PMLL Memory MCP — persistent KV context memory and Q-promise deduplication.
Persistent memory logic loop with short-term KV cache (peek pattern), Q-promise deduplication, and Context+ long-term semantic memory graph for 99% accuracy in Claude Sonnet/Opus agent tasks. v2.0.0 — Four-way benchmarked, agentinstructions workflow, combined Context+ + PMLL/peek. Four-way speed benchmarks — baseline, Context+-only, PMLL/peek-only, and combined (Context+ + PMLL/peek)…
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
initNo description publishedThis tool published no description. Forge does not invent one.
peekNo description publishedThis tool published no description. Forge does not invent one.
setNo description publishedThis tool published no description. Forge does not invent one.
resolveNo description publishedThis tool published no description. Forge does not invent one.
flushNo description publishedThis tool published no description. Forge does not invent one.
graphqlNo description publishedThis tool published no description. Forge does not invent one.
upsert_memory_nodeNo description publishedThis tool published no description. Forge does not invent one.
create_relationNo description publishedThis tool published no description. Forge does not invent one.
search_memory_graphNo description publishedThis tool published no description. Forge does not invent one.
prune_stale_linksNo description publishedThis tool published no description. Forge does not invent one.
add_interlinked_contextNo description publishedThis tool published no description. Forge does not invent one.
retrieve_with_traversalNo description publishedThis tool published no description. Forge does not invent one.
resolve_contextNo description publishedThis tool published no description. Forge does not invent one.
promote_to_long_termNo description publishedThis tool published no description. Forge does not invent one.
memory_statusNo description publishedThis tool published no description. Forge does not invent one.
0 of 15 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Persistent memory logic loop with short-term KV cache (peek pattern), Q-promise deduplication, and Context+ long-term semantic memory graph for 99% accuracy in Claude Sonnet/Opus agent tasks. v2.0.0 — Four-way benchmarked, agentinstructions workflow, combined Context+ + PMLL/peek. Four-way speed benchmarks — baseline, Context+-only, PMLL/peek-only, and combined (Context+ + PMLL/peek) configurations benchmarked in both TypeScript and Python with 5-run averages Combined speed tests — new (14…
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This package was last scanned before Forge began storing the resolved tree. The next scan will record it.