MCP.Market

Memstack MCP server

by isiomaC·io.github.isiomaC/memstack·v0.8.5
No reviews yet

MCP server for persistent, searchable memory for AI agents.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars475 downloads/wk

Reviews

Write one

Nobody has reviewed Memstack yet.

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

Memstack tools (18, 4 write)

write = sends, deletes, buys or posts

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

  • memory_compile_context

    Compile memories into an LLM-ready system prompt (markdown formatted, token-budgeted, split into important and recent sections).

  • memory_deletewrite action

    Delete a single memory by ID.

  • memory_delete_manywrite action

    Delete multiple memories by ID in one call. Returns the number actually deleted.

  • memory_dry_run_prunewrite action

    Preview what would be pruned by a given strategy WITHOUT actually deleting. Scoped to a single actor \u2014 defaults to the current session actor. Returns the memory IDs that would be removed.

  • memory_export

    Export a snapshot of memories for backup or migration. Returns { version, memories, exportedAt }.

  • memory_get

    Get a single memory by ID. Returns null if not found.

  • memory_health

    Check the health of storage, LLM, and embedding connections.

  • memory_import

    Import memories from a snapshot previously produced by memory_export. Restores each memory as-is, including its original ID.

  • memory_merge

    Merge multiple memories into one. Uses the highest-importance memory as the base and appends content from the rest.

  • memory_process

    Store a memory with auto-enrichment (importance scoring, tag extraction, auto-summarization, auto-pruning). This is the primary method for recording interactions.

  • memory_prune

    Prune (delete) memories matching the given strategy. Scoped to a single actor \u2014 defaults to the current session actor. Returns the pruned memory IDs and count. Handle with care.

  • memory_purge_actorwrite action

    Delete ALL memories belonging to a specific actor. Irreversible.

  • memory_retrieve

    Retrieve memories for an actor with optional filtering, semantic search, and date range constraints.

  • memory_stats

    Get memory statistics: total count, by type, by actor, average importance, and more.

  • memory_store

    Store a memory directly without enrichment. Use this when you already have importance/tags or want precise control.

  • memory_store_batch

    Store multiple memories in one call, directly without enrichment. Embeddings (if configured) are computed in a single batched call for efficiency.

  • memory_summarize

    Summarize old memories into a single summary memory. Compresses N interactions into 1 summary via LLM.

  • memory_touch

    Bump a memory's recency (last-accessed timestamp) without changing its content, id, or createdAt.

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

no findings
  • Code scan5 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 4 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Memstack compares

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

Safety score
92/100
higher than 93% of 48,243 servers
Tools
18
the typical server has 7
Tools that change things
22%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
475
more than 87% of 12,306 servers with a package

What its tools let an agent do: 14 read · 4 change

Release history: 3 versions in the registry since 2026-09-03, latest 2026-10-08, typically one every 29 days.

Install Memstack in Claude Code, Cursor or VS Code

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

claude mcp add memstack -- npx -y @memstack/mcp
Add to Cursor

What the publisher says

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

MemStack

Implementation priority is maintained in the canonical roadmap.

The open-source memory layer for AI agents — store, retrieve, summarize, and prune.

# Use MemStack in your application
npm install @memstack/core

# Give your coding agent the MemStack skill
npx skills add isiomaC/memstack

@memstack/core is the runtime SDK; the Agent Skill teaches compatible coding agents how to integrate and operate MemStack correctly.

The problem: AI agents forget. Every interaction starts from zero. You either stuff everything into the context window (expensive, slow, degrades output quality) or the agent has no memory of past conversations.

What MemStack does: A persistent memory pipeline that lives between your agent and the LLM. It stores every interaction, retrieves only what's relevant, summarizes old memories to save tokens, and prunes stale ones automatically. One method call, no infrastructure required.

Think of it as the open-source alternative to Mem0 — pluggable storage, bring your own LLM, zero vendor lock-in.

Table of Contents

  • Why MemStack
  • Quick Start
  • The Memory Pipeline
  • Store
  • Retrieve
  • Compile Context
  • Summarize
  • Prune
  • Real-World Use Cases
  • Support Agent
  • RAG Pipeline
  • Multi-User Chatbot

Why MemStack

LLMs have context windows, not memory. The difference matters.

What MemStack handles that raw vector DBs don't:

Shortened. The full README is on GitHub.

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

Memstack: common questions

Is Memstack MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Memstack safety report
How do I install Memstack?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Memstack need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Memstack maintained?
The last commit was 24 days ago (2026-10-12). The latest release is v0.8.5.
What can I use instead of Memstack?
Servers from other publishers that do the same job: State Memory MCP server and Knowl MCP server.
How does Memstack compare with other MCP servers?
safety score 92/100 (higher than 93% of 48,243 servers); tools 18 (the typical server has 7); tools that change things 22% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Memstack

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

  • 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