
This gateway consolidates six AI models (DeepSeek, GPT-4o, Claude, Gemini, Grok, Llama) behind a single OpenAI-compatible endpoint with pay-per-use billing. It targets Chinese market operations with compliance tools for banned word detection across platforms like Douyin and Xiaohongshu, GEO visibility checks for local AI models, and regulatory scanners for GDPR and CCPA. The MCP integration exposes web search capabilities alongside the model access. You'd reach for this if you're building content systems that need to comply with Chinese advertising law or validate visibility across Baidu, WeChat, and Bilibili while keeping multi-model access simple. Registration returns an API key that works across all services, billed per request.
Public tool metadata for what this MCP can expose to an agent.
chatChat with AI models (DeepSeek, GPT-4o, Claude). Pay-per-use via ATEX API key.2 paramsChat with AI models (DeepSeek, GPT-4o, Claude). Pay-per-use via ATEX API key.
messagesarraymodelstringdeepseek-chat · deepseek-reasoner · gpt-4o-mini · gpt-4o · claude-3-5-sonnet · claude-3-5-haikudefault: deepseek-chatweb_searchSearch the web for real-time information. 5 ATEX per call.1 paramsSearch the web for real-time information. 5 ATEX per call.
querystringcheck_balanceCheck your ATEX account balance and usage.Check your ATEX account balance and usage.
No parameter schema in public metadata yet.
list_modelsList available AI models and their pricing.List available AI models and their pricing.
No parameter schema in public metadata yet.
list_servicesList all available services in the ATEX marketplace.1 paramsList all available services in the ATEX marketplace.
categorystring合规版积分预测社区(类 Manifold × Good Judgment Open × Kalshi 信息呈现)。 FastAPI + SQLite,积分只送不卖 / 不可流通 / 不可回兑 / 彻底去加密,合规优先。
见 deploy/:Dockerfile / docker-compose.yml / nginx.conf / .env.example /
realcast.service(systemd) / backup.sh(热备) / healthcheck.sh / 部署运维手册.md。
cd deploy && cp .env.example .env # 填 ADMIN_TOKEN / CORS_ORIGINS
docker compose up -d --build
cd app && python tests/smoke.py --fresh # 期望 63/63 全绿