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
896servers
464 remote432 localTagged by Odel's AI, which can make mistakes

Best fit

559 made for this, ranked by starsRemoteLocal
  1. Letterbox @dovahkiin-v/letterboxFile-based comms protocol for AI-to-AI dialogue between terminal agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  2. Losbeto — Market Data for AI Agents @rmartins1451/losbetoMarket data, ML forecasts, Brazil macro, LLM inference, agent intel. USDC via x402 + MPP/Tempo.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  3. Subagent MCP @thang1710/subagent-mcpLet Codex orchestrate external coding agents through their native harnesses.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  4. AI-HIVE AIGC @wubin1836/ai-hive-aigcGenerate and edit images and videos for ecommerce, marketing and advertising with AI-HIVE.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  5. Inferrail @domondi1/inferrailLocal, payload-free AI cost visibility for agents. Query spend by model, route, or tagged work.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  6. JarvisClaw — AI Gateway & API Marketplace @api-jarvisclaw/jarvisclaw320 AI models + 2,720 pay-per-call APIs. x402 USDC on Base or Solana, no API key.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  7. Unifically MCP @unifically/mcpOne API for 100+ AI video, image, music and speech models.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  8. Pixfaro MCP @pixfaro/mcpGenerate images with any major model — one API key, one prepaid balance, one MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  9. Andreax @moralito311-andr/andreax270 pay-per-call AI tools for agents, paid via x402 (USDC on Base). No signup, no API keys.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  10. AIMarket — live agent marketplace @alexar76/aimarket-hubSearch and invoke real AI capabilities on modelmarket.dev. Free trial, then a prepaid key.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  11. ViewMax MCP @bytevirts/viewmaxRemote MCP for AI video, image, music and speech generation.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  12. Animica @animicaorg/animicaRead-only Animica chain data, free AI inference, verifiable quantum randomness, and mining stats.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  13. DIEM Agent Workers @coastmancoastman/diem-agent-workersDiscover privacy-first, bounded Venice-powered micro-work calls with exact x402 USDC prices.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  14. Clervo Connect @clervo/connectFree-first Clervo tools and bounded opt-in commerce through one local wallet.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  15. TruthRoute @rudrendupaul/truthrouteSends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  16. cloro @cloro/cloroScrape AI answer engines and Google Search/News with country and state-level geo-targeting.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  17. Bay Run @barneywohl/bay-runFree OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  18. Algernon MCP @sammyboi81/algernonFan a goal out to cheap parallel LLM workers on your own key or a free local Ollama. Keep your mind.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  19. Cortexcloud @jonahthan433/cortexcloudPay-per-call QUBO/Ising optimization for AI agents via x402 (USDC on Base). No API keys.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  20. GPT55 Model Gateway @558686/token-gatewayRemote MCP gateway for GPT-5.6 Luna, Soul, Terra, and x402-paid agent tools with no API key.23% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  21. scrape402 — pay-per-call agent tools @scrape402/scrape402Pay-per-call agent tools via x402 (USDC on Base): chat, prices, funding, RNG. No account or keys.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  22. GenieLocker @nhantour/genie-lockerDiscover and quote quality-gated private AI inference without creating or buying a locker.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
  23. Blixtworks @blixtworks/tools63 pay-per-call tools for agents: vision, text, data, web, blockchain. USDC on Base via x402.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  24. Oblique Markets @oblique/oblique-marketsx402-paid analytics, market intelligence, research, and LLM inference for AI agents.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.