Crypto market-signal MCP tools (regime, sentiment, price, risk) via RapidAPI. Needs RAPIDAPI_KEY
Stelar MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. Crypto market-signal MCP tools (regime, sentiment, price, risk) via RapidAPI. Needs RAPIDAPI_KEY.
An MCP (Model Context Protocol) server that gives any MCP-compatible AI agent (Claude Desktop, Claude Code, Cursor, etc.) six crypto market-signal and utility tools, backed by the same classifier that runs a live production grid-trading system, plus Claude-powered text tools.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Once Stelar is connected, these are the calls the assistant has available:
crypto_regime — Market regime (chop / trend_up / trend_down / high_vol) + grid-suitability verdict for SOL, XLM, BTC, ETH, XRP, DOGE, LTC, ADAcrypto_sentiment — Sentiment score (-1..+1) + label for free text or a crypto asset's recent price actionsummarize — 3-5 sentence LLM summary of a URL or raw textfactcheck — true/false/uncertain verdict + confidence + reasoning for a claimpricecheck — Price, 24h/7d change, bullish/bearish/neutral signal for a major crypto assettoken_risk — Volatility/drawdown risk regime (low/med/high) vs 30-day baseline, for position sizingtelemetry — $0.005sentiment — $0.005price — $0.005risk — $0.02regime — $0.03gridparams — $0.05You will need 4 environment variables: RAPIDAPI_KEY, YOUR_RAPIDAPI_KEY, RAPIDAPI_HOST, BASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Stelar's toolset — crypto_regime, crypto_sentiment, summarize and 11 more — is a fair guide to whether it matches your workflow. It is maintained by StelarDigital; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Stelar's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| crypto_regime | Market regime (chop / trend_up / trend_down / high_vol) + grid-suitability verdict for SOL, XLM, BTC, ETH, XRP, DOGE, LTC, ADA |
| crypto_sentiment | Sentiment score (-1..+1) + label for free text or a crypto asset's recent price action |
| summarize | 3-5 sentence LLM summary of a URL or raw text |
| factcheck | true/false/uncertain verdict + confidence + reasoning for a claim |
| pricecheck | Price, 24h/7d change, bullish/bearish/neutral signal for a major crypto asset |
| token_risk | Volatility/drawdown risk regime (low/med/high) vs 30-day baseline, for position sizing |
| telemetry | $0.005 |
| sentiment | $0.005 |
| price | $0.005 |
| risk | $0.02 |
| regime | $0.03 |
| gridparams | $0.05 |
| Tier | Price |
| Basic | Free |
{
"mcpServers": {
"stelar-signals": {
"command": "npx",
"args": ["-y", "github:StelarDigital/stelar-signals-mcp"],
"env": {
"RAPIDAPI_KEY": "YOUR_RAPIDAPI_KEY"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| RAPIDAPI_KEY | Credential the server authenticates with. | Yes |
| YOUR_RAPIDAPI_KEY | Credential the server authenticates with. | Yes |
| RAPIDAPI_HOST | Endpoint or connection string the server talks to. | Optional |
| BASE_URL | Endpoint or connection string the server talks to. | Yes |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.