MemoryBLOCK
Persistent memory for Claude Code — never lose context between sessions
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/claude-code-memory) [](https://www.npmjs.com/package/claude-code-memory) [](LICENSE) [](package.json) [](tsconfig.json)
Persistent memory + automatic git snapshots for Claude Code. Never lose context. Never lose code.
🧠 45 memories | 📊 2.8K tokens | 📸 23 snapshots | ⏱️ 5m ago
Why 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-app
That's it. Start coding. Memories accumulate automatically.
How It Works
graph TB subgraph "Phase 1: Silent Capture" A[Claude Code Se
a455c84259a7OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add claude-code-memory -- npx -y [email protected]
Exposed tools (10)
7 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
memory_ask | read | Ask a question and get an answer synthesized from project memories. Like RAG over your project knowledge. |
memory_consciousness | read | Generate the full consciousness document. This is what gets written to CLAUDE.md. |
memory_consolidate | write | Manually trigger memory consolidation. Merges duplicates, removes outdated memories, keeps memory sharp. |
memory_delete | destructive | Delete a specific memory by ID. |
memory_init | read | Initialize project memory with name and description. |
memory_recall | read | Recall all active memories, optionally filtered by type or tags. |
memory_related | read | Get all memories related to specific tags/areas. Use to explore a topic in depth. |
memory_save | write | Save a memory about this project. Records decisions, patterns, architecture, gotchas, progress, or context for future sessions. |
memory_search | read | Search memories by keyword. Returns ranked results matching the query across content and tags. |
memory_stats | read | Show memory statistics: counts by type, active/archived/superseded, last consolidation. |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (2 observation(s))
- Shell
- declared (6 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
atob( ... new Function(
exec(`open "${outputPath}"`);memory_delete
@modelcontextprotocol/sdk, zod, @types/node, typescript
.smithery/shttp/module.js.map
Gates applied: critical_finding, no_behavioural_pass.
a455c84259a7full audit observations/trust-audit/mcp-server/yuvalsuede__memory-34.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | a455c84259a7 | BLOCK | D | 69 | first audit |
Questions
What is the Memory MCP server?
Persistent memory for Claude Code — never lose context between sessions
What tools does Memory expose?
10 in total: 7 read-only, 2 that write, and 1 that can delete or overwrite (memory_delete). Every one is listed on this page with its risk.
Is Memory safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Memory need?
It reads ANTHROPIC_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Memory run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as claude-code-memory at 1.2.1.
How current is this page?
The grade is for one exact copy of the source (a455c84259a7), read on 2026-10-07. The repository is watched and re-audited when it changes.