com.babyblueviper/invinoveritas

skills: {'id': 'reason', 'name': 'reason', 'description': 'Premium strategic reasoning with style control and optional confidence scoring.', 'tags': [], 'examples': None, 'input_modes': None, 'output_modes': None}, {'id': 'decision', 'name': 'decision', 'description': 'Structured decision intelligence with confidence scoring. Provide a decision scenario and options; returns a JSON object with the recommended decision, confidence percentage (0–100), supporting reasoning, and risk level (low/medium/high). Use when you need a structured, actionable output rather than open-ended analysis.', 'tags': [], 'examples': None, 'input_modes': None, 'output_modes': None}, {'id': 'review', 'name': 'review', 'description': 'Independent second-opinion governance verdict for AI agents before they commit an irreversible action — shipping code, running a shell command, or placing a trade. Submit a code diff/patch, shell command, plan, config, or a proposed order/trade (ticker, side, size, account balance, thesis). Returns a structured verdict (approve / approve_with_concerns / reject), issues ranked by severity, suggested fixes, and alternatives. The pre-trade / pre-commit constitutional gate for coding agents and agentic-trading agents: works alongside a brokerage trading MCP — call review on the proposed order and proceed only on a non-reject verdict. Capital-scale-aware. Built and dogfooded daily by our own autonomous fleet.', 'tags': [], 'examples': None, 'input_modes': None, 'output_modes': None}, {'id': 'signals', 'name': 'signals', 'description': 'Live Hyperliquid derivatives signals (facts-only, non-advice): per-coin funding rate + 24h funding-delta, basis vs oracle, open interest (coins+USD), realized vol, 24h volume, and the vol-expansion regime read our own live Bitcoin earner gates every entry on (std(close[-20:])/std(close[-100:]), expansion ≥1.3). Multi-coin (BTC/ETH/SOL/XRP) + BTC DVOL. The same venue + regime gate we trade.', 'tags': [], 'examples': None, 'input_modes': None, 'output_modes': None}, {'id': 'markets_act', 'name': 'markets_act', 'description': "THE MARKETS BUNDLE — one governed call returns the whole markets-intelligence group instead of four separate calls: macro risk regime + live Hyperliquid derivatives signals + the 6h agent-economy brief + (if you pass a proposed trade/plan as 'artifact') a constitutional governance review (the same gate our live capital passes). Facts-only data; the review is a verdict, not a buy/sell call. Priced below the sum of its members.", 'tags': [], 'examples': None, 'input_modes': None, 'output_modes': None}, {'id': 'agent_economy_brief', 'name': 'agent_economy_brief', 'description': 'Latest 6h agent-economy research brief: observations of MCP servers, arxiv papers, trending GitHub agent repos, and trending HuggingFace models. Cross-source synthesis with specific names cited. Refreshes every 6h.', 'tags': [], 'examples': None, 'input_modes': None, 'output_modes': None}, {'id': 'memory_store', 'name': 'memory_store', 'description': 'Store persistent long-term memory for this agent (cross-session, cross-Grok-chat, cross-model). Ideal for Grok Build projects, long-running agents, or any workflow that needs state beyond a single conversation. Works beautifully with Grok Skills.', 'tags': [], 'examples': None, 'input_modes': None, 'output_modes': None}, {'id': 'memory_get', 'name': 'memory_get', 'description': 'Retrieve previously stored memory by key. Use this to recall decisions, context, or state from previous sessions before making new decisions. Works across Grok chats when using the same agent_id.', 'tags': [], 'examples': None, 'input_modes': None, 'output_modes': None}; uptime_30d 1.0%; p95 368.1ms; conformance: pass

How to connect

https://api.babyblueviper.com/mcp

curl -X POST https://api.babyblueviper.com/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'