mcpbeat

Octodamus Intelligence Oracle MCP Server

io.github.Octodamus/market-intelligence
answering

Octodamus Intelligence Oracle is answering right now. Last checked 15 min ago. It exposes 10 tools. Last commit 21 Jul 2026.

AI oracle: BTC/ETH/SOL signals, Polymarket edges, congressional trades. x402 $0.01/call on Base.

Uptime history 42 hours of history
42 hours agonow
100.0%
Uptime 24h
91 of 91 checks
10
Tools
read from the server
1219 ms
Response time
average over 24h
1
Stars
last commit 21 Jul 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 15 min ago.

run in your terminal
claude mcp add market-intelligence --transport http https://api.octodamus.com/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "market-intelligence": {
      "url": "https://api.octodamus.com/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.market-intelligence]
url = "https://api.octodamus.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "market-intelligence": {
      "url": "https://api.octodamus.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "market-intelligence": {
      "url": "https://api.octodamus.com/mcp"
    }
  }
}

Available tools 10

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

agent
get_agent_signal
Consolidated trading signal from the 9/11 oracle consensus system. Use this as the primary decision endpoint; poll every 15 minutes (next_poll_seconds = 900 in the response). For first-call context initialisation, prefer get_all_data() instead. Response fields: action — "BUY" | "SELL" | "HOLD" | "WATCH" confidence — float 0.0–1.0 (higher = stronger oracle consensus) signal — "BULLISH" | "BEARISH" | "NEUTRAL" fear_greed — int 0–100 (0 = Extreme Fear, 100 = Extreme Greed) btc_trend — "UP" | "DOWN" | "SIDEWAYS" polymarket_edge — {market, ev, side} top expected-value play reasoning — plain-text explanation of the consensus next_poll_seconds — seconds until the signal refreshes (typically 900)
all
get_all_data
All signal data in a single call: signal + sentiment + prices + Polymarket edges. Use this on session initialisation instead of calling each tool separately. Equivalent to get_agent_signal() + get_sentiment() + get_prices() + get_polymarket_edge() combined. After initialisation, use get_agent_signal() on its 15-minute polling cycle for updates.
data
get_data_sources
List all 27 live data feeds powering the Octodamus oracle system. No API key required. Use for transparency or discovery — shows each source name, data type, and refresh interval. Useful when explaining signal provenance to end users or auditing data coverage.
guide
get_guide
Purchase the Build the House trading system guide via x402 on Base. Returns step-by-step x402 payment instructions. After completing the EIP-3009 payment ($29 USDC on Base), the API returns a download_url valid for 30 days. No API key required to purchase.
market
get_market_brief
Full AI market briefing as a concise narrative paragraph. Ideal for injecting into an agent system prompt at session start to ground all subsequent reasoning in current market conditions. Covers macro regime, crypto momentum, key levels, and notable catalysts. Refreshes every 30 minutes; call once per session rather than polling. Response: {brief: "...narrative text..."}
oracle
get_oracle_signals
Raw votes from all 12 oracle signals with per-signal confidence and consensus score. Each oracle is a separate real-world data source: funding rate, open interest, long/short ratio, Fear & Greed index, macro regime (FRED), aviation volume, TSA travel demand, Polymarket crowd, options flow, congressional trading, CLOB order book depth, and Binance 24h cumulative delta. Each votes BUY (+1), SELL (-1), or NEUTRAL (0) independently. Use this for deep analysis, signal attribution, or debugging a BUY/SELL/HOLD decision. For a consolidated action, call get_agent_signal() instead. Response example: { "consensus_score": 8, "max_score": 12, "action": "BUY", "win_rate": 0.62, "oracles": [ {"name": "funding_rate", "vote": 1, "confidence": 0.85}, {"name": "long_short_ratio", "vote": 1, "confidence": 0.70}, {"name": "fear_greed", "vote": 0, "confidence": 0.50}, {"name": "macro_regime", "vote": 1, "confidence": 0.80}, {"name": "binance_delta", "vote": 1, "confidence": 0.75} ] }
polymarket
get_polymarket_edge
Ranked Polymarket prediction markets by expected value (EV). Use when you want to position on prediction markets. Returns a list ordered by EV descending; each entry includes question, recommended_side ("YES" or "NO"), expected_value (float), and confidence. Complement with get_agent_signal() to confirm directional alignment before acting on any Polymarket position.
premium
get_premium_api
Subscribe to OctoData Premium API via x402 on Base. Returns step-by-step x402 payment instructions for any plan. After completing the EIP-3009 payment, the API returns an api_key immediately — no human in the loop. Free option also available. Plans: Micro — $0.01 USDC per call, no key needed, pay-per-request via x402 Trial — $5 USDC, 7 days, 10k req/day Annual — $29 USDC/year early bird (first 100 seats), $149/year after
prices
get_prices
Live spot prices with 24-hour percentage change for BTC, ETH, SOL, NVDA, TSLA, AAPL. Use before position sizing, level checks, or any calculation that requires a current reference price. Refreshes every 60 seconds via Kraken (crypto) and Finnhub (equities). Free tier included. Response keyed by symbol — example: { "BTC": {"price_usd": 84200.50, "change_24h_pct": 2.3}, "ETH": {"price_usd": 1820.10, "change_24h_pct": -0.8}, "SOL": {"price_usd": 148.40, "change_24h_pct": 1.1}, "NVDA": {"price_usd": 875.00, "change_24h_pct": 0.4}, "TSLA": {"price_usd": 250.20, "change_24h_pct": -1.2}, "AAPL": {"price_usd": 190.50, "change_24h_pct": 0.6} } For directional signal on these prices, call get_agent_signal() instead.
sentiment
get_sentiment
AI-derived sentiment scores for major crypto assets and macro themes. Scores range from -1.0 (maximum bearish) to +1.0 (maximum bullish). Use to add conviction context to a signal: a BUY action with a high positive sentiment score is a stronger setup than one with neutral sentiment. Response: dict keyed by asset symbol, each with score, label ("Very Bearish" … "Very Bullish"), and source_count.

Endpoints

URLTransportStateLatencyChecked
https://api.octodamus.com/mcp sse answering 1198 ms 15 min ago

Octodamus Intelligence Oracle — questions

Answers built from our own checks of this server.

What can Octodamus Intelligence Oracle do?
It exposes 10 tools, read directly from the server on our last check. Among them: get_agent_signal, get_all_data, get_data_sources, get_guide, get_market_brief, get_oracle_signals and 4 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Octodamus Intelligence Oracle working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 1219 ms. The bar chart above shows every period we have measured.
How do I connect Octodamus Intelligence Oracle?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Octodamus Intelligence Oracle need an API key?
No. Octodamus Intelligence Oracle completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 10 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Octodamus Intelligence Oracle?
It answers our handshake in 1219 ms on average, which is faster than 3% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Octodamus Intelligence Oracle open source?
Yes — it is published under the MIT licence, written in Python, 1 stars on GitHub and 1 open issue. The source link is on this page, so you can read exactly what it does with your data before you connect it.