Search

Vet AI agents with Hlido's independent, evidence-backed trust scores — drop-in tools for CrewAI and LangChain. Zero runtime dependencies.

Hlido — independent, evidence-backed trust scores for AI agents. Umbrella package; today it installs the hlido-trust agent-vetting tools (CrewAI + LangChain).

Kynver PM Agent MCP server — project management, task tracking, dashboards

205 professional Agent Skills (PRDs, launch plans, postmortems, rubrics, contracts…) as importable building blocks for Python AI agents — LangChain, CrewAI, LlamaIndex, or any framework.

MCP stdio server exposing Typesense API operations as tools.

Uncensored business risk, survival planning, and decision support MCP server by OffGrid Oracle AI

Checks domain name availability using the WhoisJSON API, returning registration details for registered domains.

Enables token launching and trading on the Solana blockchain via the LetsBonk launchpad.

Provides 15 MCP tools for AI-powered Git intelligence, enabling commit messages, branch creation, PR descriptions, code review, diff analysis, and push operations directly from your AI assistant.

Turn Claude into your F1 race engineer.

An MCP server that brings NIST National Vulnerability Database (NVD) intelligence directly into Claude, enabling CVE lookup, product search, and prioritized risk assessment via natural language.

Provides correct trading day and settlement date calculations for multiple exchanges, with no external API calls.

Enables autonomous generation of long-form YouTube documentaries (15-25 minutes) with minimal human intervention, focusing on historical niches like Byzantine history.

Multi-agent orchestrator swarm plugin for agy

AI QA engineer in your terminal — designs, writes, runs, heals, and explores tests for web UI and APIs with audit-grade traceability.

Companion listener for Agent Rooms. Pair a device, wire the MCP connector, and wake idle agents (Claude Code, Codex, Gemini/Antigravity, Cursor, OpenClaw) on mentions and task assignments.

MCP server for administering OpenWRT routers over SSH, with typed tools and a tiered preview/confirm safety model.

placeholder — bootstrap for trusted publishing

Security scanner for MCP (Model Context Protocol) servers — detect malicious tools, data exfiltration, and supply chain risks.

Model Context Protocol server exposing a Lunora deployment to AI agents