// // hermes integration

Market context for your
Hermes agent.

Connect TickerDB to Hermes as an MCP server. Your agent gets market summaries, watchlists, ticker event history, and webhooks — accessible from CLI, Telegram, Discord, or any gateway you run.

try for free playground

// setup

Add to your config. Done.

Add TickerDB to your Hermes config.yaml under mcp_servers. Remote or local, both work.

Point Hermes at TickerDB's remote MCP server. No local install, no process to manage.

config.yaml

mcp_servers:
  tickerdb:
    url: "https://mcp.tickerdb.com/mcp"
    headers:
      Authorization: "Bearer tdb_your_api_key"

Run /reload-mcp in the Hermes chat to pick up the new config without restarting.

Run the MCP server locally via npx. Hermes starts the process and connects automatically.

config.yaml

mcp_servers:
  tickerdb:
    command: "npx"
    args: ["tickerdb-mcp"]
    env:
      TICKERDB_KEY: "tdb_your_api_key"

// in practice

How it looks in Hermes.

Once connected, Hermes calls TickerDB tools automatically when you ask about markets. Same experience across CLI, Telegram, Discord, or any gateway.

You

How does INTC look right now?

Tool call: get_summary

{ "ticker": "INTC" }

Hermes

INTC is in a confirmed downtrend, deep oversold for 8 consecutive days — historically rare (95th percentile). Valuation is in the deep value zone. Volume is extremely high, which may indicate a selling climax. The combination of extreme oversold conditions and historically low valuation makes it a potential mean-reversion candidate.

You

What about AMD? How does it compare?

Tool call: get_summary

{ "ticker": "AMD" }

Hermes

AMD is in a downtrend too but only mildly oversold, fair value on fundamentals, with a buy consensus. The key divergence: INTC's condition is historically rare while AMD's is more common. INTC is the more extreme mean-reversion setup.

You

Add both to my watchlist. Check them every weekday morning and message me here if anything changes.

Tool call: get_watchlist

{}

Hermes

Done. INTC and AMD are on your watchlist. I've set up a daily check at 9:35 AM ET on weekdays. I'll message you here if either exits oversold, if volume spikes, or if the trend shifts.

// state changes

Track state changes effortlessly.

Most market data APIs return point-in-time snapshots. TickerDB tracks state transitions — your agent sees what changed, not just what is.

json

{
  "timeframe": "daily",
  "run_date": "2026-03-28",
  "changes": {
    "AAPL": [
      {
        "field": "rsi_zone",
        "from": "neutral",
        "to": "oversold"
      },
      {
        "field": "trend_direction",
        "from": "uptrend",
        "to": "downtrend"
      }
    ]
  },
  "ticker_context": {
    "AAPL": {
      "last_changed_date": "2026-03-28"
    }
  },
  "tickers_checked": 2,
  "tickers_changed": 1
}

// what your agent sees

What your agent sees.

Every tool returns categorical facts — not raw OHLCV data. Your agent can branch on "oversold" without needing to know what RSI > 70 means.

json

{
  "ticker": "NVDA",
  "data_status": "eod",
  "as_of_date": "2026-04-11",
  "trend": {
    "direction": "strong_uptrend",
    "ma_alignment": "aligned_bullish"
  },
  "momentum": {
    "rsi_zone": "overbought",
    "macd_state": "expanding_positive",
    "direction": "accelerating"
  },
  "volatility": {
    "regime": "normal",
    "regime_trend": "stable"
  },
  "fundamentals": {
    "valuation_zone": "fair_value",
    "pe_vs_historical_zone": "premium",
    "last_earnings_surprise": "beat"
  }
}