crypto-intel-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@crypto-intel-mcpAnalyze Bitcoin"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
crypto-intel-mcp
Crypto market intelligence for any LLM, over the Model Context Protocol.
Gives any MCP client (Claude Desktop, Claude Code, agents) clean tools for crypto price, momentum, and what's trending — and blends them into a single scored verdict. Runs entirely on CoinGecko's free public API (no key), fails gracefully (a missing source returns "no data", never a fabricated value), and outputs Markdown by default or JSON on demand.
# Crypto Intelligence — BTC
**Signal:** Lean positive `[........|##......]` +22/100 · confidence 80%
Building momentum → LEAN LONG. BTC momentum: 24h +1.9% · 7d +4.4% · 30d -17.0%.
- In CoinGecko trending (elevated attention).
- Total crypto market cap +1.8% 24h, BTC dominance 57%.Tools
Tool | What it does | Source | Status |
| Hero tool. Blends momentum + trending + market tide into one scored verdict (RISK-ON → AVOID). | composite | ✅ |
| Live price, 24h change, market-cap rank, volume, distance from ATH. | CoinGecko | ✅ |
| Multi-timeframe momentum (24h/7d/30d) scored into one directional signal. | CoinGecko | ✅ |
| The coins the market is searching for most right now. | CoinGecko | ✅ |
Every tool returns Markdown (human-readable, default) or JSON
(response_format="json") for programmatic use.
Related MCP server: CG Alpha MCP
Quick start
git clone <your-repo-url> crypto-intel-mcp
cd crypto-intel-mcp
python -m venv .venv && .venv\Scripts\activate # Windows
pip install -r requirements.txt
python -m crypto_intel_mcp # starts the MCP server over stdio (no .env needed)Smoke test (hits the live CoinGecko API and prints each signal):
python tests/test_smoke.py bitcoinUse it in Claude Desktop
Add this to claude_desktop_config.json
(%APPDATA%\Claude\ on Windows, ~/Library/Application Support/Claude/ on macOS),
then restart Claude Desktop:
{
"mcpServers": {
"crypto-intel-mcp": {
"command": "python",
"args": ["-m", "crypto_intel_mcp"],
"cwd": "C:/path/to/crypto-intel-mcp"
}
}
}Why it's built this way
Uniform result contract. Every source returns the same
Resultshape, so an LLM can reason across tools instead of parsing N formats.Graceful degradation. A source with no data returns "no data", not a fake value. Missing data never invents an answer.
Resilient + cached. A short per-source TTL cache avoids hammering rate-limited endpoints when an agent calls several tools in one turn.
Disclaimer
For research and educational use only. Data comes from third-party sources and may be delayed or incomplete.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/cstamigo-droid/crypto-intel-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server