About Mftool Mcp
Mftool Mcp is an MCP server for Indian mutual fund data, built on mftool. It gives MCP clients tools for NAV lookup, history, fund performance, and portfolio calculations.
Key features
- 01Look up single or bulk fund NAVs
- 02Fetch NAV history and scheme details
- 03Search by name, AMC, or type
- 04View fund performance and AMC AUM
- 05Calculate returns and portfolio values
- 06Manage cached data
Use cases
- 01Check a scheme’s current NAV
- 02Compare funds’ historical returns
- 03Find fund types from a specific AMC
- 04Calculate SIP returns or portfolio value
MCP support
The MCP server exposes tools for querying, searching, analyzing, and calculating with Indian mutual fund data.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README🇮🇳 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
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.