signallord-mcp-server
Bitcoin market intelligence MCP server. Exposes Signal Lord's composite gauge scoring, on-chain and macro regime signals, and market data to AI agents.
README
signallord-mcp-server
MCP server for Signal Lord — know which Bitcoin regime you're in and the probabilities of what happens next.
Not another price feed. Signal Lord tells AI agents where Bitcoin is in its market cycle, what similar periods looked like historically, and what usually happens next — backed by 20+ real-time indicators and pattern matching against documented cycle history.
Quick Start
1. Install
npm install -g signallord-mcp-server
Requires Python 3.10+ with pip on your PATH. Dependencies install automatically.
2. Get an API Key
Sign up at signallord.io, then generate a key:
# After logging in, via the API:
curl -X POST https://signallord.onrender.com/api/keys/generate \
-H "Authorization: Bearer YOUR_JWT_TOKEN" \
-H "Content-Type: application/json" \
-d '{"label": "my MCP key"}'
Save the returned sk-sl-... key — it's shown only once.
3. Configure
export SIGNALLORD_API_KEY=sk-sl-your-key-here
export SIGNALLORD_API_BASE_URL=https://signallord.onrender.com
4. Run
signallord-mcp
Server starts on http://localhost:8100 (streamable HTTP transport).
5. Connect to Claude Desktop
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"signallord": {
"command": "signallord-mcp",
"env": {
"SIGNALLORD_API_KEY": "sk-sl-your-key-here",
"SIGNALLORD_API_BASE_URL": "https://signallord.onrender.com"
}
}
}
}
Or connect via URL:
{
"mcpServers": {
"signallord": {
"url": "http://localhost:8100/mcp"
}
}
}
What You Get
The question every trader asks: "What's Bitcoin doing right now and what happens next?"
Signal Lord answers with regime detection, not price predictions:
| Instead of... | Signal Lord gives you... |
|---|---|
| "BTC is $84,000" | "Bitcoin is in a High Vol Chop regime, similar to March 2025 tariff volatility" |
| "Fear & Greed is 45" | "35% chance of consolidation, 30% chance of V-recovery based on 4 similar historical periods" |
| "ETF flows were +$200M" | "Institutional score 6.2/10 — steady accumulation but not FOMO. Pattern matches post-halving 2024 buildup" |
Tiers & Rate Limits
| Tier | Regime Detail | Rate Limit | Data |
|---|---|---|---|
| Free | Regime + probabilities + top match name | 10/min, 500/day | 4 gauges + basic market data |
| Premium | Full historical matches + catalysts + feature vectors | 30/min, 2000/day | All 8 gauges + ETF/on-chain + Odin AI |
| Pro | Everything + signals | 60/min, 5000/day | Full platform access |
Tools (26)
Regime Detection (flagship)
| Tool | Tier | Description |
|---|---|---|
signallord_get_regime |
Free* | Current regime, historical matches, outcome probabilities |
signallord_get_regime_history |
Free | Regime evolution over time from daily snapshots |
Gauges
| Tool | Tier | Description |
|---|---|---|
signallord_get_composite_score |
Free | Composite 0-100 score with regime label |
signallord_get_gauge_breakdown |
Free* | Individual gauge scores (4 free, 8 premium) |
signallord_get_gauge_history |
Free | Historical scores for trend analysis |
Odin AI
| Tool | Tier | Description |
|---|---|---|
signallord_get_odin_analysis |
Free* | AI market analysis (basic free, enriched premium) |
signallord_ask_odin |
Premium | Ask Odin a question about BTC markets |
Market Data
| Tool | Tier | Description |
|---|---|---|
signallord_get_btc_metrics |
Free* | Price, volume, derivatives (+ on-chain on premium) |
signallord_get_institutional_data |
Premium | ETF flows, Coinbase premium, CME basis |
signallord_get_macro_indicators |
Free | DXY, VIX, Fear & Greed, liquidity stack |
signallord_get_what_changed |
Free | Day-over-day market changes |
Signals & Analytics
| Tool | Tier | Description |
|---|---|---|
signallord_get_btc_vix_correlation |
Premium | BTC vs VIX correlation + spike detection |
signallord_get_btc_gold_ratio |
Premium | BTC vs Gold normalized comparison |
signallord_get_etf_flow_history |
Premium | Daily ETF flow history (since Jan 2024) |
signallord_get_exchange_flow_history |
Premium | Exchange flow accumulation/distribution |
signallord_get_liquidation_data |
Free | Liquidation momentum scoring |
signallord_get_odin_track_record |
Free | AI prediction accuracy and learned patterns |
Cycle Indicators (v1.2.0)
| Tool | Tier | Description |
|---|---|---|
signallord_get_pi_cycle |
Premium | 111DMA vs 350DMA·2 cross — cycle-top warning |
signallord_get_realized_price |
Premium | Spot vs on-chain cost basis + reclaim/loss events |
signallord_get_reserve_risk |
Premium | Price/HODL Bank ratio banded into cycle phases |
signallord_get_mtf_trend |
Premium | D/W/M trend alignment composite (-3 to +3) |
signallord_get_hash_ribbons |
Premium | 30/60-day hashrate MA cross + 30d divergence z-score |
signallord_get_capitulation_score |
Premium | Composite of volume, liquidations, funding, OI, velocity |
Probability Playbooks (v1.2.0)
| Tool | Tier | Description |
|---|---|---|
signallord_get_cycle_bottom_probability |
Premium | Weighted accumulation playbook score (0-100) |
signallord_get_cycle_top_probability |
Premium | Weighted distribution playbook score (0-100) |
Meta (v1.2.0)
| Tool | Tier | Description |
|---|---|---|
signallord_get_data_health |
Free | Which signals are currently stale due to upstream data issues |
* Returns limited data on free tier, full data on premium.
Example: Regime Detection Response
{
"regime": "high_vol_chop",
"regime_label": "High Vol Chop",
"regime_confidence": 0.72,
"regime_duration_hours": 168.5,
"most_likely_outcome": "consolidation",
"most_likely_outcome_label": "Consolidation — went sideways for weeks",
"most_likely_probability": 40.0,
"outcome_probabilities": {
"consolidation": 40.0,
"v_recovery": 30.0,
"reversal": 20.0,
"correction": 10.0
},
"expected_move_pct": -2.5,
"expected_timeframe_days": 35,
"most_similar": {
"name": "March 2025 Tariff Volatility",
"date_range": "2025-03 to 2025-04",
"similarity": 0.89,
"outcome_description": "Oscillating as market digests policy uncertainty."
},
"historical_matches": ["...3 most similar periods with full details..."]
}
Environment Variables
| Variable | Default | Description |
|---|---|---|
SIGNALLORD_API_KEY |
(empty) | Your sk-sl-... API key |
SIGNALLORD_API_BASE_URL |
http://localhost:8000 |
Signal Lord backend URL |
MCP_SERVER_PORT |
8100 |
Server listen port |
Testing
# Syntax check
python -m py_compile server.py
# Tier verification (against production)
SIGNALLORD_PREMIUM_KEY=sk-sl-xxx python test_tiers.py
# MCP Inspector
npx @modelcontextprotocol/inspector
Architecture
AI Agent (Claude, Cursor, etc.)
| MCP Protocol (Streamable HTTP)
v
signallord-mcp-server (port 8100)
| HTTP + X-SIGNALLORD-API-KEY header
v
Signal Lord backend API
| Regime Detection + Historical Pattern Matching
| 20+ real-time indicators + 8 data sources
v
PostgreSQL + Odin AI + Pattern Database
The MCP server is a stateless protocol adapter. All data, auth, rate limiting, and regime detection is handled by the backend.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.