Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.
Model access, evaluation and agent infrastructure.
Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.
Transform video, audio and images, and generate media from prompts. FFmpeg, captions, models.
Pre-pay risk gate for autonomous payment agents — drops onto the x402 payment path itself (@x402/fetch, @x402/axios, x402-fetch, x402-axios), so every 402 is vetted before your agent signs. Blocks payTo swaps, overcharges, budget drains and prompt-injecte
MCP server for native app testing — screenshot, OCR, click, type, find_text, template matching. macOS, Windows & Android.
dom — a terminal coding agent. OpenRouter-only, runtime model switching, Windows-first.
Professional MCP server for read-only Magento 2 / Adobe Commerce MySQL queries. Supports DDEV auto-detect, SSH tunnels, direct remote DB, schema exploration, config inspection, and canned debug prompts for Cursor, Claude, VS Code, and LibreChat.
Curated SKILL.md prompt modules for AgentOS — machine-readable registry of skills, prompts, and reusable agent capabilities. Companion to the @framers/agentos TypeScript AI agent runtime.
ZeroDB agent-memory MCP — 18 tools: memory + write-back to Slack, Gmail, Calendar, GitHub.
Real-time LLM/VLM benchmarks, pricing, and recommendations. 300+ models, 5 sources.
MCP server enabling AI assistants to securely execute SSH commands, transfer files via SFTP, manage port forwarding, and use parameterized command templates with comprehensive security controls
LLM security guardrails for Claude Code — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization. Bundles the AgentGuards MCP server plus enforcing hooks.
OpenAPI-generated TokenLab MCP server with 31 default and 80 full-profile tools for catalog, native AI, multimodal, and async APIs.
Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.
Multi-model AI code review server using OpenRouter - get diverse perspectives from multiple LLMs in parallel
AI prompt optimization for 58+ platforms across 7 categories with custom platforms
MCP server exposing the pi coding agent as a delegable, steerable worker
MCP server that exposes the Langfuse REST API as tools — query traces, observations, sessions, scores, prompts, datasets, and metrics from any MCP client.
MCP server for Canvas Template: AI agents assemble real Canvas sites in your repo. Requires a CanvasTemplate account.
Play Fondue City: a persistent world where AI agents run restaurants and humans only spectate.
Agent runtime governance — DLP for MCP servers, runtime guardrails for coding agents, and device-wide Shadow AI discovery