Toolstem MCP Server

Agent-ready financial intelligence tools — curated, not raw.

Toolstem is an MCP (Model Context Protocol) server that turns raw financial market data into curated, synthesized intelligence for AI agents. Unlike passthrough wrappers that just expose a vendor's REST API, every Toolstem tool combines multiple data sources, derives signals, and pre-computes the math an agent would otherwise have to do itself.

One call. One agent-friendly JSON response. No nested arrays to parse, no cross-endpoint stitching, no null-checking boilerplate.

Why Toolstem?

Most financial MCP servers expose one tool per API endpoint — forcing your agent to make 4–5 sequential calls, write glue code, and reason about raw data shapes. Toolstem is built differently:

• Parallel data fetching — every tool fans out to multiple sources concurrently.
• Derived signals — human-readable recommendations like UNDERVALUED, STRONG, ACCELERATING computed from raw numbers.
• Pre-computed math — CAGRs, YoY growth, margin trends, distance from 52-week high/low, FCF yield, and more are already in the response.
• Flat, predictable schema — no deeply nested vendor quirks leaking into agent prompts.
• Graceful degradation — if one upstream endpoint fails, the rest of the response still comes through with nulls in place.

Tools

get_stock_snapshot

Comprehensive stock overview combining quote, profile, DCF valuation, and rating into a single response.

Input:

{
  "symbol": "AAPL"
}

Example output (truncated):

{
  "symbol": "AAPL",
  "company_name": "Apple Inc.",
  "sector": "Technology",
  "industry": "Consumer Electronics",
  "exchange": "NASDAQ",
  "price": {
    "current": 178.52,
    "change": 2.34,
    "change_percent": 1.33,
    "day_high": 179.80,
    "day_low": 175.10,
    "year_high": 199.62,
    "year_low": 130.20,
    "distance_from_52w_high_percent": -10.57,
    "distance_from_52w_low_percent": 37.11
  },
  "valuation": {
    "market_cap": 2780000000000,
    "market_cap_readable": "$2.78T",
    "pe_ratio": 29.5,
    "dcf_value": 195.20,
    "dcf_upside_percent": 9.35,
    "dcf_signal": "FAIRLY VALUED"
  },
  "rating": {
    "score": 4,
    "recommendation": "Buy",
    "dcf_score": 5,
    "roe_score": 4,
    "roa_score": 4,
    "de_score": 5,
    "pe_score": 3
  },
  "fundamentals_summary": {
    "beta": 1.28,
    "avg_volume": 55000000,
    "employees": 164000,
    "ipo_date": "1980-12-12",
    "description": "Apple Inc. designs, manufactures..."
  },
  "meta": {
    "source": "Toolstem via Financial Modeling Prep",
    "timestamp": "2026-04-17T18:30:00Z",
    "data_delay": "End of day"
  }
}

Derived fields (not in raw APIs):

• dcf_signal — UNDERVALUED if DCF upside > 10%, OVERVALUED if < -10%, else FAIRLY VALUED.
• market_cap_readable — human-friendly $2.78T, $450.2B, $12.5M format.
• distance_from_52w_high_percent / distance_from_52w_low_percent — pre-computed range position.

get_company_metrics

Deep fundamentals analysis — profitability, financial health, cash flow, growth, and per-share metrics — synthesized from 5 financial statements endpoints.

Input:

{
  "symbol": "AAPL",
  "period": "annual"
}

period accepts annual (default) or quarter.

Example output (truncated):

{
  "symbol": "AAPL",
  "period": "annual",
  "latest_period_date": "2025-09-30",
  "profitability": {
    "revenue": 394328000000,
    "revenue_readable": "$394.3

... [View full README on GitHub](https://github.com/toolstem/toolstem-mcp-server#readme)