MCPVault

plur_feedback

MCP tool from Plur by plur-ai

Rate relevance (trains quality over time)

How to use it

plur_feedback is exposed by the Plur MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the plur_feedback tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Plur

$npx @plur-ai/mcp init
FULL PLUR LISTING

Other tools in Plur (15)

Cross-tool

the same ~/.plur/ store works in Claude Code, Cursor, Windsurf, OpenClaw, and Hermes. Your memory isn't trapped in one vendor.

plur_capture

Record an event — incident, resolution, session milestone

plur_forget

Retire a memory (activation decays, eventually pruned)

plur_ingest

Extract engrams from text automatically

plur_inject_hybrid

Select engrams for current task within token budget

plur_learn

Store a correction, preference, or convention

plur_learn_batch

Store many engrams in one call (batch dedup + per-item failure isolation)

plur_outbox

Inspect (and retry) team writes queued while their store was unreachable

plur_recall

Retrieve relevant memories — hybrid (BM25 + embeddings) by default; mode:"keyword" for BM25-only

plur_receipt

Counted, local report of what your memory retrieved for you

plur_rescope

Move an existing engram to another scope — personal → team, or back

plur_session_scope

Change the session's default write scope mid-session

plur_status

Check system health and engram counts

plur_sync

Sync via git. personal remotes mirror everything (use a private repo); shared remotes receive only shared-scope, non-private engrams

plur_timeline

Query episode history by time, agent, or channel