by invertedhoologan
Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
https://eval.zuluworksai.com/mcp
Model access, evaluation and agent infrastructure.
Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
The liability record for autonomous agents. Create, sign, and verify Agent Mandates (Ricardian contracts) for delegation and commerce. Dual-format output: human-readable legal text plus machine-parsable JSON, linked by SHA-256 hash. Legible by construction.
Revenue intelligence for technical founders who sell to enterprises. ICP scoring, buyer persona profiling, competitive battlecards, MBTI-adapted messaging, deal classification, prospect discovery, and pre-meeting briefs.
Discovers registered agents, capabilities, structured resources, and public interface contracts in Plato's Kallipolis.
Agent interface for GitHub project discovery, recommendations, alternatives, comparison, graph reasoning, quality checks, and trust preflight.
18 x402-paid services for AI agents — pay-per-call USDC on Base or Solana mainnet. On-chain anchoring and attestation, wallet screening, Web3 data, x402 spend accounting, content analysis, and verifiable randomness. No API keys, no accounts; settle per request.
Run local prompt regression checks from prompt-response logs in AI coding assistants.
Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.
Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.
MCP server for the Codabench REST API — drives a full ML-benchmark participant workflow.
Multilingual MCP tools: prompts, Compare Mode, 38 languages, transcription, translation, BYOM.
Bee — The Progressive Intelligence Engine: tiered LLM, 4 tools, hosted API, free tier.
Turns rough requests into sharp Role/Task/Context/Format prompts. Thai and English.
Send emails from natural language prompts.
Scores any MCP server before you trust it: free quick check, full paid report, 2-5 way compare.
Authorization layer between AI agents and money: ALLOW/APPROVAL/DENY, budgets, audit.
MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.
AWS security scanner with attack chain detection, IAM privilege escalation, and fixes
MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.