MCP.Market

Zikkaron MCP server

by amanhij·io.github.amanhij/zikkaron·v1.0.0·63 stars
No reviews yet

Biologically-inspired persistent memory engine for Claude Code MCP agents

B82/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
Growing

63 stars24 downloads/wk

Reviews

Write one

Nobody has reviewed Zikkaron yet.

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

Zikkaron tools (23, 1 write)

write = sends, deletes, buys or posts

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

  • add_rule

    Add a neuro-symbolic rule for filtering/re-ranking memories.

  • anchor

    Mark critical context as compaction-resistant.

  • assess_coverage

    Assess how well Zikkaron knows about a topic.

  • checkpoint

    Snapshot your current working state for post-compaction recovery.

  • consolidate_now

    Trigger an immediate consolidation cycle.

  • create_triggerwrite action

    Create a prospective memory trigger that fires on matching context.

  • detect_gaps

    Detect knowledge gaps for a project directory.

  • drill_down

    Drill into a cluster to see its members.

  • forget

    Mark a memory for deletion by setting heat to 0, then delete it.

  • get_causal_chain

    Get causal causes and effects for an entity from the PC algorithm DAG.

  • get_project_context

    Return all hot memories for a directory, sorted by heat descending.

  • get_project_story

    Get the autobiographical narrative for a project directory.

  • get_rules

    Get active rules. If directory is provided, returns only applicable rules.

  • install_hooks

    Install Claude Code hooks for automatic Hippocampal Replay.

  • memory_stats

    Return system memory statistics.

  • navigate_memory

    Navigate concept space using Successor Representation cognitive maps.

  • rate_memory

    Rate a memory's usefulness for metamemory tracking.

  • recall

    Semantic + keyword search filtered by heat. Boosts accessed memories.

  • recall_hierarchical

    Retrieve memories from the fractal hierarchy at a specific level or adaptively.

  • remember

    Store a new memory with embedding and optional file hash.

  • restore

    Restore context after compaction using Hippocampal Replay.

  • sync_instructions

    Sync Zikkaron instructions into the global CLAUDE.md file.

  • validate_memory

    Check memory validity against current file state.

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

no findings
  • Code scan37 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 180 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Zikkaron compares

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

Safety score
82/100
higher than 63% of 48,255 servers
Tools
23
the typical server has 7
Tools that change things
4%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
63
more than 95% of 28,688 servers
Downloads a week
24
more than 10% of 12,191 servers with a package

What its tools let an agent do: 19 read · 2 create · 1 change · 1 run or deploy

Install Zikkaron in Claude Code, Cursor or VS Code

claude mcp add zikkaron -- uvx zikkaron
Add to Cursor

What the publisher says

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

Zikkaron

<!-- mcp-name: io.github.amanhij/zikkaron -->

Zikkaron (זיכרון) is Hebrew for "memory."

Your AI forgets you every time you close the tab. Every architecture decision you explained, every debugging rabbit hole you went down together, every "remember, we're using Postgres not SQLite" correction. Gone. You start the next session a stranger to your own tools.

Zikkaron is a persistent memory engine for Claude Code built on computational neuroscience. It remembers what you worked on, how you think, what you decided and why. Not as a dumb text dump that gets shoved into context, but as a living memory system that consolidates, forgets intelligently, and reconstructs the right context at the right time.

26 subsystems. 24 MCP tools. Runs entirely on your machine. One SQLite file.

Two minutes to never repeat yourself again

pip install zikkaron

Add to your Claude Code config:

{
  "mcpServers": {
    "zikkaron": {
      "command": "zikkaron"
    }
  }
}

Tell Claude how to use it. Drop this in your global ~/.claude/CLAUDE.md (your home directory, not per-project):

## Memory
- On every new session, call `recall` with the current project name
- Before starting any task, call `get_project_context` for the current directory
- After completing significant work, call `remember` to store decisions and outcomes

Or just let Zikkaron handle it. On every startup, it automatically syncs ~/.claude/CLAUDE.md with the latest instructions via sync_instructions. You set it up once and never think about it again.

What this actually feels like

Monday. You spend an hour debugging a nasty auth token race condition. Claude helps you trace it to a TTL mismatch between Redis and your JWT config. You fix it. Claude stores the memory.

Thursday. A user reports intermittent logouts. You open Claude Code in the same project. Before you even describe the bug, Claude recalls the Redis TTL fix from Monday, checks if it's related, and asks whether the middleware you added is handling the edge case where Redis restarts mid-session.

That's the difference. Not "here's your conversation history." Real recall. The kind where your tools understand the shape of what you've been building, not just the words you typed last time.

Retrieval that actually works

We tested Zikkaron against LoCoMo (Maharana et al., ACL 2024), the standard benchmark for long conversation memory. 10 conversations, 1,986 questions, everything from simple factual lookups to multi-hop reasoning to adversarial trick questions designed to trip you up.

The thing is, there's no LLM running at query time. No API calls. No billion parameter models. Just a 22MB embedding model, a SQLite file, and a bunch of neuroscience algorithms doing the heavy lifting. Most systems that hit numbers like these need GPT-4 in the loop. Zikkaron gets there with Hopfield energy scoring, spreading activation, and a cross-encoder reranker.

BEAM: 10 million tokens of conversation, one memory system

Shortened. The full README is on GitHub.

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

Zikkaron: common questions

Is Zikkaron MCP server safe?
Mostly: it is graded B (82/100). Read the Zikkaron safety report
How do I install Zikkaron?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Zikkaron need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Zikkaron maintained?
The last commit was 217 days ago (2026-04-01). The latest release is v1.0.0.
What can I use instead of Zikkaron?
Servers from other publishers that do the same job: State Memory MCP server and Knowl MCP server.
How does Zikkaron compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); tools 23 (the typical server has 7); tools that change things 4% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Zikkaron

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