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.

io.github.kael-bit/engram

NPM · ENGRAM-RS-MCP · SCANNED SEP 20

Hierarchical memory for AI agents. Three-layer (buffer/working/core) with decay and promotion.

Available components

0 this week 82 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 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability78
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1393 tokens (~92/item across 15 items; 15 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
  • Stability observed for 28 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 Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "engram_delete" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 15 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 io.github.kael-bit/engram MCP server?

io.github.kael-bit/engram runs locally as an npm package, launched with npx -y engram-rs-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 · engram-rs-mcp

# add to Claude Code
claude mcp add kael-bit-engram -- npx -y engram-rs-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "kael-bit-engram": {
      "command": "npx",
      "args": [
        "-y",
        "engram-rs-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "kael-bit-engram": {
      "command": "npx",
      "args": [
        "-y",
        "engram-rs-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add kael-bit-engram -- npx -y engram-rs-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "kael-bit-engram": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "engram-rs-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add kael-bit-engram --command npx --arg -y --arg engram-rs-mcp
# ~/.hermes/config.yaml
mcp_servers:
  kael-bit-engram:
    command: "npx"
    args: ["-y", "engram-rs-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "kael-bit-engram": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "engram-rs-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add kael-bit-engram -t stdio -c npx -a -y engram-rs-mcp
// mcp.json
{
  "mcpServers": {
    "kael-bit-engram": {
      "command": "npx",
      "args": [
        "-y",
        "engram-rs-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 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 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 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −3
    • Stability: pass → 0.80 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.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 −3
    • Stability: pass → 0.80 functional
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/engram-rs-mcp@0.10.0

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 96 packages
Packages resolved 96
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 15 exposed · ~1,393 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
engram_consolidate ~111

Run a memory consolidation cycle. Promotes important memories upward, drops decayed entries. With merge=true, uses LLM to merge similar memories.

NameTypeReqDescription
decay_drop_thresholdnumberDrop below this recency (default 0.01)
mergebooleanUse LLM to merge similar memories
promote_min_importancenumberMin importance to promote (default 0.6)
promote_thresholdintegerMin access count to promote (default 3)

No output schema declared.

No examples provided.

engram_delete ~38

Delete a memory by ID. Use when a memory is outdated, incorrect, or redundant.

NameTypeReqDescription
idstringyesMemory ID to delete

No output schema declared.

No examples provided.

engram_extract ~55

Extract structured memories from raw text using LLM. Feed conversation logs or notes and get individual memories.

NameTypeReqDescription
auto_embedbooleanGenerate embeddings (default true)
textstringyesRaw text to extract memories from

No output schema declared.

No examples provided.

engram_health ~26

Detailed health check: uptime, RSS memory, embed cache stats, AI config status.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

engram_recall ~291

Hybrid semantic + keyword search with budget-aware retrieval. Fast by default (~30ms cached, ~1s first query). Optional rerank/expand add LLM calls (+2-4s each) — only use when needed.

NameTypeReqDescription
budget_tokensintegerMax token budget
drybooleanSkip touch/reinforcement on results (for background queries)
expandbooleanLLM query expansion (+1-2s). Use for short/vague queries like single words
layersarrayFilter by layers
limitintegerMax results
min_importancenumberMin importance threshold
min_scorenumberDrop results below this score (0-1)
namespacestringFilter by namespace (also includes "default" namespace automatically)
querystringyesSearch query
rerankbooleanRe-rank via LLM (+2-4s). Use only when result ordering is critical
sinceintegerOnly memories created after this unix ms timestamp
sort_bystringSort order (default: score)
sourcestringFilter by source (e.g. session, extract, api)
tagsarrayFilter by tags (must have ALL specified)
untilintegerOnly memories created before this unix ms timestamp

No output schema declared.

No examples provided.

engram_recent ~105

List recent memories by creation time. Good for session context recovery.

NameTypeReqDescription
hoursnumberLook back N hours (default 2)
layerintegerFilter by layer
limitintegerMax results (default 20)
min_importancenumberMinimum importance threshold
namespacestringFilter by namespace (also includes "default" namespace automatically)
sourcestringFilter by source (e.g. session)

No output schema declared.

No examples provided.

engram_repair ~35

Repair FTS search index. Removes orphaned entries and rebuilds missing ones. Safe to run anytime — idempotent.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

engram_restore ~36

Restore a soft-deleted memory from trash back to its original layer.

NameTypeReqDescription
idstringyesMemory ID to restore from trash

No output schema declared.

No examples provided.

engram_resume ~182

Full memory bootstrap for session recovery. Returns core (permanent knowledge), working (ongoing context/decisions), buffer (transient), recent activity, and session notes. Use workspace tags to filter by current work context. Compact mode (default) minimizes token usage.

NameTypeReqDescription
budgetnumberMax chars across all sections (default 8000, 0=unlimited)
compactbooleanCompact output: content+tags only (default true)
hoursnumberLook back N hours for recent/sessions (default 4)
limitnumberMax memories per layer (default 100)
namespacestringFilter by namespace (also includes "default" namespace automatically)
workspacestringComma-separated workspace tags to filter core/working memories (e.g. 'engram,rust')

No output schema declared.

No examples provided.

engram_search ~64

Quick keyword search. Lighter than recall — no scoring or budget logic.

NameTypeReqDescription
limitintegerMax results (default 10)
namespacestringFilter by namespace (also includes "default" namespace automatically)
qstringyesSearch query

No output schema declared.

No examples provided.

engram_stats ~22

Get memory statistics: counts per layer, AI status, version.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

engram_store ~222

Store a memory. All memories start in Buffer and promote to Working/Core through access frequency and LLM quality gating. Procedural memories and lessons (tag=lesson) auto-promote to Working after 2h. Use supersedes to replace outdated memories by their ids.

NameTypeReqDescription
contentstringyesMemory content text
importancenumberImportance 0-1 (default 0.5, bumps +0.02 on each recall)
kindstringMemory type: semantic (facts, default), episodic (events), procedural (how-to, persists indefinitely)
namespacestringOverride namespace. Use "default" for cross-project knowledge (user identity, preferences, universal lessons)
skip_dedupbooleanSkip near-duplicate detection
sourcestringSource identifier
supersedesarrayIDs of old memories this one replaces
sync_embedbooleanWait for embedding generation before returning (default: false)
tagsarrayTags for categorization

No output schema declared.

No examples provided.

engram_trash ~36

List soft-deleted memories. Recently deleted items can be restored.

NameTypeReqDescription
limitintegerMax results (default 100)

No output schema declared.

No examples provided.

engram_triggers ~61

Fetch trigger memories for a specific action. Call before performing an action (e.g. git-push, deploy) to recall relevant lessons and rules.

NameTypeReqDescription
actionstringyesAction name (e.g. git-push, deploy, send-message)

No output schema declared.

No examples provided.

engram_update ~109

Update a memory's content, metadata (importance, tags, layer, kind). Use supersedes on store to replace with history.

NameTypeReqDescription
contentstringNew content text
idstringyesMemory ID to update
importancenumberNew importance value
kindstringMemory type
layerintegerMove to layer: 1=buffer, 2=working, 3=core
tagsarrayReplace tags

No output schema declared.

No examples provided.

Common questions

What is the io.github.kael-bit/engram MCP server?

io.github.kael-bit/engram is an MCP server listed in the public MCP registry as io.github.kael-bit/engram. Hierarchical memory for AI agents. Three-layer (buffer/working/core) with decay and promotion. This page covers its npm package (engram-rs-mcp).

Is the io.github.kael-bit/engram MCP server safe to use?

io.github.kael-bit/engram scores 82 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 io.github.kael-bit/engram MCP server expose?

io.github.kael-bit/engram exposes 15 tools: engram_store, engram_recall, engram_recent, engram_resume, engram_extract, and 10 more. Their descriptions and schemas cost roughly 1,393 tokens of context every time the server is loaded.

Is the io.github.kael-bit/engram MCP server still maintained?

io.github.kael-bit/engram 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 io.github.kael-bit/engram MCP server under?

io.github.kael-bit/engram declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.