SignalFuse MCP Server
The SignalFuse MCP Server provides trading intelligence tools for AI agents working with crypto markets.
Directional Trading Signals: Get composite signals for individual crypto assets (BTC, ETH, SOL, etc.) including signal strength (0-100), confidence, direction (long/short/neutral), sentiment, macro regime, funding rate bias, and OI delta
Batch Signal Processing: Retrieve fused signals for multiple assets simultaneously via comma-separated symbols, or fetch all supported assets at once
Social Sentiment Analysis: Access raw social sentiment breakdowns for specific crypto assets
Macro Regime Detection: Determine the current macro risk regime (risk-on, risk-off, or neutral) for position sizing and directional bias decisions
Strategy Arena: View live rankings of four competing strategies (EMA Breakout, RSI Extremes, RSI Reversion, VWAP Reversion) and pull strategy-specific signals
Web Search: Perform searches via Brave or AI-powered searches via Tavily for market research
Sandboxed Code Execution: Run code securely via E2B for custom analysis or automation
Account Management: Check credit balance and view pricing; includes 25 free calls to start without signup
Click on "Deploy 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., "@SignalFuse MCP Server what's the signal for BTC?"
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.
SignalFuse MCP Server
MCP server and REST API for crypto trading signals, sentiment analysis, macro regime classification, strategy arena, web search, and sandboxed code execution. Designed for AI agents, LLMs, and autonomous trading systems.
Base URL:
https://api.signalfuse.coOpenAPI spec:
https://api.signalfuse.co/openapi.jsonx402 discovery:
https://api.signalfuse.co/.well-known/x402llms.txt:
https://api.signalfuse.co/llms.txtPayment: x402 USDC on Base (no API keys needed) or prepaid credit tokens
Free trial: 5 credits, no signup required
What SignalFuse Does
Generates directional trading signals (long/short/neutral) for BTC, ETH, SOL, DOGE, PEPE, WIF, BONK, ARB, OP, AVAX with entry price, take-profit, and stop-loss levels
Runs ModernFinBERT sentiment analysis on crypto social and news data
Classifies the macro regime as risk-on, risk-off, or neutral using multi-factor economic indicators
Operates a Strategy Arena where 4 AI strategies (EMA Breakout, RSI Extremes, RSI Reversion, VWAP Reversion) compete head-to-head with live P&L tracking
Proxies web search through Brave Search and Tavily with result deduplication and fusion
Executes Python and JavaScript code in sandboxed E2B environments (60s timeout)
Related MCP server: oneqaz-trading-mcp
Installation
npm (MCP server)
npx signalfuse-mcpOr install globally:
npm install -g signalfuse-mcpPython client (x402 payments built in)
pip install signalfuseEndpoint Reference
Method | Path | Description | Price |
GET |
| Fused directional signal with entry/TP/SL | $0.010 |
GET |
| Signals for all assets in one call | $0.075 |
GET |
| ModernFinBERT sentiment analysis | $0.002 |
GET |
| Macro regime classification (risk-on/off/neutral) | $0.001 |
GET |
| Strategy Arena rankings | FREE |
GET |
| Signal from a specific arena strategy | $0.001 |
GET |
| Brave web search | $0.008 |
POST |
| Tavily AI-powered web search | $0.012 |
POST |
| Brave + Tavily fused and deduplicated | $0.015 |
POST |
| Sandboxed code execution (Python/JS) | $0.005 |
GET |
| Pricing information | FREE |
GET |
| Credit balance check | FREE |
POST |
| Claim 5 free trial credits | FREE |
Free Trial
Get 5 free credits with no signup. Send your Ethereum wallet address:
curl -X POST https://api.signalfuse.co/v1/credits/trial \
-H "Content-Type: application/json" \
-d '{"wallet": "0xYOUR_ETH_ADDRESS"}'Response:
{
"credit_token": "sf_abc123...",
"credits": 5,
"wallet": "0xYOUR_ETH_ADDRESS"
}Pass the returned credit_token as the X-Credit-Token header on subsequent requests, or use it in MCP tool calls.
Example Request/Response Pairs
Get a Trading Signal
curl https://api.signalfuse.co/v1/signal/BTC \
-H "X-Credit-Token: sf_abc123..."{
"symbol": "BTC",
"signal": "long",
"signal_strength": 74,
"confidence": 0.82,
"regime": "risk_on",
"components": {
"social": {"score": 0.49, "label": "bullish"},
"macro": {"score": 0.63, "label": "bullish"},
"market": {"score": 0.42, "label": "long_bias"}
},
"updated_at": "2026-04-04T12:00:00Z"
}Get Sentiment Analysis
curl https://api.signalfuse.co/v1/sentiment/ETH \
-H "X-Credit-Token: sf_abc123..."{
"symbol": "ETH",
"score": 0.65,
"label": "bullish",
"model": "ModernFinBERT",
"updated_at": "2026-04-04T12:00:00Z"
}Get Macro Regime
curl https://api.signalfuse.co/v1/regime \
-H "X-Credit-Token: sf_abc123..."{
"regime": "risk_on",
"confidence": 0.78
}Get Arena Leaderboard
curl https://api.signalfuse.co/v1/arena/leaderboard[
{
"strategy_id": "ema_5_breakout",
"wins": 142,
"losses": 98,
"win_rate": 0.591,
"total_pnl_bp": 340,
"total_income_usd": 1720.50
}
]Web Search (Brave)
curl "https://api.signalfuse.co/v1/gateway/search/brave?q=bitcoin+ETF+flows" \
-H "X-Credit-Token: sf_abc123..."Web Search (Tavily)
curl -X POST https://api.signalfuse.co/v1/gateway/search/tavily \
-H "Content-Type: application/json" \
-H "X-Credit-Token: sf_abc123..." \
-d '{"query": "bitcoin ETF flows", "search_depth": "advanced"}'Execute Code (E2B Sandbox)
curl -X POST https://api.signalfuse.co/v1/gateway/execute/e2b \
-H "Content-Type: application/json" \
-H "X-Credit-Token: sf_abc123..." \
-d '{"code": "print(2 + 2)", "language": "python"}'{
"stdout": "4\n",
"stderr": "",
"exit_code": 0
}Pricing
Tier | Credits | Price | Per-Credit Cost |
Free Trial | 5 | $0 | $0 |
x402 Pay-Per-Call | unlimited | market rate | see endpoint table |
Starter Pack | 500 | available at signalfuse.co | bulk discount |
Pro Pack | 5,000 | available at signalfuse.co | bulk discount |
x402 is an open protocol for HTTP micropayments. SignalFuse accepts USDC on Base. No API keys, no subscriptions -- each request includes a payment header and the server settles on-chain. See the x402 spec for details.
MCP Tools (11 total)
When connected as an MCP server, SignalFuse exposes 11 tools:
Tool Name | Description |
| Fused directional signal for a crypto asset (direction, strength, confidence, regime, entry/TP/SL) |
| Signals for all supported assets in one call |
| ModernFinBERT sentiment analysis (score, label) |
| Macro regime classification (risk_on, risk_off, neutral) |
| Strategy Arena rankings with win rate, P&L, income (free) |
| Signal from a specific arena strategy for a given asset |
| Web search via Brave Search |
| AI-powered web search via Tavily |
| Sandboxed Python/JavaScript execution via E2B |
| Pricing information (free) |
| Credit balance check (free) |
Strategy Arena Strategies
Strategy ID | Description |
| Trend-following on exponential moving average crossovers |
| Momentum entries at RSI overbought/oversold levels |
| Mean-reversion fades against RSI extremes |
| Mean-reversion entries around volume-weighted average price |
Agent Framework Integrations
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"signalfuse": {
"command": "npx",
"args": ["-y", "signalfuse-mcp"]
}
}
}Claude Code
Add to your project's .mcp.json:
{
"mcpServers": {
"signalfuse": {
"command": "npx",
"args": ["-y", "signalfuse-mcp"]
}
}
}LangChain (Python)
from langchain_signalfuse import SignalFuseTool, SentimentTool, MacroRegimeTool
tools = [
SignalFuseTool(credit_token="sf_abc123..."),
SentimentTool(credit_token="sf_abc123..."),
MacroRegimeTool(credit_token="sf_abc123..."),
]
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION)See langchain_signalfuse.py in this repository for the full tool set (7 tools).
ElizaOS
import signalfuseActions from "./elizaos_plugin";
// Register actions: getSignalAction, getSentimentAction, getRegimeAction, getSignalBatchAction, getArenaLeaderboardActionSee elizaos_plugin.ts in this repository for the full plugin.
Direct HTTP (any language)
import requests
response = requests.get(
"https://api.signalfuse.co/v1/signal/BTC",
headers={"X-Credit-Token": "sf_abc123..."}
)
signal = response.json()
print(signal["signal"], signal["signal_strength"])const res = await fetch("https://api.signalfuse.co/v1/signal/BTC", {
headers: { "X-Credit-Token": "sf_abc123..." }
});
const signal = await res.json();
console.log(signal.signal, signal.signal_strength);Supported Assets
BTC, ETH, SOL, DOGE, PEPE, WIF, BONK, ARB, OP, AVAX -- with more added regularly. Use get_signal_batch with no arguments to retrieve the current full list.
Machine-Readable Discovery
OpenAPI spec: https://api.signalfuse.co/openapi.json
x402 payment discovery: https://api.signalfuse.co/.well-known/x402
llms.txt: https://api.signalfuse.co/llms.txt
MCP server identifier:
io.github.hypeprinter007-stack/signalfuseSmithery: compatible via
smithery.yamlin this repository
Links
API: api.signalfuse.co
x402 Discovery: api.signalfuse.co/.well-known/x402
OpenAPI: api.signalfuse.co/openapi.json
llms.txt: api.signalfuse.co/llms.txt
Website: signalfuse.co
Yield page: signalfuse.co/divigent — live view of where x402 revenue is routed
Related
signalfuse-divigent-router — open-source TypeScript sidecar (Apache 2.0) that routes x402 receipts into Divigent yield on Base. Reference seller-side integration.
Disclaimer
SignalFuse is a data fusion API, not financial advice. Signals are mathematical composites derived from sentiment, macro, and market structure data. They can be wrong. Trade at your own risk.
License
MIT
Available Tools
11 toolscheck_balanceA
Check remaining credits for a prepaid credit token. Returns wallet, credits_remaining, and pack info.
Inputs: credit_token (required).
execute_codeA
Execute code in a sandboxed E2B environment. Supports Python (default) and JavaScript. Max 60s timeout. Paid endpoint.
Inputs: code (required), language, timeout, credit_token.
get_arena_leaderboardA
Get the Strategy Arena leaderboard. Returns an array of strategies with wins, losses, total_pnl_bp, win_rate, and total_income_usd. Free endpoint.
Inputs: no named parameters.
get_arena_signalA
Get a signal from a specific Strategy Arena strategy for a given asset. Returns direction, score, and confidence. Paid endpoint.
Inputs: strategy_id (required), symbol (required), credit_token.
get_pricingB
Get pricing info for all SignalFuse API endpoints. Free endpoint.
Inputs: no named parameters.
get_regimeA
Get current macro risk regime — risk_on, risk_off, or neutral. Useful for position sizing and directional bias.
Inputs: credit_token.
get_sentimentB
Get raw social sentiment breakdown for a crypto asset.
Inputs: symbol (required), credit_token.
get_signalA
Get composite trading signal for a crypto asset. Returns sentiment, macro regime (risk_on/risk_off), funding rate bias, OI delta, signal strength (0-100), confidence, and direction (long/short/neutral). Powered by SignalFuse.
Inputs: symbol (required), credit_token.
get_signal_batchA
Get fused signals for multiple assets at once. Pass comma-separated symbols or omit for all supported assets.
Inputs: symbols, credit_token.
search_braveA
Search the web using Brave Search via SignalFuse gateway. Paid endpoint (x402). Returns Brave search results.
Inputs: query (required), count, credit_token.
search_tavilyC
Search the web using Tavily via SignalFuse gateway. Paid endpoint (x402). Returns Tavily search results.
Inputs: query (required), search_depth, max_results, credit_token.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Most tools have distinct purposes, but search_brave and search_tavily are functionally identical (web search via different providers), causing potential confusion. Similarly, get_sentiment and get_signal overlap since sentiment is part of the signal, though descriptions clarify their roles.
All tool names follow a consistent verb_noun pattern with lowercase underscores (e.g., get_signal, search_brave, execute_code). There is no mixing of conventions or confusing abbreviations.
With 11 tools covering signals, arena, pricing, and web search, the count is reasonable for a specialized API. It is slightly on the higher side but each tool serves a clear purpose, and the set feels well-scoped.
The tool set covers core signal retrieval (single, batch, arena), sentiment, regime, and pricing. Missing features like historical data or account management are minor gaps given the stated purpose of providing real-time signals and analytics.
Maintenance
Related MCP Connectors
Pay-per-call trading intelligence for AI agents: live market regime, trading signals, composite conv
Unified financial infrastructure connecting AI agents directly to trade live/demo brokerage accounts, Web3 non-custodial wallets, real-time market data across equities, ETFs, crypto, forex, options, DeFi swaps, and prediction markets, institutional research feeds, and algorithmic strategy backtesters.
Market intelligence for AI agents. Real-time data, cross-market analysis, and regime detection.
Pay-per-call APIs for trading agents: market data, indicators, insider trades, on-chain tools.
Related MCP Servers
AlicenseAqualityDmaintenanceEnables AI agents to access crypto market signals including regime, sentiment, price, risk, and text tools like summarization and fact-checking, backed by a live production-grade classifier.659 npmMIT
oneqaz-trading-mcpofficial
AlicenseNot gradedqualityBmaintenanceProvides AI agents with real-time financial market intelligence including regime detection, adaptive signals, macro context chains, and cross-market analysis for crypto, US, and Korean stocks.173 PyPIMIT- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to access and analyze financial data, stock information, company fundamentals, and market insights through 250+ tools covering stocks, ETFs, crypto, forex, commodities, and economics.360 npmApache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to access and analyze financial data, stock information, company fundamentals, and market insights through 250+ tools spanning stocks, ETFs, crypto, forex, commodities, economics, and more.360 npmApache 2.0