Servidor MCP

cache-proxy

io.github.Ainode-tech/cache-proxy
Infraestructura MCP y de agentes Público y accesible MCP 2025-11-25

Qué hace este MCP

Provides an exact and semantic cache proxy for LLM requests, including cached responses and upstream forwarding.

cache_query
Send an LLM request through the caching proxy. Returns cached response if available, otherwise proxies to upstream LLM.
Esquema de entrada
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['provider', 'path', 'body', 'api_key'], 'properties': {'body': {'type': 'string', 'description': 'JSON request body as string'}, 'path': {'type': 'string', 'description': 'API path (e.g. /v1/chat/completions)'}, 'api_key': {'type': 'string', 'description': 'API key for the upstream provider'}, 'provider': {'enum': ['openai', 'anthropic'], 'type': 'string', 'description': 'LLM provider to proxy to'}, 'cache_ttl': {'type': 'number', 'description': 'Cache TTL in seconds (default 86400)'}}, 'additionalProperties': False}
health
Health check. Returns server status and optional echo.
Esquema de entrada
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'echo': {'type': 'string', 'description': 'Optional string to echo back'}}, 'additionalProperties': False}
Añadido
cache_query
17 de September de 2026 a las 12:40
Añadido
health
17 de September de 2026 a las 12:40