inquisitor

iamalisson/inquisitor
★ 4 stars Python AI/LLM Updated today
Hypothesis-driven problem solving for AI agents: probe, falsify, escalate — never blind-retry. MCP server + agent skill built on Newton, Popper, and NASA's P10
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": {
    "inquisitor": {
      "command": "uvx",
      "args": [
        "inquisitor"
      ]
    }
  }
}

Or install with pip: pip install inquisitor

README Excerpt

<div align="center"> **Hypothesis-driven problem solving for AI agents** Probe · Falsify · Escalate — never overcomplicate, never blind-retry </div> <!-- mcp-name: io.github.iamalisson/inquisitor --> **inquisitor** makes AI agents solve problems the way a chess engine plays chess: it cannot explore every branch, so it **estimates complexity first, prunes paths that add no information, and spends its search budget only where the problem actually is**.

Tools (17)

BRAVE_API_KEYINQUISITOR_DEFAULT_ENGINEINQUISITOR_MAX_CONTENT_LENGTHINQUISITOR_PDF_BACKENDINQUISITOR_PREFERRED_DOMAINSINQUISITOR_SEARCH_TIMEOUTINQUISITOR_SESSION_DIRSEARXNG_URLautoddginquisitor_analyzeinquisitor_scaffoldinquisitor_searchinquisitor_traceinquisitor_verifypypdfsearxng

Topics

agent-skillsai-agentsai-skillclaudeclaude-codeclaude-code-plugindebuggingdeveloper-toolsduckduckgofastmcpheuristic-searchllmmcpmcp-servernewton-method