GenPark LRU TTL Multi-Tier Cache MCP
An in-memory LRU cache server with per-key TTL expiration, deterministic eviction, and hit/miss/stale telemetry designed for LLMs. It is built with 100% Python Standard Library, has zero third-party runtime dependencies, and plugs directly into Claude Desktop, Cursor, LobeChat, and autonomous agent DAGs.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Cache LLM prompts with per-key TTL expiration
- Monitor cache hit/miss/stale telemetry
- Integrate with Claude Desktop or Cursor as an MCP server
- Reduce latency for repeated agent queries
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/Alpha-Park/genpark-lru-ttl-multi-tier-cache-skill/releases/download/v1.0.1/genpark-lru-ttl-multi-tier-cache-skill-v1.0.1.mcpb
{
"transport": "stdio",
"fileSha256": "676cd2b5eb12947400674526c654f97a997a8e73383a82fc30176441cd1db6a1",
"identifier": "https://github.com/Alpha-Park/genpark-lru-ttl-multi-tier-cache-skill/releases/download/v1.0.1/genpark-lru-ttl-multi-tier-cache-skill-v1.0.1.mcpb",
"registryType": "mcpb"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Let your agent find its tools
Find servers like GenPark LRU TTL Multi-Tier Cache MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.