- Token Optimizer @rccola990-cloud/mcp-token-optimizerCut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- modelmux @pure-maple/modelmuxModel multiplexer — route tasks to Codex, Gemini, and Claude CLIs with smart routing.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Oroute @netclaus/orouteAuto-route AI requests to 13 models (Claude, GPT, Gemini, Qwen, DeepSeek). 57% cost savings.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Huggingface @mrfentmen/huggingface-mcpHugging Face models and datasets. No key required for public data.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MostAI @most-ai-com/mostai-mcpGenerate images, video, music, speech and text with 60+ models through your MostAI account.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Kongen Labs — Pattern Intelligence @fisnik/kongen-mcpLLM reasoning regime detection, cross-domain pattern transfer, and model routing.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Clawbackai @rckl88/clawbackai-mcpLLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Seracade @rckl88/seracadeLLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- TokenEyez @reemedri/tokeneyezTrack every AI token across Claude, ChatGPT, Gemini, Cursor, and Claude Code.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- LiteLLM Multi-Model API @berriai/litellm-mcpAccess 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Payment @apoth3osis-ai/agent-payment-mcpSecure MCP router providing access to AgentPMT's pay-per-use AI tools marketplace.13% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Leanroute MCP @leanroute/mcp-serverLeanroute MCP: route to 13 LLM providers, check pricing/usage/credit, manage keys from any agent.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Gate @spideriq/gateSpiderIQ Gate: SpiderGate LLM gateway (completions, models, usage, traces)8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AgentUtility Model Router @agentutility/mcp-model-routerMCP server for the @agentutility model-router cluster — pay-per-call x402 tools, no API keys, USDC…8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Glint Model Hub — image generation for AI agents @zzzjy765/glint-imageGenerate and edit images with every image model on the platform. Returns the image to the agent.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Glint Meet — every global model for your agent @zzzjy765/glint-meetCall every global AI model through one OpenAI-compatible API. One key, all models.18% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Animica @animica/animicaAnimica chain data, free keyless AI inference, quantum randomness, x402 discovery, mining stats.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Baton @ribato22/batonMulti-model AI orchestration: plan a task DAG, route each task to the best capable model.Not assessed yet.Runs on your machine, installed from PyPI.
- Mafdet MCP @mafdet/mcpRead-only Mafdet AI account tools (models, balance, usage, subscription) and docs search.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- 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.
- 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.
- 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.
- 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.
