经 AI Skill Hub 精选评估,Mori MCP工具 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
Mori MCP工具 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。
Mori MCP工具 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/fjwood69/mori
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mori-mcp--": {
"command": "npx",
"args": ["-y", "mori"]
}
}
}
# 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 Mori MCP工具 执行以下任务... Claude: [自动调用 Mori MCP工具 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": {
"mori_mcp__": {
"command": "npx",
"args": ["-y", "mori"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Mori (森) is a shared memory layer for AI coding agents — one that compounds. Sessions feed a dream pipeline that distils activity into durable knowledge, so every instance starts informed rather than cold. One Mori, many agents — every session benefits from what every other session learned.
Works with any OpenAI-compatible provider. No homelab, no Anthropic account, no LLM Gateway required — though those all work too.
---
| Capability | What it does | Slash command |
|---|---|---|
| **Dream pipeline** | Auto-distils session events into structured memories | /dream |
| **Session grounding** | Loads shared context at session start — not per-query RAG; lightweight delta re-grounding after context compaction | /brief, /brief --post-compact |
| **Memory search** | Ranked full-text search and browse across the shared store (SQLite FTS5 / Postgres tsvector) | /pensieve |
| **Web dashboard** | Built-in memory browser served at the mori root URL — search, browse, unfurl | — |
| **Universal ingestion** | Feed PDFs, images, git, transcripts into the memory store | /ingest |
| **Strategic review** | LLM guidance with focus areas and auto-injected standards | /consult |
| **Requirements tracking** | Lightweight project checklist surfaced via /brief | /req |
| **Governance** | Versioning, trusted dreamers, rollback, attribution | — |
| **NATS messaging** | Real-time cross-device awareness | /nats |
| **Inter-agent messaging** | Send tasks, questions, and decisions across the device network | /msg |
| **Skill deployment** | Push slash commands to all devices in one step | /update |
Full reference: docs/reference/slash-commands.md
---
See docs/deployment/quickstart.md for all platforms. Docker Compose is the fastest path:
```bash git clone https://github.com/fjwood69/mori.git cd mori cp deploy/homelab/.env.example deploy/homelab/.env
./scripts/install-mori-claude.sh
./scripts/install-mori-cursor.sh
```bash git clone https://github.com/fjwood69/mori.git cd mori podman build -t localhost/mori-advisor:latest .
```
| Platform | Installer | Full guide |
|---|---|---|
| Claude Code | ./scripts/install-mori-claude.sh | [docs/getting-started/claude-code.md](docs/getting-started/claude-code.md) |
| Cursor | ./scripts/install-mori-cursor.sh | [docs/getting-started/cursor.md](docs/getting-started/cursor.md) |
| Google Antigravity IDE | ./scripts/install-mori-antigravity.sh | [docs/getting-started/antigravity.md](docs/getting-started/antigravity.md) |
| Cline | ./scripts/install-mori-cline.sh | [docs/getting-started/cline.md](docs/getting-started/cline.md) |
---
docker compose -f deploy/homelab/docker-compose.yml up -d ```
Configuration reference → docs/reference/configuration.md Recommended models → docs/reference/models.md For teams → docs/for-teams.md Team configuration reference → docs/reference/team-configuration.md
Key environment variables:
| Variable | Default | Description |
|---|---|---|
MORI_PROVIDER_MODE | bifrost | direct or bifrost |
MORI_API_KEY | — | Provider key (required in direct mode) |
MORI_BASE_URL | — | OpenAI-compatible base URL |
MORI_MODEL | moonshotai/kimi-k2.6 | Advisor + consult model |
MORI_DREAM_MODEL | falls back to MORI_MODEL | Dream + ingest distillation model |
MORI_FAST_MODEL | deepseek/deepseek-v4-flash | Contradiction scan + freshness checks |
MORI_API_KEYS | — | Named client API keys: name:secret,name:secret,... — see [Authentication](docs/reference/configuration.md#authentication) |
MORI_TRUSTED_DREAMERS | — | Comma-separated trusted hostnames |
MORI_DREAM_INTERVAL | 60 | Dream cron interval (minutes) |
MORI_STANDARDS_DIR | — | Path to team standards .md files |
MORI_MSG_HEADLESS_ENABLED | false | Spawn headless Claude for incoming tasks |
MORI_MSG_HEADLESS_TRUSTED | — | Comma-separated hostnames allowed to trigger headless CC |
Authentication: Set MORI_API_KEYS to give each client a named key. Without it the server starts in open mode (fine for private Tailscale networks; always set keys for shared or internet-accessible deployments). Generate secrets with python3 -c "import secrets; print(secrets.token_hex(32))". Full details: docs/reference/configuration.md → Authentication.
---
Session events are captured via Claude Code lifecycle hooks and distilled into structured memories by a configurable LLM.
Hook fires → POST /api/events/raw → SQLite events table
↓
PreCompact → POST /api/precompact → dream_run() reads since watermark
↓
LLM distills events → structured memories
↓
memories written to store (with attribution)
↓
watermark advanced
The PreCompact hook triggers an immediate synchronous dream before context compression — so nothing is lost at the moment it matters most.
Its counterpart, the PostCompact hook, fires /brief --post-compact after compression — a lightweight delta that surfaces only what changed in the shared store since your last brief (new, superseded, and evicted memories), skipping the full base reload and the freshness scan. PreCompact preserves what this session learned; PostCompact re-grounds it on what every other instance changed while it was busy.
What it captures: PostToolUse, PostToolUseFailure, PreCompact, UserPromptSubmit, Stop — tool calls, prompts, errors, stop reasons, session ID, hostname, working directory, transcript path, and (on Stop) the assistant's own reasoning — the plans, analysis, and decisions behind each turn.
高质量的开源MCP工具,为AI编码代理提供了共享内存层
该工具使用 AGPL-3.0 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。
⚠️ AGPL 3.0 — 最严格的 Copyleft,网络服务端使用也需开源,SaaS 使用受限。
AI Skill Hub 点评:Mori MCP工具 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | mori |
| 原始描述 | 开源MCP工具:mori MCP server — A shared memory layer for AI coding agents — one that compound。⭐17 · Python |
| Topics | mcpai-agentsanthropicclaude-codellm |
| GitHub | https://github.com/fjwood69/mori |
| License | AGPL-3.0 |
| 语言 | Python |
收录时间:2026-06-04 · 更新时间:2026-06-08 · License:AGPL-3.0 · 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