Catalog
io.github.Ainode-tech/cache-proxy
Official2 toolsLLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.
Caches LLM requests using exact and semantic matching to reduce API costs.
Captured live from the server via tools/list.
health
Health check. Returns server status and optional echo.
Parameters (1)
- echostring
Optional string to echo back
cache_query
Send an LLM request through the caching proxy. Returns cached response if available, otherwise proxies to upstream LLM.
Parameters (5)
- providerstringrequired
LLM provider to proxy to
- pathstringrequired
API path (e.g. /v1/chat/completions)
- bodystringrequired
JSON request body as string
- api_keystringrequired
API key for the upstream provider
- cache_ttlnumber
Cache TTL in seconds (default 86400)
README not available yet.
Install
claude_desktop_config.json
{
"mcpServers": {
"cache-proxy": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://cache.api.ainode.tech/mcp"
]
}
}
}Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.