caura_keystones
Read mandatory governance rules for the current scope (tenant + fleet + agent merged). Call once per session.
How to use it
Project documentation lists caura_keystones for the Caura MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.
Install Caura
claude mcp add --transport http -s user memclaw http://localhost:8000/mcp --header "X-API-Key: standalone"Other tools in Caura (11)
Structured-document CRUD, op-dispatched: write \
Look up a knowledge-graph entity by UUID.
Karpathy-Loop feedback: record an outcome (success \
Karpathy-Loop reflection: contradictions, failures, stale, divergence, patterns, discover.
Author/remove keystone rules, op-dispatched: set \
Non-semantic enumeration with filters, sort, cursor pagination.
Per-memory lifecycle, op-dispatched: read \
Hybrid semantic + keyword search over memories, with optional LLM-summarised brief.
Aggregate counts: total + breakdowns by type / agent / status. Read-only.
Read/update an agent's per-search profile (topk, ftsweight, freshness, blend, …).
Single or batch (≤100) memory write; auto-enriched with type, title, summary, tags.