Mmcp.market

Engram MCP server

by devinmlowe·io.github.devinmlowe/engram·v0.4.0
No reviews yet

Cognitive memory for coding agents: hybrid recall, remember/forget, knowledge graph, nightly dreams.

C68/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C68/100

full report

Adoption
Growing

1 stars182 downloads/wk

Reviews

Write one

Nobody has reviewed Engram yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Engram tools (16, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • commitments

    List tracked commitments — first-person promises, intentions and

  • commitments_updatewrite action

    Resolve a tracked commitment once the user confirms it is handled:

  • explore

    Explore connections in the knowledge graph starting from an entity.

  • explore_selective

    Explore the knowledge graph selectively by expanding only branches

  • fetch_snippets

    Fetch multiple line ranges from a single file in one call. Ranges are

  • forgetwrite action

    Remove a memory the user says is wrong or stale. Pass the memory_id

  • index_file_structure

    Parse a source file to extract function, class, and module definitions,

  • ingest_turn

    Record one user/assistant turn of an external agent conversation

  • recall

    Retrieve relevant memories from past Claude Code conversations and

  • recall_drill

    Drill into a specific result from a recall session to get expanded

  • recall_sessionwrite action

    Create or continue an iterative search session for multi-step memory

  • reflect

    View emergent patterns and structure in the knowledge graph.

  • remember

    Store a fact, preference, decision, or other knowledge as a semantic

  • remember_batch

    Store multiple facts, preferences, decisions, or other knowledge items

  • scan_file

    Scan a file server-side with regex patterns and return structured matches

  • show

    Read full conversations to extract detailed context after

Public scan report

scanner v0.1.8 · 2026-09-19 · same rubric, same numbers if you re-run it

2 medium
  • Code scan270 source files scanned15/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 1 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (2)

  • mediumnpm install lifecycle script presentinstall.script
  • mediumnpm install lifecycle script presentinstall.script
    package.json: …npm run build && npm run test:run", "postinstall": "node scripts/preflight.cjs", "vers…
Overall 68/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

Grade history

  • 2026-09-19restoreD → Cscore 68: npm install lifecycle script present; npm install lifecycle script present

Install directly

Runs npx -y @devinmlowe/engram on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add engram -- npx -y @devinmlowe/engram
Add to Cursor

Engram: common questions

Is Engram MCP server safe?
With care: it is graded C, so read the findings first (68/100). Read the Engram safety report
How do I install Engram?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Engram need an API key?
Yes. The registry entry asks for ENGRAM_MCP_TOKEN.
Is Engram maintained?
The last commit was 2 days ago (2026-09-18). The latest release is v0.4.0.
What can I use instead of Engram?
Servers from other publishers that do the same job: Codebase Memory MCP server, Prism Coder MCP server and Deja Vu MCP server. Compare all Engram alternatives.

Alternatives to Engram

Same job from other publishers: the closest match first, then the best rated.

All Engram alternatives →
  • Codebase Memory
    Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
    C
  • Prism Coder
    Session memory for coding agents: local-first recall, drift detection, on-device inference.
    C
  • Deja Vu
    deja-vu: local memory over the session histories of thirty-three coding agents.
    A
  • State Memory MCP
    Deterministic, persistent graph server for tracking workflow state, decisions, and blockers.
    A
  • Plur
    Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP.
    A

More from devinmlowe →