io.github.Ainode-tech/cache-proxy is an MCP server published by io.github.Ainode-tech, hosted at cache.api.ainode.tech. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 2 tools, including health, cache_query.
LLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.
10 connections through 4 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Health check. Returns server status and optional echo.
| Parameter | Type | Description |
|---|---|---|
| echo | string | Optional string to echo back |
{
"name": "health",
"description": "Health check. Returns server status and optional echo.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"echo": {
"type": "string",
"description": "Optional string to echo back"
}
},
"additionalProperties": false
}
}Send an LLM request through the caching proxy. Returns cached response if available, otherwise proxies to upstream LLM.
| Parameter | Type | Description |
|---|---|---|
| body * | string | JSON request body as string |
| path * | string | API path (e.g. /v1/chat/completions) |
| api_key * | string | API key for the upstream provider |
| provider * | string | LLM provider to proxy to |
| cache_ttl | number | Cache TTL in seconds (default 86400) |
{
"name": "cache_query",
"description": "Send an LLM request through the caching proxy. Returns cached response if available, otherwise proxies to upstream LLM.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"provider",
"path",
"body",
"api_key"
],
"properties": {
"body": {
"type": "string",
"description": "JSON request body as string"
},
"path": {
"type": "string",
"description": "API path (e.g. /v1/chat/completions)"
},
"api_key": {
"type": "string",
"description": "API key for the upstream provider"
},
"provider": {
"enum": [
"openai",
"anthropic"
],
"type": "string",
"description": "LLM provider to proxy to"
},
"cache_ttl": {
"type": "number",
"description": "Cache TTL in seconds (default 86400)"
}
},
"additionalProperties": false
}
}Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.