MCP.Market

MCP Light Memory MCP server

by PeterPirog·io.github.PeterPirog/mcp-light-memory·v1.8.1

Local-first persistent memory for coding agents and MCP clients.

B80/100grade B
What users say
No reviews yet
Be the first
Safety scan
B80/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed MCP Light Memory yet.

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

MCP Light Memory tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-10-31 · same rubric, same numbers if you re-run it

no findings
  • –Code scanpackage could not be scannedn/a
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 65 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 80/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How MCP Light Memory compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
80/100
higher than 60% of 48,255 servers

Install MCP Light Memory in Claude Code, Cursor or VS Code

The registry entry has no remote endpoint or installable package.

What the publisher says

From the MCP Light Memory repository's README, as published. We do not edit it. Read it on GitHub

MCP Light Memory

Lightweight local-first persistent memory for coding agents and MCP clients. formerly internal-rag

What is this?

MCP Light Memory is a lightweight, local-first, persistent memory system for coding agents and MCP clients (Warp, OpenCode, JetBrains AI Assistant / PyCharm, Claude Code, Cursor). It acts as a checkpoint + retrieval layer — it stores the minimum durable state needed to resume complex work across sessions, without keeping the full conversation in the model's context window.

When your agent starts a task, it calls context and gets back relevant past decisions, gotchas, constraints, and hypotheses — ranked, deduplicated, and trust-bounded. When it finishes, it checkpoints the working state. Next session, even after a restart, the memory is there.

Why use it?

How it works (mechanisms)

  • Markdown is the source of truth. Every memory is a .md file with YAML frontmatter (id, type, status, tags, sources, links, validfrom, validto, supersedes). Human-readable, diffable, durable.
  • SQLite is a rebuildable cache. BM25/FTS5 index + optional embedding vectors + usage tracking. Delete it and everything rebuilds from Markdown.
  • Retrieval: pure-Python BM25 + optional dense embeddings → RRF fusion → MMR diversification → policy boosts (type/status/temporal) → token-budget cut. Adaptive mode: sparse first, dense only if weak.
  • Lifecycle: remember → update → supersede (links both directions, never deletes history) → forget (archives, never deletes) → timeline (temporal view). search --at YYYY-MM-DD for historical queries.
  • Trust boundary: retrieved content is wrapped in === BEGIN/END INTERNALRAG MEMORY === with a SECURITY NOTICE header. Structured JSON/MCP carries trust: untrusted + optional securityflags: ["instructionlikecontent"].
  • Evidence freshness: each result includes evidence_state (present/missing/unverifiable) for local path-like evidence — derived at retrieval time, never persisted.
  • Multi-project router: one MCP stdio server in front of many projects via a JSON registry. write:false blocks mutating tools before spawning a child. Per-call subprocess isolation (no shared state).

Setup

Prerequisites

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-10-31downgradeA → Bscore 80

MCP Light Memory: common questions

Is MCP Light Memory MCP server safe?
Mostly: it is graded B (80/100). Read the MCP Light Memory safety report
Does MCP Light Memory need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is MCP Light Memory maintained?
The last commit was 69 days ago (2026-08-27). The latest release is v1.8.1.
What can I use instead of MCP Light Memory?
Servers from other publishers that do the same job: Deja Vu MCP server, Memorix MCP server and Nautilus Compass Memory MCP server.

Alternatives to MCP Light Memory

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

  • Deja Vu
    deja-vu: local memory over the session histories of forty-three coding agents.
    A
  • Memorix
    Local-first project memory with legacy MCP and 2026 discovery compatibility.
    B
  • Nautilus Compass Memory
    Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
    B
  • State Memory MCP
    Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.
    A
  • Knowl
    Persistent memory for AI agents, for code, research and everyday life. Stale facts retire.
    A