries a provenance block (source, as_of,
reference), so AI agents can cite where each number came from instead of
hallucinating it.
Links
| Resource | URL |
|---|---|
| GitHub repository | https://github.com/Akhilesh-Chandewar/eco-policy-mcp |
| PyPI package | https://pypi.org/project/eco-policy-mcp/ |
| MCP Registry name | io.github.Akhilesh-Chandewar/eco-policy-mcp (active on registry.modelcontextprotocol.io) |
| Releases | https://github.com/Akhilesh-Chandewar/eco-policy-mcp/releases |
| Issues | https://github.com/Akhilesh-Chandewar/eco-policy-mcp/issues |
| License | MIT |
Install & run
# Run with any MCP client via uvx (installs automatically from PyPI):
uvx eco-policy-mcp
# Or pin the version:
uvx [email protected]
# From a clone:
uv sync
uv run eco-policy-mcp # stdio (default, local clients)
uv run eco-policy-mcp --http --port 8000 # streamable-HTTP (remote clients)
See examples/ for client configs (Claude Desktop,
Cursor, Gemini CLI, VS Code, remote HTTP).
Tools
| Domain | Tool | What it does |
|---|---|---|
| GST | gst_split | CGST/SGST vs IGST breakup for an amount + slab rate |
| GST | gst_from_inclusive | Extract GST from a tax-inclusive amount |
| GST | gst_reverse_charge | Reverse-charge (RCM) tax payable |
| GST | gstin_validate | GSTIN mod-36 checksum validation + state code |
| Income tax | income_tax_new_regime | FY 2026-27 new-regime estimate (std deduction + 87A rebate) |
| Income tax | income_tax_old_regime | Old-regime estimate (80C, age-based exemption) |
| Income tax | income_tax_compare_regimes | New vs old with recommendation |
| Mutual funds | mf_search_schemes | Search all AMFI schemes by name |
| Mutual funds | mf_get_nav | Latest NAV for a scheme code |
| Mutual funds | mf_get_nav_history | Historical NAVs between dates |
| Mutual funds | mf_compute_returns | Absolute return + CAGR between dates |
| Mutual funds | mf_sip_calculator | SIP simulation on real NAVs with XIRR |
| RBI | rbi_get_policy_rates | Repo, SDF, MSF, bank rate, CRR, SLR (as-of dated) |
| NSE | nse_get_quote | Equity quote (unofficial public endpoint) |
| NSE | nse_get_index_quote | Index snapshot (NIFTY 50, BANK, IT...) |
| NSE | nse_get_historical | Daily OHLCV (max 1y window) |
| Server | eco_server_info | Version, tool list, cache health |
Also exposes resources (eco-policy://amfi/freshness,
eco-policy://rbi/policy-rates) and prompts (compare_mutual_funds,
gst_invoice_breakup).
Data sources & disclaimers
- AMFI (
NAVAll.txt) — official daily NAV dump; parsed and cached 6h. - mfapi.in — community mirror of AMFI's NAV archive (history, returns, SIP).
- RBI — curated policy-rate snapshot stamped with its as-of date; verify at rbi.org.in before acting on it.
- NSE — unofficial public endpoints; quotes may be delayed and endpoints can change without notice. Failures return structured errors, never raw HTML.
- Tax computations are estimators (excludes surcharge, capital-gains special rates); nothing here is investment or tax advice.
Configuration
All settings via env vars (prefix ECO_): ECO_TTL_AMFI_INDEX,
ECO_TTL_NSE_QUOTE, ECO_NSE_MIN_INTERVAL, ECO_HTTP_TIMEOUT,
ECO_MFAPI_BASE, ECO_NSE_BASE, ECO_AMFI_NAV_URL, ... — see
src/eco_policy_mcp/config.py.
Development
uv sync --dev # install with dev tools
uv run pytest # run the test suite (no network needed)
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.