WhiteMagic recall

Endpoints (1 live)

• POST /mcp — WhiteMagic hosted recall: read-only hybrid memory search (BM25 + vector + associative) over a curated public corpus for agent continuity. Call when an agent needs durable context from prior sessions or the public knowledge store. Keyless discovery (initialize/tools/list) is free; free evaluation keys and a daily no-key trial are available. One paid tool call per payment. (0.05 USDC on Base)

MCP tools (24)

whitemagic https://mcp.whitemagic.dev/mcp

• gnosis.explain — Explain why a memory or route was selected (provenance readout).
• gnosis.status — Knowledge-surface status: galaxies, counts, and index health.
• memory.aggregate — Aggregate a numeric or categorical field over matched memories.
• memory.associations — Associative neighbours of a memory (spreading activation over the association graph).
• memory.batch_read — Read several memories by id in one call.
• memory.count — Count memories matching optional filters without returning content.
• memory.filter — Filter memories by metadata (tags, importance, recency).
• memory.hybrid_recall — Compatibility alias of memory.search — same implementation, same arguments, same results. Kept for clients pinned to this name; prefer memory.search.
• memory.list — List memories with filters (galaxy, tags, limit, offset) for browsing and discovery.
• memory.nearby — Memories near a coordinate address (5D spatial neighbourhood).
• memory.query — Structured query over memories with filters and ordering.
• memory.read — Retrieve a specific memory by its ID or coordinate address.
• memory.revisions — List or verify a memory's content revision chain (tamper evidence): every content update is chained and head-checked.
• memory.search — Search memories: hybrid BM25 + vector fusion with deterministic episodic and full-text fallbacks; each result discloses its recall_mode. The preferred recall tool.
• memory.search_batch — Execute multiple memory search queries concurrently in a single turn. Unpacks up to 10 queries, searches the curated corpus, and returns consolidated results.
• memory.stats — Memory index statistics: totals, galaxy spread, and index health.
• memory.tags — List the tag vocabulary with usage counts.
• memory.vector.search — Vector-similarity search over memory embeddings.
• receipts.verify — Verify a receipt id or a bundle offline; fail-closed without an anchor (verdict PROVISIONAL).
• session.continuity — Recall where the previous session left off: recent turns, checkpoints, and open work.
• session.list — List sessions with titles and summaries.
• session.recall — Recall a session's turns without continuity packaging.
• session.replay — Replay a session's recorded turns in order.
• wm — WhiteMagic meta-tool — memory and continuity kernel over the curated tool surface (70 tools): persistent memory, session continuity and recall, governance/audit, and local tool execution. Mode: READ-ONLY — writes (session.*, memory.create/update) are refused; recall only. Scope: store /srv/whitemagic/hosted-store/lmdb. Invoke with thought=<natural language> (auto-routed), route=<exact tool id> (e.g. 'memory.search', 'session.continuity'), or args=<object> (passthrough). Provide exactly one of thought or route. Say 'list tools' to enumerate the curated surface. Prefer a discrete lifecycle tool when one matches your task; use wm for natural-language routing and the wider curated catalog.