agnifolio-mcp
The agnifolio-mcp server provides two sets of tools:
Public Tools (no authentication): Calculate FIRE number, retrieve high-interest savings/fixed deposit/treasury rates (SG, IN, US), find net worth percentile globally/by country/age/gender, and get information about Agni Folio and how to connect to personal data.
Personal Financial Tools (hosted, OAuth required): Read portfolio holdings, account summaries, performance, FIRE/Coast FIRE status, crypto P&L, exchange balances, open positions, trades, insurance summaries, and nominees; write operations (add/delete portfolio entries, transactions, policies, set crypto cost basis, update FIRE goals) with confirmation gates.
Agni Folio MCP Server
Official Model Context Protocol server for Agni Folio — a free, multi-currency wealth & portfolio tracker (stocks, crypto, real estate, fixed deposits, mutual funds, insurance, and loans across 20+ markets).
This is a hosted remote server. There is nothing to install or run — you connect your MCP client to the production endpoint and authenticate with your own Agni Folio account.
Endpoint:
https://agnifolio.com/mcp(streamable HTTP)Auth: OAuth 2.1 with Dynamic Client Registration + PKCE — any MCP client can onboard without pre-registration
Scopes:
agnifolio:read,agnifolio:write(per-user, revocable from Settings → Connected AI)Server card:
/.well-known/mcp/server-card.jsonAgent skills:
/.well-known/agent-skills/index.jsonDocs: Connect Your AI · auth.md · llms.txt
Quick connect
Claude (web/desktop): Settings → Connectors → Add custom connector → https://agnifolio.com/mcp → complete the OAuth sign-in.
Cursor / Cline / Continue / other stdio-first clients — bridge via mcp-remote:
{
"mcpServers": {
"agnifolio": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://agnifolio.com/mcp"]
}
}
}The first call opens a browser window for the OAuth consent flow; tokens are cached locally by mcp-remote.
Related MCP server: personal-finance-mcp
Public-tools server (open source, in this repo)
This repo also contains a small runnable MCP server for Agni Folio's public tools — no account needed:
Tool | What it does |
| FIRE number, progress %, years-to-FIRE, Coast FIRE — pure local math |
| Current savings/FD/treasury rates across SG, IN, US (public API) |
| Net-worth percentile by country/age/gender (anonymized public dataset) |
| About Agni Folio + how to connect to the personal-data server |
npm install && npm run build
node dist/index.js # stdio MCP server
# or via Docker
docker build -t agnifolio-public-mcp .
docker run -i --rm agnifolio-public-mcpClaude Desktop / Cursor config:
{
"mcpServers": {
"agnifolio-public": {
"command": "node",
"args": ["/path/to/agnifolio-mcp/dist/index.js"]
}
}
}The public-tools server never sees credentials; personal portfolio data is only available through the hosted OAuth server above.
Tools (23)
Read — portfolio: query_holdings, query_holding_by_symbol, query_account_summary, query_performance_summary, query_classification_warnings
Read — FIRE planning: query_user_fire_status, query_user_coast_fire, query_fire_what_if
Read — crypto & trading: query_crypto_pnl, query_exchange_spot_balances, query_open_positions, query_margin_detail, query_recent_trades
Read — protection & legacy: query_insurance_summary, query_nominees
Write (confirm-gated): add_portfolio_entry, add_transaction, add_insurance_policy, delete_portfolio_entry, parse_text_into_entries, set_crypto_cost_basis, recover_crypto_cost_basis, update_user_fire_goals
Every mutating tool is confirm-before-execute: the change is staged and must be approved inside the Agni Folio app before it takes effect. Every external call — read or write — is recorded in a per-user audit log.
Security model
Per-user OAuth tokens; the server never sees your client's credentials
Scoped access (
readvswrite) chosen at consent timeRevocation: one click in Settings → Connected AI kills the grant
Confirm-gated writes + full audit trail
Agni Folio is not a brokerage and executes no trades; it is a tracking/analytics tool
About this repository
The server implementation is part of the Agni Folio production backend and is not open source; this repository is the canonical public home for connection docs and issue reports for the MCP surface. Found a problem with a tool? Open an issue or use contact.
Available Tools
4 toolscalculate_fire_numberA
Calculate the FIRE (Financial Independence, Retire Early) number from annual expenses and a safe withdrawal rate, plus — when current net worth, savings and return assumptions are given — progress %, estimated years to FIRE, and the Coast FIRE number. Pure local math, no data leaves the machine.
Inputs: annual_expenses (required), current_age, monthly_savings, current_net_worth, +3 more.
find_networth_percentileA
Find what percentile a given net worth falls into, globally or within specific countries, optionally segmented by age and gender. Uses Agni Folio's anonymized public dataset.
Inputs: networth_amount (required), age, gender, currency, +2 more.
get_agnifolio_infoB
What Agni Folio is, what this public server can do, and how to connect an AI to a user's own portfolio via the hosted OAuth MCP server.
Inputs: no named parameters.
get_high_interest_productsA
List current high-interest savings accounts, fixed deposits, treasury products and similar across Singapore, India and the USA, with rates and conditions. Community-verified data from Agni Folio's public rates database.
Inputs: country, product_type.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a distinct domain: FIRE calculation, server information, high-interest products, and net worth percentiles. There is no functional overlap or ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case (calculate_, get_, find_). Even though 'find' and 'get' differ, they are both action verbs and the pattern is clear.
With 4 tools, the server is well-scoped for a personal finance assistant. Each tool provides meaningful functionality without unnecessary bloat.
The core financial planning workflows (FIRE calculation, rate lookup, percentile comparison) are covered. A minor gap is the absence of a tool for detailed investment or expense tracking, but it does not hinder the main purpose.
Maintenance
Related MCP Connectors
Official Intrinio MCP server. US stock prices, options and fundamentals for AI agents.
Open-source MCP server for Zerodha Kite Connect. Portfolio, market data, backtesting, alerts.
MCP server for Financial Modeling Prep API with 250+ financial data tools
Hosted MCP server with managed OAuth for 15+ toolkits: Google Workspace, Fitbit, Oura, Kalshi, etc.
Related MCP Servers
- AlicenseAqualityDmaintenanceA portfolio analysis MCP server that enables AI agents to manage investment portfolios, fetch financial data from Yahoo Finance and CoinGecko, and perform advanced analysis like weight optimization and Monte Carlo simulations. It utilizes reference-based caching to efficiently handle large datasets without bloating the LLM's context window.261MIT
- AlicenseAqualityDmaintenanceSelf-hosted, read-only MCP server that connects banks, credit cards, loans, and brokerage accounts via Plaid. 9 tools for balances, transactions, recurring charges, liabilities, and investment holdings.99MIT
- AlicenseCqualityAmaintenanceopen-source personal finance app with a first-party MCP server. 91 HTTP tools (OAuth 2.1 + DCR) and 87 stdio tools cover transactions, budgets, accounts, portfolio analytics, FX conversion, loans, subscriptions, goals, importers, and rules. Users self-host with Docker + PostgreSQL or use the managed cloud8935AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceFinancialFilings gives AI assistants and agents official filings, as published (annual and interim reports, ad-hoc disclosures, insider transactions, ESG reports) and standardized financials for listed companies in the US, EU, UK, APAC and LATAM. Remote MCP server at https://mcp.financialfilings.com/mcp with OAuth sign-in: no API key to copy, free for any FinancialFilings account.2MIT