Memory MCP server
Persistent memory + git snapshots for Claude Code. Never lose context or code.
98 stars59 downloads/wk
Reviews
Write oneNobody has reviewed Memory yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Memory tools (10, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
memory_askAsk a question and get an answer synthesized from project memories. Like RAG over your project knowledge.
memory_consciousnessGenerate the full consciousness document. This is what gets written to CLAUDE.md.
memory_consolidateManually trigger memory consolidation. Merges duplicates, removes outdated memories, keeps memory sharp.
memory_deletewrite actionDelete a specific memory by ID.
memory_initInitialize project memory with name and description.
memory_recallRecall all active memories, optionally filtered by type or tags.
memory_relatedGet all memories related to specific tags/areas. Use to explore a topic in depth.
memory_saveSave a memory about this project. Records decisions, patterns, architecture, gotchas, progress, or context for future sessions.
memory_searchSearch memories by keyword. Returns ranked results matching the query across content and tags.
memory_statsShow memory statistics: counts by type, active/archived/superseded, last consolidation.
Public scan report
scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it
- Code scan19 source files scanned13/25
- –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 242 days ago4/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (1)
- highShell command built from a string (injection risk)
exec.shell-concatdist/cli.js: …= require("child_process"); exec(`open "${outputPath}"`); } return…
How Memory compares
Against every graded Developer tools MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 57/100
- higher than 11% of 1,119 Developer tools servers
- Tools
- 10
- the typical Developer tools server has 7
- Tools that change things
- 10%
- typical: 5%. Fewer write tools means less an agent can break
- GitHub stars
- 98
- more than 95% of 855 Developer tools servers
- Downloads a week
- 59
- more than 44% of 436 Developer tools servers with a package
What its tools let an agent do: 9 read · 1 change
Install Memory in Claude Code, Cursor or VS Code
Runs npx -y claude-code-memory on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add memory-mcp -- npx -y claude-code-memory
What the publisher says
From the Memory repository's README, as published. We do not edit it. Read it on GitHub
memory-mcp
Persistent memory + automatic git snapshots for Claude Code. Never lose context. Never lose code.
🧠 45 memories | 📊 2.8K tokens | 📸 23 snapshots | ⏱️ 5m agoWhy memory-mcp?
What makes it different
- Git Snapshots — Every memory save commits your entire project. Roll back anytime.
- Two-Tier Memory — CLAUDE.md loads instantly, deep store searchable mid-conversation.
- LLM-Powered — Haiku extracts what matters, consolidates duplicates, prunes stale info.
- Visual Dashboard — See your context: tokens, memories by type, snapshot history.
- Zero friction — No commands to run. It just works silently.
Quick Start
# Install globally
npm install -g claude-code-memory
# Interactive setup (API key + hooks)
memory-mcp setup
# Initialize a project
memory-mcp init ~/Projects/my-appThat's it. Start coding. Memories accumulate automatically.
How It Works
graph TB
subgraph "Phase 1: Silent Capture"
A[Claude Code Session] -->|User sends message| B[Claude responds]
B -->|Hook fires: Stop/PreCompact/SessionEnd| C[extractor.js]
C --> D[Read transcript from cursor]
D --> E[Chunk if >6000 chars]
E --> F[Send to Haiku LLM]
F -->|Extract memories as JSON| G[Dedup via Jaccard similarity]
G --> H[Save to .memory/state.json]
H --> I[Decay confidence scores]
I --> J{Consolidation needed?}
J -->|>80 memories or every 10 extractions| K[Haiku merges/drops]
J -->|No| L[Sync CLAUDE.md]
K --> L
end
subgraph "Phase 2: Recovery"
M[New session starts] -->|Built-in behavior| N[Claude reads CLAUDE.md]
N --> O[Claude has full project context]
end
subgraph "Phase 3: Deep Recall"
O --> P{Need specific context?}
P -->|memory_search| Q[Keyword search across memories]
P -->|memory_ask| R[Haiku synthesizes answer from top 30 matches]
P -->|memory_related| S[Tag-based retrieval]
end
subgraph "Data Store"
H -.-> T[(.memory/state.json<br/>Full memory store)]
L -.-> U[(CLAUDE.mdTwo-tier memory architecture:
Silent capture via hooks:
Claude Code hooks fire after every response (Stop), before context compaction (PreCompact), and at session end (SessionEnd). A fast LLM (Haiku) reads the transcript and extracts:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Memory: common questions
- Is Memory MCP server safe?
- With care: it is graded C, so read the findings first (57/100). Read the Memory safety report
- How do I install Memory?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Memory need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Memory maintained?
- The last commit was 279 days ago (2026-01-29). The latest release is v1.2.1.
- What can I use instead of Memory?
- Servers from other publishers that do the same job: Palinode MCP server, Kindex MCP server and Kindex MCP server.
- How does Memory compare with other Developer tools MCP servers?
- safety score 57/100 (higher than 11% of 1,119 Developer tools servers); tools 10 (the typical Developer tools server has 7); tools that change things 10% (typical: 5%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Memory
Same job from other publishers: the closest match first, then the best rated.
- PalinodeInspectable, correctable project memory in git-versioned Markdown for AI agents.not reviewedEstablishedC
- KindexPersistent knowledge graph and MCP server for AI workflows with git-tracked project context.not reviewedEstablishedA
- KindexPersistent knowledge graph and MCP server for AI workflows with git-tracked project context.not reviewedEstablishedB
- NexusmemLocal-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.not reviewedGrowingA
- Agent MemoryGit-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.not reviewedGrowingA