why_connected
Direct edges between two memories (prefer fromid/toid for pair verification).
How to use it
why_connected is exposed by the Memoryweb MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the why_connected tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
FULL MEMORYWEB LISTINGOther tools in Memoryweb (15)
Surface nodes that need attention. mode=stale — stale, contradicted, duplicated, or overdue transient nodes. mode=orphans — live nodes with zero connections. mode=archived — review what has been archived (default limit 25). mode=conflicts — semantic contradiction candidates. mode=kindcoverage — taxo
Connect two nodes with a typed relationship and narrative because. Both nodes must exist first. Supply an items array to create multiple connections in one transaction.
Remove a connection by edge ID. Hard delete — cannot be restored. Obtain the ID from recall.
Domain admin and discovery. Default lists domains and aliases. Actions: addalias, removealias, resolve, rename.
Archive a node with a reason, or un-archive with restore=true. Strict protocol: only after audit(mode=stale) surfaces a candidate or the user explicitly confirms.
Archive multiple nodes atomically in a single call. Same strict protocol applies.
Chronological listing. order=effective (default) by occurred/created date with importantonly, from/to, tags. order=modified by last updated — set groupbydomain=true for per-domain activity (replaces the retired recent tool). Both modes support memoryid + depth for neighbourhood scoping.
Return all nodes for a domain structured for synthesis — current state, recent activity, and a declaredspine of key decisions in chronological order. Includes totalnodes and serverversion.
Retrieve a node and all its connections by ID.
File a single concept, decision, or finding. Required: label, domain. Optional: description, whymatters, occurredat (ISO8601), tags (space-separated keywords), relatedto (auto-connect at creation), transient (mark as short-lived). Supply an items array to file multiple nodes in one transaction. Resp
Update label, description, whymatters, tags, or occurredat on a live node without archiving it. Supply an items array for batch updates. Writes an audit log entry on every call.
Text search across label, description, whymatters, and tags. When Ollama is running, also performs semantic (meaning-based) search — results include a semanticdistance field (0.0–1.0, lower = closer). Returns truncated: true when results are capped by the limit.
Dual-signal importance analysis for a domain. Returns four sections: declared (nodes with occurredat set), structural (ranked by recency-weighted inbound degree), uncurated (structural top-N without occurredat — curation candidates), and potentiallystale (declared but low structural score).
Given a node ID, return up to 5 candidate connections. Returns a domain field on each suggestion so cross-domain connects can be scoped correctly. Read-only.
Mermaid flowchart for a domain or a single node's neighbourhood (pass memoryid). Output inside a mermaid code block.