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

Hindsight MemPalace

NPM · HINDSIGHT-MEMPALACE-MCP · SCANNED SEP 20

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

0 this week 71 Trust /100
Trust breakdown (7 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 → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 95 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
  • Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 84 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability40
  • 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 Management90
  • Stability observed for 27 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
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Hindsight MemPalace MCP server?

Hindsight MemPalace runs locally as an npm package, launched with npx -y hindsight-mempalace-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · hindsight-mempalace-mcp

# add to Claude Code
claude mcp add holetron-hindsight-mempalace -- npx -y hindsight-mempalace-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "holetron-hindsight-mempalace": {
      "command": "npx",
      "args": [
        "-y",
        "hindsight-mempalace-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "holetron-hindsight-mempalace": {
      "command": "npx",
      "args": [
        "-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"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "holetron-hindsight-mempalace": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "hindsight-mempalace-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add holetron-hindsight-mempalace -t stdio -c npx -a -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.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −3
    • Stability: pass → 0.77 functional
  • 15 Sept 26 0
    • Stability: 0.97 → pass security
  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 8 Sept 26 0
    • Stability: 0.97 → pass security
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 20 Sept 2026 · Analysed npm/hindsight-mempalace-mcp@1.0.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 95 packages
Packages resolved 95
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

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.

Common questions

What is the Hindsight MemPalace MCP server?

Hindsight MemPalace is an MCP server listed in the public MCP registry as io.github.holetron/hindsight-mempalace. Self-hosted long-term memory for AI agents over MCP, hierarchical recall backed by pgvector. This page covers its npm package (hindsight-mempalace-mcp).

Is the Hindsight MemPalace MCP server safe to use?

Hindsight MemPalace scores 71 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Hindsight MemPalace MCP server expose?

Hindsight MemPalace exposes 5 tools: memory_retain, memory_recall, memory_reflect, memory_compress, memory_bridge. Their descriptions and schemas cost roughly 705 tokens of context every time the server is loaded.

Is the Hindsight MemPalace MCP server still maintained?

Hindsight MemPalace is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Hindsight MemPalace MCP server under?

Hindsight MemPalace declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.