CryptoSignals

io.github.MarcinDudekDevPublished by GitHub account MarcinDudekDevv1.0.1Updated Oct 24, 2026

Real-time crypto volume anomaly detection across 50+ tokens for whale signals

The publisher's own server: SIGNALS Loyalty Agent Platform

VerifiedSTDIODesktop onlyFinanceData & Analytics

Overview

AI-generated overview

A local MCP server that surfaces real-time crypto volume anomalies across 50+ tokens, letting an assistant scan tokens, analyze one coin, and list high-signal,

What you can do
Scan all monitored tokens for unusual volume-to-market-cap ratios and classify signals as LOW, MODERATE, HIGH or CRITICAL. Analyze a single token such as BTC, ETH or SOL for unusual trading activity. Retrieve high-confidence alerts only, filtered to volume-to-market-cap ratios above 5.0. Report live prices, 24-hour changes, volume and market cap alongside the signals.
When to use it
Useful when you want an assistant to watch for unusual crypto trading volume, whale accumulation or pump-like activity, or to check a specific coin for abnormal volume before acting on it.
Requirements
Runs as a local process on the user's machine, installed from the PyPI package crypto-signals-mcp and started with fastmcp; desktop client configuration is shown for Claude Desktop. It connects to a live anomaly detection API, so network access is needed. No accounts, API keys or environment variables are declared.
Before you install
The server sends requests to a third-party anomaly detection API, so queries and token interests leave your machine. Signals are statistical indicators, not investment advice, and may be wrong or delayed; do not treat them as a basis for trading decisions without independent checks.

Installation

In SourceWeft

  1. Open CryptoSignals in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

CryptoSignals MCP Server

MCP server for real-time crypto volume anomaly detection across 50+ tokens. Detects unusual trading activity, whale movements, and pump signals.

Features

  • Volume anomaly detection — Identifies tokens with unusual volume-to-market-cap ratios
  • 50+ tokens monitored — Continuous scanning across major cryptocurrencies
  • Anomaly classification — Signals rated LOW, MODERATE, HIGH, or CRITICAL
  • High-confidence alerts — Filter for only the most actionable signals
  • Live data — Real-time prices, 24h changes, volume, and market cap

Tools

ToolDescription
scan_all_tokensScan all 50+ tokens for volume anomalies
analyze_tokenDetailed analysis for a specific token (BTC, ETH, SOL, etc.)
get_anomaly_alertsHigh-confidence alerts only (vol_mcap ratio above 5.0)

Quick Start

Install

bash
pip install crypto-signals-mcp

Run

bash
fastmcp run server.py

Configure in Claude Desktop

Add to your claude_desktop_config.json:

json
{  "mcpServers": {    "crypto-signals": {      "command": "fastmcp",      "args": ["run", "server.py"]    }  }}

Example Usage

Ask your AI assistant:

  • "Scan all crypto tokens for volume anomalies"
  • "Analyze Bitcoin for unusual trading activity"
  • "Show me high-confidence crypto alerts"
  • "Which tokens have whale movement signals right now?"

How It Works

The server connects to a live anomaly detection API that monitors trading volume across 50+ cryptocurrencies. It calculates volume-to-market-cap ratios to identify statistically unusual trading activity — often an early indicator of price movement, whale accumulation, or pump activity.

License

MIT

Source: README.md at commit 9647b99

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Signals integrations

SIGNALS Loyalty Agent Platform

global.signalsOfficial publisher

A remote MCP server giving assistants 63 tools for loyalty programs, rewards and member operations, with human-in-the-loop approval.

Streamable HTTPWeb executableAuth
Business & CommerceCredential requiredOct 24, 2026

Chaos — OKX Perpetual Signals

tw.okxOfficial publisher

Remote MCP server that gives an assistant trend and order-flow signals, indicator series and backtests for OKX USDT perpetual swaps, paid per call.

Streamable HTTPWeb executableAuth
Data & Analytics6 toolsOct 24, 2026

Greenhouse, Lever & Ashby Jobs (by flyingkiwi)

Published by GitHub account flyingkiwi-tools

Greenhouse, Lever & Ashby Jobs (by flyingkiwi)'s hosted MCP server; credential required; Streamable HTTP.

Streamable HTTPWeb executableAuth
Credential requiredNov 3, 2026

E-commerce Sales Signals MCP

Published by GitHub account GeminiGeorge22

E-commerce sales signals: Amazon bestsellers and reviews, eBay sold prices, TikTok Shop, Etsy sales.

Streamable HTTPWeb executableAuth
Business & Commerce6 toolsNov 4, 2026

QSignals AI Stock Scores

Published by GitHub account jiahongq

Remote QSignals server that gives an assistant 0-100 stock scores, signals and market-regime data for US stocks and ETFs.

Streamable HTTPWeb executableAuth
Finance6 toolsNov 1, 2026