Let Claude Code use the cache: Crowkis over MCP
One config block turns Crowkis into a tool an AI assistant can hold — check the cache, store the answer — over MCP, with the same trust pipeline as every other write.
The Model Context Protocol flips the integration: instead of your code calling the cache around the model, the assistant itself holds cache operations as tools. `crowkis mcp` speaks JSON-RPC over stdio and registers lookup, store, and stats surfaces any MCP-capable assistant can invoke mid-conversation.
// .mcp.json (or your client's MCP config)
{
"mcpServers": {
"crowkis": {
"command": "crowkis",
"args": ["mcp", "--host", "127.0.0.1", "--port", "6379"]
}
}
}The mcp subcommand boots silently — the startup banner every other verb prints would corrupt a JSON-RPC stream, so it's the one quiet door. A hit returns the answer with its confidence; a miss returns a clean signal the assistant can act on rather than hallucinate around.
Crucially, MCP writes get no trust shortcut: an assistant's store request walks the same five-stage anti-poisoning pipeline as RESP and SDK writes, tracked in the ledger as its own source. An agent that stores garbage earns a higher bar automatically. The result is agents that remember as a behaviour — Claude Code checks before spending tokens, banks what it computes, and the whole team's assistants share the dividend.
One config block, and the cache your services already share becomes a tool your agents can hold too.