MCP Memory Graph
概览
作者提供的说明（英文原文）
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.
PopNx MCP 的三大支柱
这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
- 使用情况i非常新↓ 285/周 · ★ –
它能帮你做什么
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
- 连接方式: 在你的电脑上运行
- 传输方式: stdio
- 分类: 搜索与 AI 记忆
安装
选择你使用的 AI 应用，然后复制设置。
安装之前
- 基础检查：1 项中通过 1 项
- 在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
- 需要你自己填写：
MCP_MEMORY_DB_PATH,MCP_MEMORY_MODEL
你需要
- npm已安装 Node.js（用于 npx 命令）
你用的是哪个应用？
在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"memory-graph": {
"command": "npx",
"args": [
"-y",
"mcp-memory-graph"
],
"env": {
"MCP_MEMORY_DB_PATH": "your-value",
"MCP_MEMORY_MODEL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add memory-graph --env MCP_MEMORY_DB_PATH=your-value --env MCP_MEMORY_MODEL=your-value -- npx -y mcp-memory-graph运行前请先填写空着的值。
或者自己复制设置
粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json
{
"mcpServers": {
"memory-graph": {
"command": "npx",
"args": [
"-y",
"mcp-memory-graph"
],
"env": {
"MCP_MEMORY_DB_PATH": "your-value",
"MCP_MEMORY_MODEL": "your-value"
}
}
}
}浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"memory-graph": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-memory-graph"
],
"env": {
"MCP_MEMORY_DB_PATH": "your-value",
"MCP_MEMORY_MODEL": "your-value"
}
}
}
}浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。
这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上，无需账户。
需要你填写的值
MCP_MEMORY_DB_PATHenvSQLite database file location (default ~/.mcp-memory/memory.db)MCP_MEMORY_MODELenvHuggingFace embedding model name (default Xenova/all-MiniLM-L6-v2)
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。
它能做什么
它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。
基础检查i
我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 YonasValentin 验证，该账户拥有此仓库
- … 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- – 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表
与“搜索与 AI 记忆”中的其他服务器比较i
- 星标数多于此分类中其他 5717 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 5717 个服务器的 21% 更新
- 基础检查结果等于或优于此分类中其他 5717 个服务器的 100%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。
常见问题
MCP Memory Graph 安全吗？
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。
它需要哪些密钥或代码？
注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端？
它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。
它还在维护吗？
GitHub 仓库最后更新于–，最新版本（2.10.3）于4个月前进入注册中心。
哪些应用可以使用它？
支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
有什么可以替代它？
同一分类中有：Context7, Codebase Memory, Exa
替代选择
同一分类中其他作者的服务器，按星标数排序。
如何看卡片：↓ 每周下载量i★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Codebase Memory
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Exa
Connect AI agents to Exa for web search, content fetching, and multi-step research.
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
MCP Memory Graph
A memory server for Claude Code and any other MCP client. It gives your AI assistant a permanent, searchable memory that lives in one SQLite file on your machine. Store a decision today, ask about it next month, and the answer comes back. Everything runs locally: the embedding model, the search index, the knowledge graph. No cloud account, no API key, no per-token cost.
License: source-available and free for noncommercial use (PolyForm Noncommercial 1.0.0): personal projects, hobby, study, research, charity, education, and government. Commercial use requires a paid license (COMMERCIAL.md).
Who it's for: developers who want Claude (or Cursor, Codex, any MCP client) to remember decisions across sessions. Solo builders and hobbyists use it free. Teams share a knowledge base over git. And anyone who wants to replace a cloud memory service (mem0, Zep, Letta, Supermemory) with something that runs entirely on their own machine.
What it looks like
Run npx mcp-memory-graph serve and you get a local web dashboard for browsing and searching your memory outside Claude.
Search works by meaning, not keywords. The query below ("how do we handle payments") finds the Stripe, GDPR, and Postgres notes even though none of them contains that phrase — each result carries a confidence score and a match-type badge:
Browse and sort the whole store in one table — scope, type, tags, quality score, and how often each memory has been read:
How it compares
mem0, Zep, Letta, and Supermemory are the usual names for AI memory, and several of them have open-source cores. This one is built around a different default: nothing leaves your machine and there's no infrastructure to run.
| MCP Memory Graph | Typical hosted memory service | |
|---|---|---|
| Where it runs | One SQLite file on your machine | A managed cloud service (some also self-host) |
| Embeddings | Local model in Node (MiniLM), no API key | Usually a cloud embedding API |
| Cost per token | $0 — nothing is metered | Usage-based, or a server you operate |
| Extra infrastructure | None | Often Postgres/pgvector, Redis, or a Python service |
| Claude Code integration | First-class: hooks auto-capture and recall | Manual wiring |
| Benchmarks | Committed corpus + runner, reproducible locally | Mostly self-reported |
The trade-off is honest: a single-process SQLite server tops out in the low hundreds of thousands of vectors (see Limitations), and a hosted service will scale past that without you thinking about it. If you're a solo developer or a small team who wants memory that's private, free, and zero-ops, that ceiling is rarely the thing you hit first.
Why this exists
AI assistants forget everything between sessions. Your decisions, your patterns, the bug you fixed last Tuesday: all gone when the conversation ends. This server fixes that.
- Knowledge stored today is searchable tomorrow, next week, next year.
- Search works by meaning, not just keywords. "contract notice period" finds "90-day renewal clause".
- It improves itself. It tracks what gets used, scores quality, extracts learnings from your sessions, and cleans itself up on a schedule.
- It stays private. Local embeddings, no cloud APIs, no telemetry. The one exception is the optional Stop hook, which sends your session transcript to your own locally installed Claude Code (
claude -p) for learning extraction. You can turn that off withreview_on_stop: false. - It works for any kind of knowledge. Engineers store architecture decisions, lawyers store contract patterns, accountants store audit procedures.
Quick start (about 5 minutes)
You need Node.js 20 or newer and Claude Code installed.
1. Get the server. From npm (easiest):
npm install -g mcp-memory-graphOr from source:
git clone https://github.com/YonasValentin/mcp-memory-graph.gitcd mcp-memory-graph npm install npm run build
2. Register the server with Claude Code *(optional — init in step 3 does this for you at user scope):*
# npm install:claude mcp add memory-server -- npx -y mcp-memory-graph
from source:
claude mcp add memory-server node /path/to/mcp-memory-graph/dist/index.js
3. Install the hooks (recommended):
npx mcp-memory-graph initThis is the one command that wires everything up: it registers the MCP server (user scope), installs the auto-capture/recall hooks and the usage skill, writes config, and schedules a nightly cleanup. Answer the prompts, or pass --yes to accept the defaults. (Skip the auto-registration with --no-register if you manage claude mcp yourself.)
4. Try it. Open a Claude Code session and say:
Remember this: we use Postgres for the main app database. Decided 2026-06-01,because we need JSONB and full-text search in one place.
Then, in a later session:
What database did we decide to use, and why?Claude searches its memory and answers with the stored decision. That's the whole loop.
5. Verify the install. Ask Claude:
What memory tools do you have available?It should list all 51 tools (45 memory_*, 3 vault_*, 3 core_memory_*).
The first time a memory tool runs, the embedding model (about 30 MB) downloads from HuggingFace and is cached at ~/.cache/huggingface/. Every start after that is instant.
To undo everything: npx mcp-memory-graph uninstall.
Upgrading
npm install -g mcp-memory-graph@latest # or just let `npx -y mcp-memory-graph` pull itnpx mcp-memory-graph init # re-run to refresh on-disk hooks + the nightly schedule
Upgrading the package updates the code that runs each session (hooks, tools, the server), so server-side fixes apply the next time a tool runs — nothing else needed for those.
But files that init wrote earlier are not rewritten by a package upgrade: the Claude Code hook registrations in settings.json and the macOS launchd plist at ~/Library/LaunchAgents/com.mcp-memory.consolidate.plist. If you installed before 2.6.3, that plist used a bare node that launchd (whose minimal PATH excludes nvm) could not run — so the nightly consolidation silently never fired. Re-run `npx mcp-memory-graph init` once after upgrading to regenerate it with an absolute node path and an output log. Verify it then runs:
launchctl start com.mcp-memory.consolidatecat ~/.mcp-memory/consolidation.log # should show a "Consolidation complete" report
To clear conflict noise that accumulated while the job wasn't running: npx mcp-memory-graph consolidate.
How it works, in plain terms
When you store a memory, the server turns the text into a vector (a list of 384 numbers that captures its meaning) using a small model that runs inside Node.js. It also indexes the text for keyword search. Both live in one SQLite file, by default at ~/.mcp-memory/memory.db.
When you search, the server runs both kinds of search at once, merges the rankings, and returns the best matches with a confidence label. A second model can then re-sort the top results for better precision (this is the reranker, on by default for MCP clients, and it costs about 200 ms).
On top of that sits a knowledge graph: memories link to entities and to each other, so the server can answer questions that need more than one hop, like "what does the payment service depend on?". A nightly "dream cycle" deduplicates, re-scores, prunes, and reports gaps.
The benchmarks, and how to read them
Every number below was produced locally: real embedding model, real production handlers, no network. You can rerun all of them on your own machine.
A quick primer if benchmarks are new to you. A *gold set* is a list of questions where the right answer is known in advance. *Precision@1* asks: was the top result the right one? *Recall@5* asks: was the right answer anywhere in the top 5? *MRR* (mean reciprocal rank) rewards putting the right answer near the top. The *reranker* is a second model that re-sorts the top 50 results; it is slower but noticeably more accurate.
Local gold set
| precision@1 | precision@3 | MRR | search p95 | |
|---|---|---|---|---|
| Hybrid (RRF) | 0.563 | 0.750 | 0.704 | ~4 ms |
| + cross-encoder rerank (MCP default) | 0.813 | 0.875 | 0.867 | ~230 ms |
Reproduce with npm run bench. Full methodology, the gold set itself, and every miss are printed and documented in docs/BENCHMARKS.md.
Scale
With the real embedder and a file-backed SQLite database, retrieval p95 is 9.1 ms at 10,000 vectors and 30 ms at 50,000. The rerank pass adds a roughly constant 200 ms on top. Most memory products publish self-reported, cloud-hosted numbers; these are measured locally and reproducible from a committed corpus and runner.
Public benchmarks
Four public memory benchmarks, run untuned (stock MiniLM embedder, production handlers, zero benchmark-specific tweaks), matching or beating MemPalace on all four:
| Benchmark | Our result | Comparison |
|---|---|---|
| LongMemEval-S | R@5 = 97.8% | vs 96.6% published |
| ConvoMem | R@10 = 93.5% | vs 92.9% |
| LOCOMO | session R@10 = 82.2%, R@50 = 100% | vs 60.3% baseline |
| MemBench | hit@5 = 78.7% | vs their 80.3% *tuned* |
Run them yourself: npm run bench:longmemeval, bench:locomo, bench:convomem, bench:membench. The honest notes (where the reranker helps and where it hurts, the dedup floor on MemBench, gold-set size caveats) are in docs/BENCHMARKS.md.
Features
Core
- 51 MCP tools: CRUD and retrieval, a confidence-tagged knowledge graph, a self-correcting write gate, signed provenance and verification, an event bus with SSRF-guarded webhooks, change propagation and advisor surfaces, resumable session state, expertise profiles, memory tiers, Obsidian vault round-tripping, and GDPR-grade forget and history. Full list below.
- Hybrid search: vector similarity (meaning) plus keyword matching (exact terms), merged with Reciprocal Rank Fusion.
rerank: trueadds the cross-encoder pass.use_graph: trueblends in HippoRAG Personalized PageRank multi-hop scores.as_of:searches the graph as it stood at a past moment. - Local embeddings: Transformers.js running all-MiniLM-L6-v2 (384 dimensions) inside Node.js. No Python, no cloud API, no GPU.
只显示了开头部分；其余内容请在仓库中阅读