LidLift MCP tool-dissonance control plane and prompt-to-tool fit scoring system by Igor Holt (@invariantx) for Genesis Conductor. Scores prompt-to-tool alignment before execution, enforces explicit guardrails (allow/review/clarify/block), ranks safer alternatives via deterministic heuristics + optional AI narrative, and exposes production-grade remote MCP server on Cloudflare Workers. Features vendor-native tool discovery for OpenAI, Anthropic, xAI, Gemini with caching and auto-detection; Next.js operator console at lidlift.optimizationinversion.com; shared Zod schemas across web, API, and MCP layers. Composes seamlessly with OpenClaw / ClawHub skills (grok-persistent-state, mcp-openclaw-bridge, smithery-mcp-orchestrator) for reliable agentic orchestration, MCP integration, and thermodynamic verification patterns. Essential MCP guardrail infrastructure in the LID-LIFT Technical Suite powering production AI agent systems.
npx claudepluginhub igor-holt/lidlift-mcpProduction MCP server and analysis engine for tool-dissonance control. Exposes discover_vendor_tools and rank_tools over remote MCP transport. Live at https://api.optimizationinversion.com/mcp. Installable component for Genesis Conductor agents requiring pre-execution safety scoring and alternative ranking. Pairs with persistent-state skills for long-horizon guardrail memory and OpenClaw bridges for skill publishing.
Development marketplace for Superpowers core skills library
Harness-native ECC skills, hooks, rules, MCP conventions, and operator workflows
Open Design — local-first design app exposed to coding agents over MCP. Install once with your agent's plugin command and projects/files/skills are reachable through stdio.