- Anvx @tje8x/anvxTrack and optimize AI API spending across 16 providers with live pricing.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- LLMTest @tjacquesson/llmtest-mcpBenchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Telegraph @telegraphprotocol/telegraphDecentralized AI inference (weather, deepfake detection, LLMs) with x402 USDC micropayments.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Apexapi @apexapi/apexapi-mcpCall 120+ AI models and live web context (scrape/crawl/extract) from any MCP client with one key7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- ModelRunner @modelrunner/mcpRun 100+ AI models — image, video, audio, 3D — through one API with pay-per-use billing.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- WebVoice @supermarco74/webvoice-mcpWebVoice MCP: chat, TTS, STT, translate, images. Email signup, welcome credits, optional Solana.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Hive Compute @srotzin/hive-mcp-computeHiveCompute MCP Server — decentralized inference router for AI agents10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AgentPool @sidduhere/agentpoolSee each coding-agent subscription's live limits and offload work to one with headroom.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Modelcostsaver @sachinuppal/modelcostsaverOffline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Qwen MCP @rocnubie/chat-mcpQwen AI Chat guide to Qwen3.6-Plus and qwen3.6-flash with practical notes on 1M context, coding7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- DeepSeek FR MCP @rocnubie/deepseekfr-mcpIndependent French workspace for evaluating DeepSeek-V3-class chat and DeepSeek-R1 reasoning.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- QSP @qso-graph/qsp-mcpQSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)Not assessed yet.Runs on your machine, installed from PyPI.
- Polydev @polydev-ai/polydevQuery GPT-5, Claude, Gemini, and Grok simultaneously through one MCP server8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- PathCourse Health (PCH) @pathcourse-health/mcp-serverCheaper LLM inference, USDC agent payments via x402, agent identity / reputation lookup.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MyAi @myaitoken/myai-mcpDecentralized AI inference on Base: OpenAI-compatible chat via community GPUs, paid in MYAI9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Sprout MCP @mepsopti/sprout-mcpModel-tiered content pipeline — cheap models seed, expensive models verify5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- NetIntel @kjgueye/netintel-mcpMCP server for NetIntel — DNS, SSL, WHOIS, email security, OSINT via x402 micropayments9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- The Realms of Omnarai — Memory Engine @justjlee/omnarai-mcpDeliberation + live 5-model council divergence over the Omnarai multi-AI attributed corpus.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Offline @gabrielmahia/offline-mcpMCP server enabling offline-first agent operation over intermittent connectivity4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- ChipsAI MCP Server @fgasparetto/chipsai-mcpMCP server for ChipsAI — manage chatbots, conversations, and AI models5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- SkillFM Claude Code Token Usage @ericm1018/skillfm-claude-code-token-usage-costClaude Code token usage, cost visibility, and SkillFM Beacon AI health checks for MCP agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Adclip @dreliq9/adclipAd creative generation via MCP — copy and static images from a JSON brief. Keyless.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- DCP @dhnpmp-tech/dcp-mcpSaudi sovereign AI compute: OpenAI-compatible inference, rent GPU pods, manage storage.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Cost Tracker Router @dbsectrainer/mcp-cost-tracker-routerReal-time cost awareness for MCP agent workflows4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
