MCP内存跟踪 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分，整体质量较高。我们推荐使用将其纳入你的 AI 工具库，帮助提升工作效率。
MCP内存跟踪 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。
MCP内存跟踪 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。
# 方式一：通过 Claude Code CLI 一键安装
claude skill install https://github.com/syncable-dev/memtrace-public
# 方式二：手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp----": {
"command": "npx",
"args": ["-y", "memtrace-public"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例： 用户: 请帮我用 MCP内存跟踪 执行以下任务... Claude: [自动调用 MCP内存跟踪 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入："列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"mcp____": {
"command": "npx",
"args": ["-y", "memtrace-public"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="docs/memtrace-hero.svg" alt="Memtrace — structural memory for AI coding agents" width="100%"/> </p>
<p align="center"> <a href="docs/">📖 Docs</a> · <a href="https://github.com/syncable-dev/memtrace-public/stargazers">⭐ Star us</a> · <a href="https://memtrace.io">memtrace.io</a> · <a href="https://www.npmjs.com/package/memtrace">npm</a> · <a href="https://discord.gg/gzedUSNbna">Discord</a> </p>
<p align="center"> Memtrace turns your codebase into a live knowledge graph that AI coding agents can query in milliseconds — every function, class, call edge, and version, across every session, without re-reading files or breaking things they can't see. </p>
<p align="center"> <b>Get your fleet on shared structural memory in under 90 seconds.</b> </p>
<p align="center"> <b>Structural</b> · zero LLM calls · <b>Bi-temporal</b> · time-travel queries · <b>Replay-aware</b> · zero blind refactors </p>
<p align="center"> <a href="https://github.com/syncable-dev/memtrace-public/stargazers"><img src="https://img.shields.io/github/stars/syncable-dev/memtrace-public?style=flat-square&color=00d4b8&logo=github&logoColor=white&label=stars&cacheSeconds=300" alt="Stars"/></a> <a href="https://www.npmjs.com/package/memtrace"><img src="https://img.shields.io/npm/v/memtrace?style=flat-square&color=00d4b8&logo=npm&logoColor=white&label=npm&cacheSeconds=300" alt="npm version"/></a> <img src="https://img.shields.io/badge/license-Proprietary%20EULA-E879F9?style=flat-square" alt="License"/> <img src="https://img.shields.io/badge/runtime-Rust-orange?style=flat-square&logo=rust" alt="Rust"/> <img src="https://img.shields.io/badge/MCP-native-00d4b8?style=flat-square" alt="MCP"/> <img src="https://img.shields.io/badge/languages-20%2B-22d3ee?style=flat-square" alt="Languages"/> <a href="https://discord.gg/gzedUSNbna"><img src="https://img.shields.io/badge/Discord-join-5865F2?style=flat-square&logo=discord&logoColor=white" alt="Discord" /></a> <img src="https://img.shields.io/badge/private%20beta-active-f59e0b?style=flat-square" alt="Private Beta"/> </p>
---
Memtrace runs locally — first index is CPU/RAM intensive, subsequent queries and incremental indexing are much lighter.
| Minimum | Recommended | |
|---|---|---|
| CPU | 4 cores | 8+ cores for large monorepos |
| Memory | 8 GB RAM | 16–32 GB RAM |
| Disk | 5 GB free | 10–20 GB free |
| GPU | Not required | Not required |
| Node.js | ≥ 18 | Current LTS |
| Git | Required for temporal analysis | Full repo history for best results |
---
memtrace uninstall # removes skills, MCP server, plugin, settings
npm uninstall -g memtraceAlready ran npm uninstall first? The cleanup script is at ~/.memtrace/uninstall.js:
node ~/.memtrace/uninstall.jsnpm install -g memtrace --include=optional
npm install -g @memtrace/darwin-arm64 ```
This typically only happens on machines where npm is configured to skip optional dependencies (corporate npmrc, certain CI caches).
---
Mem0 and Graphiti are strong conversational memory engines designed for tracking entity knowledge (e.g. User -> Likes -> Apples). They excel at that. For code intelligence specifically, the tradeoff is that they rely on LLM inference to build their graphs — which adds cost and time when processing thousands of source files.
Graphiti processes data through add_episode(), which triggers multiple LLM calls per episode — entity extraction, relationship resolution, deduplication. At ~50 episodes/minute (source), ingesting 1,500 code files takes 1–2 hours.
Mem0 processes data through client.add(), which queues async LLM extraction and conflict resolution per memory item (source). Bulk ingestion with infer=True (default) means every file passes through an LLM pipeline. Throughput is bounded by your LLM provider's rate limits.
Both accumulate $10–50+ in API costs for large codebases because every relationship is inferred rather than parsed.
Memtrace takes a different approach: it indexes 1,500 files in 1.2–1.8 seconds for $0.00 — no LLM calls, no API costs, no rate limits. Native Tree-sitter AST parsers resolve deterministic symbol references (CALLS, IMPLEMENTS, IMPORTS) locally. The tradeoff is that Memtrace is purpose-built for code — it doesn't handle conversational entity memory the way Mem0 and Graphiti do.
---
The installer also writes skills/guidance and MCP configuration for the newer agent surfaces:
| Agent | Global skills / guidance | Global MCP config | Project-local support |
|---|---|---|---|
| Codex | ~/.agents/skills/ | ~/.codex/config.toml | .agents/skills/, .codex/config.toml |
| Windsurf | ~/.codeium/windsurf/skills/ | ~/.codeium/windsurf/mcp_config.json | .windsurf/skills/; MCP remains user-level |
| VS Code / Copilot | ~/.copilot/skills/ | VS Code user mcp.json | .github/skills/, .vscode/mcp.json |
| Hermes | ~/.hermes/skills/ | ~/.hermes/config.yaml | user-level only |
| OpenCode | ~/.config/opencode/skills/ | ~/.config/opencode/opencode.json | .opencode/skills/, opencode.json |
| Kiro | ~/.kiro/steering/ | ~/.kiro/settings/mcp.json | .kiro/steering/, .kiro/settings/mcp.json |
Install only selected integrations:
npx memtrace-skills install --only codex,windsurf,vscode,hermes,opencode,kiroInstall project-local config where supported:
npx memtrace-skills install --only codex,vscode,opencode,kiro --localnpm install -g memtrace ships a small main package + a platform-specific binary (one of @memtrace/darwin-arm64, @memtrace/linux-x64, @memtrace/win32-x64). If memtrace start ever says "Could not find binary for your platform":
```bash
高质量的MCP工具，支持AI编码代理
该工具使用 NOASSERTION 协议，商用场景请仔细阅读协议条款，必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
经综合评估，MCP内存跟踪 在MCP工具赛道中表现稳健，质量良好。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。
| 原始名称 | memtrace-public |
| 原始描述 | 开源MCP工具：Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM 。⭐171 · Python |
| Topics | mcpai-agentsbi-temporal-graph |
| GitHub | https://github.com/syncable-dev/memtrace-public |
| License | NOASSERTION |
| 语言 | Python |
收录时间：2026-05-25 · 更新时间：2026-05-26 · License：NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型，复制安装指令后粘贴到对应客户端