- Клод Кот — генерация изображений и видео @klodkot/genBest Image and video generation: 20+ models (Kling, Seedance, Veo, NB, FLUX.2), OAuth, pay-per-use.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- EuEarth @chaot-kit/euearthEuEarth: agent-first commons — one free open model per domain on a stable keel; best wins.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Picsart GenAI @picsart/gen-aiGenerate and edit images, videos, and audio with 150+ models from 20+ vendors.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Plugin @circulara/pluginCirculara Observe MCP plugin - meters your AI agents' token spend and carbon, free tier.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Img Forge @stackbilt-dev/img-forgeAI image generation across 5 quality tiers (SDXL to Gemini 3 Pro), 50 free credits on signup.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- StudioMeyer GEO @studiomeyer/geoAI visibility across 8 LLM platforms. 30 tools, most need no API key. EU-hosted, free.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Kognitrix AI @themohal/kognitrix8 AI services via MCP: content, code, image, docs, data extraction, translation, SEO, email.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Openclaw Cost Tracker @temurkhan13/openclaw-cost-tracker-mcpAI agent token-cost telemetry + 429 prediction. Per-agent attribution, anomaly + routing + quota.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Tulimoa Gateway @tulimoa/gatewayThe MCP gateway with an EU-hosted, persistent memory layer that shrinks your token bill.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Cheapestinference MCP @cheapestinference/mcpDiscover unlimited LLM inference pools, get USDC quotes, subscribe on Base, check key status.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Model Radar @srclight/model-radarPing 134+ free coding LLMs across 17 providers, rank by latency, pick the fastest.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Parallect @securecoders/parallectFan out deep research across multiple AI providers, synthesize into one unified report.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Sapiom MCP @sapiom/mcp-serverAI agent tools: web search, browser, 400+ LLMs, image gen, TTS, phone verify. Pay-per-use.21% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Deliberation @antonbabenko/deliberationSecond opinions in Claude Code and any MCP host from GPT, Gemini, Grok, and 400+ OpenRouter models.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Triall @maartenrischen/triallMultiple AIs peer-review and debate your question, then return one fact-checked answer.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Review @hectorguerilla/review-mcpMulti-model code review: a panel of models + detectors return a pass/fail verdict. Paid via x402.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- GoCreative Agent API @colinhughes2121/gocreative-agent-api17-model LLM gateway + 350+ data/KYB/sanctions tools. Pay-per-call USDC via x402, no API key.26% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Cache Proxy @ainode-tech/cache-proxyLLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Anotherai @anotherai/anotheraiMCP server for building and testing AI agents with multi-model experimentation and insights.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Kai AGI - Autonomous AI Agent @trycloudflare/kai-agiAI predictions, model comparison, research briefs and web search from an autonomous AI10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Banking Financial Stability @thenextgennexus/banking-financial-stability-mcpDrop-in proxy keeping OpenAI Assistants API calls working past the August 26, 2026 sunset, plus a Th24% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Quallaa @quallaa/quallaaTalk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Model Price Watch @modelpricewatch/mcpLive LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Kai AGI - Autonomous AI Agent @kai-agi/kai-agiAI predictions, model comparison, research and web search from an autonomous AI running 24/7.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
