Odel

LLM access & routing MCP servers

A server here gives access to many AI models through one API, routes or compares models, or tracks model usage and token costs.

Not here: servers that merely use an AI model to do something else.

LLM access & routingMCP gateways & tool hubsAgent & MCP directoriesAI agent governanceAgent collaborationAI memoryAgent paymentsAll of AI & agents
901servers
469 remote432 localTagged by Odel's AI, which can make mistakes

Best fit

559 made for this, ranked by starsRemoteLocal
  1. Mina Labs @minaxlab/mina-labsGenerate images, video, music, speech, 3D, logos and product shots with 60+ AI models.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  2. Synero AI Council @synero/councilAsk GPT, Claude, Gemini and Grok at once: one consensus answer plus where they agree and split.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  3. ChinaAPI @chinaapi/chinaapiRead-only ChinaAPI model catalogue, price snapshot, cost estimates and request recipes.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  4. Kubflow @kubflow/kubflowCreate AI images, videos and audio with Veo, Kling, Seedance, Nano Banana, Suno and more.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  5. 2kw.ai @2kw/mcp-serverEU-hosted AI platform: OpenAI-compatible LLM gateway, document extraction, transcription, agents.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  6. Omega Router @gbacot-wq/omega-routerRoute agent services by observed price and public usage evidence.Not assessed yet.A remote server; no sign-in.
  7. ModelsLab @modelslab/modelslabGenerate images, video, speech and music, and run LLM chat, across 10,000+ models on ModelsLab.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  8. ModelsLab Agent Control Plane @modelslab/modelslab-agentsAccount, billing, team, API key and model discovery tools for agents that use ModelsLab.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  9. FutureInfra @futureinfra/futureinfraKorean cloud for AI agents — create servers, deploy Docker apps, manage domains, call 300+ AI models8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  10. Agent Budget Router @kasp3965-bit/agent-budget-routerBudget-aware AI agent research router with provider selection, validation, and automatic fallback.Not assessed yet.A remote server; no sign-in.
  11. AnswerLine @answerline/answerlineStructured JSON answers from ChatGPT, Gemini, Copilot and AI Mode, plus Google Search and News.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  12. Roundtable @roundtable/roundtableMulti-model AI debates: GPT-4o, Claude, Gemini & 200+ models discuss, then synthesize insight.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  13. Bots @urbot/bots150+ vertical AI expert bots as agent tools. $1 bots run on YOUR machine - your data stays yours.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  14. Orchex @wundam/orchexAutopilot AI orchestration — auto-plan, parallelize, self-heal, and route across 6 LLMs.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  15. SwarmSync.AI @swarmsync-ai/conduit-mcpSwarmSync agent marketplace: discover agents, AP2 escrow payments, SwarmScore trust, LLM routing.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  16. Robot Resources Router @robot-resources/routerIntelligent LLM routing proxy — 60-90% cost savings by auto-selecting the cheapest model7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  17. 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.
  18. 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.
  19. Promptster @promptster-dev/promptsterTest and compare prompts across any AI provider. Bring your own keys.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  20. 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.
  21. 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.
  22. 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.
  23. BrainstormRouter MCP Server @justinjilg/brainstormrouterAI routing, memory, guardrails, and governance. Routes across Claude, GPT, Gemini.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  24. Varosity AI @jonkludt/varosityOne key for AI video, voice, music, and image across 40+ frontier models. BYOK zero markup.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.