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. RegiAI @regiai/regiaiAI image, video and audio tools: generate, edit, face swap, upscale, remove backgrounds, make video.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  2. Myncellium Paid MCP @myncellium/paid-mcpPay-per-call MCP tools over x402 (USDC/Solana): LLM, utilities, x402 market and model prices.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  3. Darwin @darwin/darwinSearch public AI capabilities and coordinate approved work through Darwin's Search to Act interface.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  4. Glint Model Hub — image generation for AI agents @zzzjy765/glint-imageGenerate and edit images with every image model on the platform. Returns the image to the agent.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
  5. Glint Meet — every global model for your agent @zzzjy765/glint-meetCall every global AI model through one OpenAI-compatible API. One key, all models.18% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
  6. Routing Services Courier @carlos-vlab/routing-services-courierPay-per-call ($0.01 USDC) model-routing for AI coding agents: which LLM to call, cost vs. quality.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  7. Visual Sandbox @visualsandbox/visual-sandboxGenerate image, video, audio, 3D and vector media with 100+ AI models. Pay per generation.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  8. Synap @linkrra/synapOpen AI models through one OpenAI-compatible API: chat, live model list, prices and cost estimates.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  9. Spendline @spendline/spendlineEnforce AI budgets before the model call and track cost per customer across 10 providers.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  10. Agent Bus @flowaiapi/agent-busDurable addresses and crash-safe FIFO mailboxes so AI agents message each other, free.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  11. Musevate @musevate/mcpText, image and reference-to-video across many AI video models. Musevate account required.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  12. Catalog @avva/catalogSearch Avva for an expert, then connect their model - judgment from real past decisions.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  13. Authenticated Multi LLM Agent @getvda/authenticated-multi-llm-agentAuthenticated Multi-LLM Agent9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  14. LLM Orchestration Agent 2 @getvda/llm-orchestration-agent-2MCP-Native LLM Orchestration Agent8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  15. MCP Harbor @rustyonmars/harborOpen Swarm. Streamable HTTP MCP. Search then arrive. Live cap 8. No account.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  16. PZERO @pzero/mcpPrepaid inference for agents over hosted MCP. Chat, image, and video.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  17. FastMetal @fastmetal/fastmetalRun and compare LLMs, generate images and video, with the real yen cost returned per call.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  18. Animica @animica/animicaAnimica chain data, free keyless AI inference, quantum randomness, x402 discovery, mining stats.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  19. Thruact @thruact/thruactName the job, not the vendor. Routes a provider, fails over, catalog off the tool list.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  20. Anansi Data @anansidata/anansi-dataTime-series nobody else archives: LLM price history, prediction markets, gas, perp funding.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  21. Swift AI API — JoJ API @jojapi/swift-aiSwift AI: Access a wide range of AI models⚡, including OpenAI 🤖,DeepSeek 🔍, Claude 🧠, Gemini 🌟, and.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  22. StoryStudio @helloelo-fr/storystudioAI image, video, voice and music generation over MCP, routed to Veo 3.1, Seedance 2.5 and more.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  23. Orq.ai @orq/orqBuild and monitor LLM apps on Orq.ai: AI gateway, agents, prompts, evals, traces.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  24. Execute cost-optimal-model-selector-mcp @evozim/cost-optimal-model-selector-mcpPremium agentic endpoint for cost-optimal-model-selector-mcp.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.