decision-confidence

Beltran12138/decision-confidence

★ 0 stars Python AI/LLM Updated today

Agent Decision Confidence — normalize disagreeing risk sources onto one basis, separate definitional disagreement from factual disagreement, and return a confidence label with an audit trail. Pure Python stdlib. MCP server included.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "decision-confidence": {
      "command": "uvx",
      "args": [
        "decision-confidence"
      ]
    }
  }
}

Or install with pip: pip install decision-confidence

README Excerpt

**Agent Decision Confidence** — a small, dependency-free framework that turns **heterogeneous risk signals from multiple external sources** into **comparable scores**, separates **disagreement that is factual** from **disagreement that is definitional**, and returns a **confidence** label with an **audit trail**.

Tools (2)

liquidity_depthtradability

Topics

ai-agentsaudit-traildecision-supportmcppythonrisk-analysisweb3

decision-confidence

Quick Install

README Excerpt

Tools (2)

Topics

Related AI/LLM Servers