io.github.NayakwadiS/mftool-mcp
MCP Server for publicly available Indian Mutual Funds data
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
mftool-mcpclaude mcp add mftool-mcp -- uvx mftool-mcp==0.4.0
{
"mcpServers": {
"mftool-mcp": {
"command": "uvx",
"args": [
"mftool-mcp==0.4.0"
]
}
}
}
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Contents
🇮🇳 mftool-mcp
MCP Server for publicly available Indian Mutual Funds data
Powered by mftool · Works with Claude, Cursor, and any MCP-compatible LLM client
What is this?
mftool-mcp is a Model Context Protocol (MCP) server that gives any LLM client access to Indian Mutual Fund data.
Ask your AI assistant questions like:
- "What is the current NAV of SBI Bluechip Direct Growth?"
- "Show me 3-year returns for HDFC Midcap Opportunities Fund"
- "List all schemes under Mirae Asset AMC"
- "Find all flexi cap funds and compare their 5-year returns"
Tools Available
| Tool | Description |
|---|---|
get_scheme_quote | Live NAV for any scheme by AMFI scheme code |
get_bulk_quotes | Live NAV for multiple schemes at once (concurrent) |
get_scheme_historical_nav | Full NAV history for a scheme (all available dates) |
get_scheme_historical_nav_for_dates | NAV history filtered to a specific date range (DD-MM-YYYY) |
get_scheme_history | NAV history via BSE/YFinance code with period or date range |
get_scheme_codes | All AMFI scheme codes and names |
get_available_schemes | All schemes under a specific AMC |
get_scheme_details | Fund house, type, category, start date (AMFI code) |
get_scheme_info | Rich scheme info — AUM, returns, ratings (BSE/YFinance code) |
is_valid_scheme_code | Validate an AMFI numeric scheme code |
is_valid_new_scheme_code | Validate a BSE/new format scheme code |
search_schemes | Search schemes by name keyword with relevance ranking |
search_schemes_by_amc | Search schemes within a specific AMC |
search_schemes_by_type | Search schemes by type/category (equity, debt, elss, etc.) |
get_average_aum | Average AUM (domestic & overseas) for all AMCs by quarter |
get_equity_scheme_performance | Daily performance for all equity funds (1Y/3Y/5Y returns) |
get_debt_scheme_performance | Daily performance for all debt funds (1Y/3Y/5Y returns) |
get_hybrid_scheme_performance | Daily performance for all hybrid funds (1Y/3Y/5Y returns) |
get_solution_scheme_performance | Daily performance for solution-oriented funds (retirement, children) |
get_other_scheme_performance | Daily performance for index funds and Fund of Funds |
calculate_returns | Calculate SIP returns — absolute return % and annualised IRR |
calculate_balance_units_value | Current market value of held units for a scheme |
calculate_portfolio_value | Total current value of a multi-scheme portfolio (concurrent) |
get_cache_stats | View hit/miss stats for NAV and scheme code caches |
clear_cache | Clear all cached data to force fresh fetches |
set_cache_enabled | Enable or disable mftool caching globally |
Quick Start
Using uvx (Recommended — no install needed)
uvx mftool-mcp
Using pip
pip install mftool-mcp
mftool-mcp
Claude Desktop Setup
Add this to your claude_desktop_config.json:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"mftool-mcp": {
"command": "uvx",
"args": ["mftool-mcp"]
}
}
}
Restart Claude Desktop. You'll see mftool-mcp listed under connected tools.
Cursor / Other MCP Clients
In your MCP client settings, add:
{
"mftool-mcp": {
"command": "uvx",
"args": ["mftool-mcp"]
}
}
Example Conversations
Finding a fund:
You: "Find all SBI midcap mutual fund scheme codes"
Claude: callssearch_schemes_by_amc(amc_name='sbi', query='midcap')
Claude: "Here are the SBI midcap schemes: SBI Magnum Midcap Fund - Direct Growth (code: 125497)..."
Live NAV:
You: "What's the current NAV of scheme 125497?"
Claude: callsget_scheme_quote(scheme_code='125497')
Claude: "SBI Magnum Midcap Fund - Direct Growth: NAV ₹234.56 (as of 05-Apr-2025)"
Performance comparison:
You: "Compare 5-year returns for large cap equity funds"
Claude: callsget_equity_scheme_performance()
Claude: "Here's the 5-year return comparison for Large Cap funds: ..."
Data Source
All data is sourced via the mftool library. Data accuracy depends on published figures. This tool is for informational purposes only and does not constitute financial advice.
Development
git clone https://github.com/NayakwadiS/mftool-mcp
cd mftool-mcp
pip install -e ".[dev]"
# Run the server locally
python -m mftool_mcp.server
See PUBLISHING.md for the full release process (PyPI + MCP Registry).
Acknowledgements
- mftool — the underlying data library
Associated Initiatives
- NSE Stock predictions NSE-Neuron
Frequently asked questions
What is io.github.NayakwadiS/mftool-mcp?
MCP Server for publicly available Indian Mutual Funds data
How do I install io.github.NayakwadiS/mftool-mcp?
It runs on your machine. In Claude Code: claude mcp add mftool-mcp -- uvx mftool-mcp==0.4.0. For other clients, paste the JSON configuration from this page into their MCP settings.
Does io.github.NayakwadiS/mftool-mcp need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is io.github.NayakwadiS/mftool-mcp open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains io.github.NayakwadiS/mftool-mcp?
It is published by NayakwadiS. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.