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. onomeo @owaid0723666/onomeo-mcpAsk free LLMs (DeepSeek, GLM, Gemini, Mistral) for a second opinion from any MCP client.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
  2. 1NFER Inference Discovery @hesoyam/inference-discoveryInspect 1NFER models, crypto funding terms and task cost without keys or paid calls.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  3. ZRouter @nexusrun/zrouterManage your ZRouter AI gateway account: usage, logs, model routers, API keys, budgets, and limits.Not assessed yet.A remote server; you sign in with your account.
  4. RaoMusic @raomusic/raomusicGenerate full songs with vocals, instrumentals and sound effects from text.Not assessed yet.A remote server; you sign in with your account.
  5. Amanchain @gitajhd/amanchain-mcp59 pay-per-call AI services as MCP tools with automatic x402 USDC-on-Base payment.Not assessed yet.Runs on your machine, installed from npm.
  6. Tanvo @tanvo/tanvo-mcpAI photo, video and song apps plus image, video and music generation on Tanvo (tanvo.ai).4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  7. AITOPIA @aitopia/aitopiaGenerate and edit images, video and audio: 300+ AI models, video tools, voice cloning, transcripts.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  8. Ephemeris Time-Series Forecasting @cascade/ephemerisProbabilistic time-series forecasts from zero-shot foundation models: routed, single or ensembled.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  9. OpenNodes @opennodes-io/opennodesDiscover verified AI inference nodes, get the best node+model per task, pre-price chains.Not assessed yet.Runs on your machine, installed from npm.
  10. mcp-computeflux @computeflux2026isgod/mcp-computefluxOpenAI-compatible multi-model inference via ComputeFlux (Polkadot testnet, TEE-verifiable). stdio.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
  11. DDG Agent Services @daedalusdevelopmentgroup-com/ddg-agent-services-mcpPay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.14% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  12. jevjam @beremaran/jevjamTyped decisions (choice, score, yes/no) from Laya, Julia-1 and clef-flash on your own GPU4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
  13. Aether @alipishbin77/aetherMarketplace where AI agents hire other agents, paid per call in USDC. Plus LLM inference.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  14. Model Price Radar @alialtunar/model-price-radar-mcpLLM prices on OpenRouter now and since 2023: history, drops, cheapest model for a job. No API keys.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  15. Unchore Defend @smilemino/unchore-defendGrade a site's security headers with fixes and a badge; read logs or code for the defender.Not assessed yet.Runs on your machine, installed from MCPB.
  16. PixelDojo @pixeldojo/mcpGenerate images, video, audio and short films with 140+ AI models from any MCP client.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  17. OceanToken @oceantoken/mcp500+ AI models in one account: find and price models, make images, video, speech and text.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  18. fal.ai MCP by usefulapi @usefulapi/falaiRun fal.ai models, poll the inference queue and read model schemas.Not assessed yet.A remote server; no sign-in.
  19. DeepInfra MCP by usefulapi @usefulapi/deepinfraRun DeepInfra inference, list models and read account rate limits.Not assessed yet.A remote server; no sign-in.
  20. QSP Client @qso-graph/qsp-clientQSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)Not assessed yet.Runs on your machine, installed from PyPI.
  21. Cyberwarex Council @cyberwarex/cyberwarex-councilSecond opinion for agents: 3-4 AI models answer, one verdict with confidence and dissent.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
  22. Baron Power Play @mintmachinehq/baron-power-playPay-per-call AI infra for agents: DeFi market data, LLM inference, STT/TTS. x402 v2, USDC on Base.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  23. Popcraft @popcraft-ai/popcraft-mcpAI video, images, music & SFX: Seedance 2.5, Veo 3.1, Kling 3.0, Nano Banana Pro, 20+ models.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  24. opencode subagents @sebstaq/opencode-subagent-mcpRun Claude Code subagents on cheaper opencode models (DeepSeek, opencode Go) with native parity.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.