Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

Hindsight MemPalace

NPM · HINDSIGHT-MEMPALACE-MCP · SCANNED AUG 3

Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector

+19 this week 63 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security86
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability44
  • 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Fail
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 710 tokens (~118/item across 6 items; 5 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · hindsight-mempalace-mcp

# add to Claude Code
claude mcp add holetron-hindsight-mempalace -- npx -y hindsight-mempalace-mcp
# add to Codex CLI
codex mcp add holetron-hindsight-mempalace -- npx -y hindsight-mempalace-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "holetron-hindsight-mempalace": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "hindsight-mempalace-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add holetron-hindsight-mempalace --command npx --arg -y --arg hindsight-mempalace-mcp
# ~/.hermes/config.yaml
mcp_servers:
  holetron-hindsight-mempalace:
    command: "npx"
    args: ["-y", "hindsight-mempalace-mcp"]
// mcp.json
{
  "mcpServers": {
    "holetron-hindsight-mempalace": {
      "command": "npx",
      "args": [
        "-y",
        "hindsight-mempalace-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +4
    • Stability: unverified → 0.27 functional
  • 2 Aug 26 +40
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • Schema quality: unverified → good functional
    • MCP protocol: unverified → pass functional
    • Licence: MIT functional
  • 1 Aug 26 +14
    • Schema quality: unverified → 0 functional
    • Tool coverage: unverified → 100 functional
  • 31 Jul 26 −21
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −18
    • Malware scan: pass → unverified security
  • 27 Jul 26 44

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 94 packages

94 packages in the resolved dependency tree · 94 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 5 exposed · ~705 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
memory_bridge ~130

Create a cross-bank memory bridge (tunnel) between two related memories in different banks. Relations: same_concept, depends_on, contradicts, extends. Use when concepts in separate banks are related.

NameTypeReqDescription
confidencenumberConfidence score 0.0–1.0 (default: 0.8)
relationstringyesRelationship type
source_bankstringyesSource bank ID
source_memorystringyesUUID of the source memory
target_bankstringyesTarget bank ID
target_memorystringyesUUID of the target memory

No output schema declared.

No examples provided.

memory_compress ~134

Create compressed memory summaries (closets) from stored facts. Groups memories by room+hall and creates AI-generated summaries with source pointers. Use when a topic has accumulated many facts.

NameTypeReqDescription
bank_idstringMemory bank ID (default: mempalace-main)
hallstringKnowledge type to compress (e.g. "fact", "decision")
min_sourcesnumberMin memories needed to create a closet (default: 5)
querystringQuery to guide compression focus
roomstringTopic to compress (e.g. "auth", "pipeline")

No output schema declared.

No examples provided.

memory_recall ~140

Search long-term memory for relevant facts. Uses semantic search with optional room/hall scoping for significantly improved retrieval accuracy. Supports layer cascade (L0 results always prioritized).

NameTypeReqDescription
bank_idstringMemory bank ID (default: mempalace-main)
hallFilter by hall(s): fact, event, decision, etc.
limitnumberMax results (default: 10)
max_layerstringMax layer depth to search (default: L3 = all)
querystringyesWhat to search for in memory
roomFilter by room(s) — applied before semantic search

No output schema declared.

No examples provided.

memory_reflect ~80

Deep reasoning over memory — synthesizes facts, finds patterns, answers complex questions with citations. Use for analysis: "What patterns emerge from recent events?" or "Summarize everything about X."

NameTypeReqDescription
bank_idstringMemory bank ID (default: mempalace-main)
querystringyesQuestion to reason about over stored memories

No output schema declared.

No examples provided.

memory_retain ~221

Save a fact, observation, or document to long-term memory with automatic room/hall classification. Rooms: auth, pipeline, schema, infrastructure, ui, api, deployment, monitoring, agent, general. Halls: fact, event, decision, preference, discovery, procedure, warning. Layers: L0=Identity (always loaded), L1=Critical, L2=Session (default), L3=Deep.

NameTypeReqDescription
bank_idstringMemory bank ID (default: mempalace-main)
contextstringContext label (e.g. "meeting notes", "client call")
document_idstringDocument ID to group related facts
hallstringKnowledge type (auto-classified if omitted)
layerstringPriority layer (default: L2)
roomstringTopic room (auto-classified if omitted)
tagsarrayTags for categorization
textstringyesThe text to memorize — a fact, observation, or document content

No output schema declared.

No examples provided.