TL;DR
Crypto Price Alerts is a finance workflow that chains CoinGecko + Slack to automate a common task. Monitor cryptocurrency prices and receive Slack alerts when assets cross custom thresholds or drop more than 5% in an hour. Once configured, it runs through Claude Code, Cursor, Windsurf or any MCP-compatible AI agent.
Crypto Price Alerts
Monitor cryptocurrency prices and receive Slack alerts when assets cross custom thresholds or drop more than 5% in an hour.
How it works
Run with MCPizy
NewExecute this recipe in your browser — no local install, no Claude Code. Streams results live.
Why this combo?
CoinGecko has reliable real-time price data for thousands of assets; Slack gets those signals to your team immediately. Together they replace expensive Bloomberg-style terminals for crypto monitoring with a lightweight, always-on alert system.
Without this workflow
Manually check crypto prices throughout the day, miss a 20% drop while in a meeting, make decisions on stale data.
With MCPizy
Set thresholds once. Get Slack alerts the moment prices cross them. Never miss a significant move.
Business value
Concrete ROI — not marketing fluff.
Time saved
- Cooldown logic prevents alert fatigue so real signals don't get ignored
- Enables lean finance teams to monitor 50+ assets without hiring a dedicated analyst
Workflow steps
- 1Poll CoinGecko API every 5 minutes
- 2Compare price against alert thresholds
- 3Detect 1h / 24h change spikes
- 4Post alert to #crypto-desk Slack channel
- 5Suppress duplicate alerts within cooldown window
Use cases
- Alert when Bitcoin crosses a price target you set for buying or selling
- Hourly volatility alerts when any asset moves more than 5% in 60 minutes
- Daily portfolio summary posted to Slack every morning
- Cooldown logic to suppress repeated alerts for sustained trends
Agent prompt (copy into Claude Code)
This prompt is the workflow. Paste into Claude Code, Cursor, or Windsurf.
You are a crypto price-alert agent. Runs every 5 minutes.
Given a watchlist in watchlist.json ({symbol, target_high, target_low, pct_threshold_1h}):
1. Call coingecko.get_price(ids=[...symbols], vs_currencies="usd", include_24hr_change=true, include_last_updated=true) in one batch
2. For each symbol:
- If price > target_high or price < target_low → build alert
- If |1h_change| > pct_threshold_1h → build spike alert
3. De-dup: check ~/.mcpizy/state/crypto-alerts.json — skip if same alert fired in last 30min (cooldown)
4. For each new alert, call slack.send_message(channel="#crypto-desk", text=":chart_with_upwards_trend: ${symbol} ${direction} — ${price} (${pct_change}%)")
5. Persist fired alerts to state file for cooldown tracking
Reply with count of alerts fired.Trigger & credentials
How this workflow fires and what env vars you need.
*/5 * * * * # every 5 minutes
One-command deploy
Install everything — MCPs, prompt, env template — in a single call.
$ mcpizy recipe install coingecko-slack-crypto-alerts ✓ Installs all 2 MCP servers ✓ Writes prompt to ~/.mcpizy/prompts/coingecko-slack-crypto-alerts.md ✓ Generates .env.example in current directory ✓ Ready to paste into Claude Code
Requires mcpizy CLI v1.1+ — install via npm i -g mcpizy.
Quick install (MCPs only)
$ mcpizy install coingecko && mcpizy install slackMore Finance recipes
Frequently asked questions
What is this workflow?
Crypto Price Alerts is a finance automation that uses CoinGecko + Slack together via the Model Context Protocol. Monitor cryptocurrency prices and receive Slack alerts when assets cross custom thresholds or drop more than 5% in an hour.
How long does setup take?
Setup takes around 5 min setup, continuous monitoring. You install the required MCP servers with `mcpizy install coingecko && mcpizy install slack`, connect your accounts, and the workflow is ready to run.
What does this workflow change in practice?
Cooldown logic prevents alert fatigue so real signals don't get ignored; Enables lean finance teams to monitor 50+ assets without hiring a dedicated analyst.
Which MCP servers do I need for this?
You need 2 MCP servers: CoinGecko (mcpizy install coingecko), Slack (mcpizy install slack). All are installable in one command via the MCPizy CLI and configured in your `.claude.json` or `.cursor/mcp.json`.
Does this work with Claude Code, Cursor, and Windsurf?
Yes. The workflow runs with any MCP-compatible AI agent — Claude Code, Claude Desktop, Cursor, Windsurf, VS Code with Copilot, and custom agents built on the MCP SDK. The MCP servers are identical across clients; only the config file path (`.claude.json` vs `.cursor/mcp.json`) changes.
Start building this workflow
Install the required MCPs from the directory and automate this in 5 min setup.
$ mcpizy install coingecko && mcpizy install slack
Free to install. Connect your accounts and this workflow runs itself.