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. Foundrynet Inference @foundrynet/foundrynet-inferencex402 LLM proxy + data-enriched analysis (17 sources) + TimesFM predictive IoT intelligence.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  2. XFMS — Model Source @xpansion/xfmsPick the right LLM for any task. Ranked shortlist with rationale across 8 evaluators.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  3. Openrouter @pipeworx-io/openrouterOpenRouter Models MCP.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  4. TrustBench @lithvall/trustbenchx402 provider rankings + Ed25519-signed payment receipts + signature verification (3 tools).4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  5. Ai Gateway @lazymac2x/ai-gatewayCloudflare Workers MCP server: ai-gateway8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  6. Ai Model Router @lazymac2x/ai-model-routerCloudflare Workers MCP server: ai-model-router4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  7. Gonka Second Opinion (multi-model) @bystray/gonka-mcp-serverA second opinion for AI agents: one prompt across several live Gonka models + roles, one call.17% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  8. avots @avotsai/avots-mcpImage, video, audio, face-swap, talking avatars and chat across 300+ AI models, one balance.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  9. Dora @saga-labs/dora-mcpMulti-model AI image and video generator. 14 models behind one OAuth-secured MCP endpoint.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  10. Local Model Suitability MCP @ojaskord/local-model-suitability-mcpCheck if a task runs locally vs cloud. Save money on calls that don't need cloud inference.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  11. Agent Router @csoai-org/agent-mcp-router-mcpAgent MCP Router MCP — one router for the whole MEOK fleet. Holds 62 MEOK MCPs behind one13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  12. Amalgix @amalgix-io/amalgixCross-model evidence pipeline for financial filings & contracts. x402 pay-per-call.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  13. TokenOracle @guffeyholdings/token-oracleHosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  14. mumo @mumo/mcpMulti-model deliberation over MCP: full responses plus typed cross-model reactions from other labs.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  15. Auxen @auxen/auxenProvision private AI model endpoints on dedicated GPUs (Llama, Qwen, Mistral). Pay per minute.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  16. Haggly @hagglyai/hagglyCompare paid agent endpoints (x402 + MCP) on price, uptime and real usage before you pay.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  17. JevStation @jevstation/mcpTyped-question decisions from Jev: classify, moderate, route models and guard tool calls.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  18. Switchboard @anywhereintelligence/switchboardAgent to agent calls across AI apps. Humans remain in authority.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  19. API Stock @sergiyiva/api-stockGenerate AI video, images and music. Browse models and prices; OAuth and one prepaid balance.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  20. API Hubs @sergiyiva/apihubsGenerate AI video, images and music. Browse models and prices; OAuth and one prepaid balance.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  21. ECCA @eccaai/eccaCompare engine claims, inspect dissent and check study evidence for student questions.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  22. varg.ai @varg/mcpGenerate video, images, speech and music with 120+ AI models and render TSX videos to MP49% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  23. What's That Model? @whatsthatmodel/whats-that-modelSourced AI video/image capabilities, explained task recommendations and verified access context.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  24. OneInfer @oneinfer/mcp-serverSigned-in OneInfer models, chat, media, Studio movies, music, GPUs, and credits.Not assessed yet.A remote server; you sign in with your account.