"OpenAI Gym" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
BridgeNode — x402 pay-per-request AI inference. OpenAI-compatible API + MCP, Solana USDC, gas-free.
Unified AI API — 30+ models from OpenAI, Anthropic, Google, Groq, and xAI through one API key. Plus translation, weather, and utility endpoints.
Free OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.
Synap (pool.linkrra.com/v1), Linkrra's OpenAI-compatible LLM API, as an MCP server.
OpenAI announcements: models, releases, news. $0.01/query. Register in-session — free testnet funds.
Counts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.
Swift AI: Access a wide range of AI models⚡, including OpenAI 🤖,DeepSeek 🔍, Claude 🧠, Gemini 🌟, and.
OpenAI-compatible LLM MCP (7 tools); chat via balance key or x402 USDC on Base
OpenAI Ads MCP for ChatGPT Ads campaigns, creatives, audiences, insights, and conversions.
Secure API key proxy for AI agents. Store keys once, route API calls through a proxy — agents use your keys without seeing them. Supports 30+ providers including OpenAI, Anthropic, and Stripe.
AI-powered WordPress content management. 104 tools for generating posts, images, managing SEO, automating content, handling menus/categories/comments, and publishing — all from your AI assistant. BYOK model: bring your own OpenAI, Claude, or Gemini API key.
Hubris is an OpenAI-compatible LLM gateway for the Russian market, billed in rubles. This MCP server gives agents access to the model catalog (400+ models with ruble pricing), account balance, and chat completions with full parity to POST /v1/chat/completions. Tools: models_list, models_search (filter by capability/price/context length), models_get_pricing, balance_get, chat_complete. Resources: hubris://catalog/models, hubris://docs/quickstart. Prompt: compare-models. Docs: https://hubris.pw/
Pay-per-call GLM 5.3 MCP tool via x402 on Base. Reasoning, tool-calls, OpenAI-compatible.
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
Token guard and rate limiter preventing runaway API cost spikes for OpenAI and Anthropic.
OAuth LangChain OpenAI Agent
Traced OpenAI LangChain Agent
Structured Output Agent (Openai)