Web3 Signals MCP
@manavaga
About Web3 Signals MCP
AI-powered crypto signal intelligence. Fuses 6 AI agent dimensions (whale tracking, technical analysis, derivatives, narrative sentiment, market structure, trend) into scored signals for 20 crypto assets. Updated every 15 minutes with LLM-generated insights.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"web3-signals": {
"url": "https://web3-signals-api-production.up.railway.app/mcp/sse"
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Web3 Signals Agent?
A signal fusion engine that scores 20 crypto assets from 0–100 by combining five independent data agents (Whale, Technical, Derivatives, Narrative, Market) refreshed every 15 minutes. It delivers structured, multi-dimensional crypto intelligence for AI agents and trading systems — not raw price feeds.
How to use Web3 Signals Agent?
Connect via MCP by adding the endpoint to your MCP client config (e.g. Claude Desktop). Then ask your AI: “What are the current crypto signals?” or “Get me the BTC signal.” Alternatively, use the REST API endpoints for individual asset signals, portfolio summaries, performance data, and health checks — some endpoints require x402 micropayments ($0.001/call on Base mainnet).
Key features of Web3 Signals Agent
- Five weighted data agents (Whale 30%, Technical 25%, Derivatives 20%, Narrative 15%, Market 10%)
- Composite scores from 0–100 with directional labels (STRONG BUY to STRONG SELL)
- LLM-generated cross-dimensional insights explaining each signal
- 30‑day rolling accuracy tracking evaluated at 24h and 48h windows
- Supports MCP (SSE), REST API, x402 micropayments, A2A, and OpenAPI
- Self‑hostable with environment variable configuration
Use cases of Web3 Signals Agent
- Swing trades (hours to days) using scored, opinionated signals
- Portfolio risk monitoring across 20 major crypto assets
- Market regime detection (e.g. extreme_fear, degrading momentum)
FAQ from Web3 Signals Agent
What is the signal refresh rate?
Signals are updated every 15 minutes.
Which assets are covered?
BTC, ETH, SOL, BNB, XRP, ADA, AVAX, DOT, MATIC, LINK, UNI, ATOM, LTC, FIL, NEAR, APT, ARB, OP, INJ, SUI — 20 assets total.
How does accuracy tracking work?
The system snapshots signals every 12 hours and evaluates them against actual price moves from CoinGecko at 24h and 48h windows. A 30‑day rolling accuracy score is calculated, with neutral signals considered correct if the price move is ≤2%.
How do I pay for API calls?
x402 micropayments: $0.001 USDC per call on Base mainnet. No API keys or signup needed. The protocol handles payment and settlement automatically via the Coinbase CDP Facilitator.
What are the signal label ranges?
| Score Range | Label | Direction |
|---|---|---|
| 80–100 | STRONG BUY | bullish |
| 60–79 | MODERATE BUY | bullish |
| 40–59 | NEUTRAL | neutral |
| 20–39 | MODERATE SELL | bearish |
| 0–19 | STRONG SELL | bearish |
More AI & Agents MCP servers
Perplexity Ask MCP Server
ppl-aiThe official MCP server implementation for the Perplexity API Platform
MCP Server - Remote MacOs Use
baryhuangThe only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App
MCP Manager for Claude Desktop
zueaisimple web ui to manage mcp (model context protocol) servers in the claude app
Intervals.icu MCP Server
mvilanovaModel Context Protocol (MCP) server for connecting Claude and ChatGPT with the Intervals.icu API.
Sequential Thinking Multi-Agent System (MAS)
FradSerAn advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.
Comments