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. Qwen38 Free Gateway @khs0927/qwen38-free-gatewayFree Qwen3.8-27B gateway with isolated Minis provider, SSE, retry/failover, and MCP.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  2. Reelfy Agent Tools @mgnlockii/reelfyPay-per-use AI and data tools via x402: image, video, music, voice, search, crypto. USDC.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  3. Frontier @openfrontier/frontierDiscover Frontier inference capabilities and read sanitized usage through read-only tools.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  4. YouCam for Beauty & Personal Care @makeupar/beautyProvides YouCam API for skin, face & body analysis, beauty/makeup try-on, and hair & beard styling.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  5. YouCam for Creators @makeupar/creatorsProvides YouCam API for AI image and video editing and generation.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  6. NinjaChat MCP @ninjachat/mcpCreate images & video from any MCP agent — 17 models, spend limits, one URL.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  7. AICIA AI Signal @jack-mi/aicia-ai-signalClosed-source remote MCP: model benchmarks, costs, HN signals, tech registry.18% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  8. Council AI @omarkeshk/council-aiMulti-LLM council: 25+ frontier models in parallel, consensus scoring, verdict-first code review.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  9. CNAPS.ai MCP Server @cnaps/studioRun 70+ AI models and 50+ tools on CNAPS Studio in natural language — Claude, n8n, or Zapier.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  10. CCAPI @ccapi/mcpImage, video, music and text generation across 100+ models through one endpoint.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  11. AgentDataHub Gateway @agentdatum/gatewayx402 data & AI gateway: 194 services + AI Gateway free data (save 50-90% tokens).11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  12. Writingmate MCP @writingmate/writingmate-mcpUse AI models for chat, image, and video generation from Claude Code and other MCP hosts.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  13. FOTOhub Creative AI @fotohub/fotohubGenerate images, video, music, voice and 3D through one API. 30 tools, 200+ models.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  14. Genomic Intelligence @genomicintelligence/genomic-intelligenceHosted DNA language models: promoter, splice, enhancer, chromatin, expression, annotation3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  15. Webhound @webhound/webhoundBudgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  16. 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.
  17. Terradev @theoddden/terradevCross-cloud GPU orchestration CLI.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  18. Mcpmyadmin @mcpmyadmin/mcpmyadminQuery 40 databases from Claude, ChatGPT, or Cursor — on any device. Read-only, encrypted, audited.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  19. QuoteFirst @quotefirst/quotefirstGet dollar quotes from 200+ LLMs before any work runs; accept, execute, and verify quality.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  20. 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.
  21. SYNTHORA x402 Intelligence Mesh @hergertsynthora/synthora-x402Calibrated intelligence via x402 (USDC Base). ERC-8004 #84581: 272 payments, 49 wallets.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  22. LMX Cloud LLM Inference @lmxcloud/mcp-serverOpenAI-compatible LLM MCP (7 tools); chat via balance key or x402 USDC on Base5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  23. K402 @kali123411/k402Agent-payable APIs on Kaspa: LLMs, chain data, covenants, zk proofs — pay per call, no API key10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  24. Oriora Router @orioralabs/routerAI model routing on your own vendor keys: pick the best model per prompt, or route and run it.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.