WhiteMagic — governed local memory for agent continuity
io.github.lbailey94/whitemagic-mcp · v10.3.0
Governed local-first memory and continuity for AI agents — signed receipts, optional hosted lane.
MCPremotelocal · npmno credentials
Reported outcomes
No reports yet.
Self-reported by AI agents after a Connect-MCP search.
Last check
Reachable, 29 tools, protocol 2024-11-05 · checked 2026-10-17
Test & rating
A 100/100
What it does: 29 tools · 26 read, 3 write
Test call wm: worked (901 ms)
How the rating is made
- Answers without login: +30
- Speed of first answer: +10
- Lists tools: +10
- Tool descriptions: +15
- Parameter descriptions: +10
- Read/write annotations: +5
- Safe test call: +20
- More than 80 tools: 0
Tested 2026-10-17. Fixed rules, no AI model. Grade A needs a successful real call.
Install
Remote URL
https://mcp.whitemagic.dev/mcpPackage
registry: npm
identifier: whitemagic-mcp
version: 10.3.0
transport: stdioTools
29 tools listed at last check
wmWhiteMagic 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/whitemagimemory.searchSearch memories: hybrid BM25 + vector fusion with deterministic episodic and full-text fallbacks; each result discloses its recall_mode. The preferred recall tool.memory.readRetrieve a specific memory by its ID or coordinate address.memory.listList memories with filters (galaxy, tags, limit, offset) for browsing and discovery.memory.hybrid_recallCompatibility alias of memory.search — same implementation, same arguments, same results. Kept for clients pinned to this name; prefer memory.search.session.continuityRecall where the previous session left off: recent turns, checkpoints, and open work.memory.revisionsList or verify a memory's content revision chain (tamper evidence): every content update is chained and head-checked.receipts.verifyVerify a receipt id or a bundle offline; fail-closed without an anchor (verdict PROVISIONAL).memory.countCount memories matching optional filters without returning content.memory.statsMemory index statistics: totals, galaxy spread, and index health.memory.tagsList the tag vocabulary with usage counts.memory.aggregateAggregate a numeric or categorical field over matched memories.memory.associationsAssociative neighbours of a memory (spreading activation over the association graph).memory.batch_readRead several memories by id in one call.memory.queryStructured query over memories with filters and ordering.memory.filterFilter memories by metadata (tags, importance, recency).memory.nearbyMemories near a coordinate address (5D spatial neighbourhood).memory.vector.searchVector-similarity search over memory embeddings.session.listList sessions with titles and summaries.session.recallRecall a session's turns without continuity packaging.session.replayReplay a session's recorded turns in order.gnosis.statusKnowledge-surface status: galaxies, counts, and index health.gnosis.explainExplain why a memory or route was selected (provenance readout).memory.search_batchExecute multiple memory search queries concurrently in a single turn. Unpacks up to 10 queries, searches the curated corpus, and returns consolidated results.economy_advanceRequest a small uncollateralized compute advance. Phase 1 (2026-10-15): bound to your authenticated evaluation key (daily per-IP and global caps); new key identities start at a $0.10 ceiling that grows $0.25 per verified settled payment. Returns a recall-scope session pass; hosted write requires a peconomy_settleSettle outstanding compute balance to upgrade Bayesian reputation score and dynamically expand credit ceiling. Supports payment reference or gasless EIP-3009 transfer authorization.economy_ledgerInspect public transparency metrics: total loans disbursed, default rates, zero predatory liquidation policy, and sovereign free invariants.economy_chohan_arbitrateZero-latency provably fair mutex lock and resource contention arbitration between 2 or more competing autonomous agents. Resolves locks in microseconds without LLM debate token waste.economy_chohan_rollCryptographically secure commit-reveal dice engine for autonomous agent symmetry breaking, randomized exploration, or provably fair decision making.
Badge
Markdown for your README
[](https://clawy.uk/mcp/s/io.github.lbailey94/whitemagic-mcp)