经 AI Skill Hub 精选评估,开源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。
local-first background AI daemon for Logseq OG,转换你的笔记成一个有意图的agent。
开源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。
local-first background AI daemon for Logseq OG,转换你的笔记成一个有意图的agent。
开源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/MarcoPorcellato/matryca-plumber
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"--mcp--": {
"command": "npx",
"args": ["-y", "matryca-plumber"]
}
}
}
# 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 开源MCP工具 执行以下任务... Claude: [自动调用 开源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": {
"__mcp__": {
"command": "npx",
"args": ["-y", "matryca-plumber"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
v1.5 — Ironclad Release. Agentic Knowledge Management for Logseq OG. An enterprise-grade, local-first background AI daemon with a real-time Sovereign UI control room, a typed CLI, and direct Logseq Markdown AST mutation (no Logseq HTTP API, no auxiliary database). The default experience is autonomous: the daemon and Python workers poll your graph, run structured local-LLM passes, and commit indexes and lint artifacts while you work or sleep. An optional FastMCP stdio sidecar exposes the same headless mutation plane to external clients (for example Claude Desktop) — same graph_dispatch contract, not a separate data path. Heavily inspired by Andrej Karpathy's LLM-Wiki vision. 100% native Logseq AST parity, optimistic concurrency safety, versioned AI authorship stamping.

Matryca Plumber is a 100% headless, sandboxed standalone daemon + CLI that turns your local Logseq graph into a high token-density agentic workspace — no network APIs and no Logseq desktop JSON-RPC. It treats your vault as a tree of blocks, not a flat document store. Logseq OG remains optional: humans and the daemon co-edit the same .md trees on disk.
Matryca Plumber is not a one-shot script — it is an enterprise-grade, local-first background AI daemon for Logseq. It polls your graph on a duty cycle, calls a local LLM (LM Studio or Ollama), appends semantic indexes, runs optional cognitive lint modules, and logs every token transaction — while you edit the same .md files in Logseq or leave the vault idle. Optional MCP-attached sessions reuse the identical mutation plane for interactive queries; they are not required for background operation. Every write path mirrors Logseq's on-disk AST contract: page frontmatter at line 0, block properties contiguous to their parent bullet, namespace filenames encoded exactly like Logseq's Clojure Datalog layer, and optimistic concurrency control that aborts stale writes when you type during inference.
Matryca Plumber turns your local graph into a high token-density agentic workspace by continuously polling your notes, running local LLMs (like LM Studio or Ollama), appending semantic indexes, and healing broken links—all completely offline, while you work or sleep.
Zero Cloud. Zero Data Leaks. 100% Native Logseq AST.
---
.md files directly using atomic file I/O.st_mtime before any AI inference. If you typed in Logseq while the AI was "thinking", Matryca aborts its write. No silent data loss..matryca_plumber_daemon.lock).---
The fastest way to get started is using uv, the blazing-fast Python package manager.
Run the CLI directly without polluting your system:
uvx --from matryca-plumber matryca-plumber status
Install the binary to use the matryca command anywhere:
uv tool install matryca-plumber
Want to contribute or run from source?
```bash git clone https://github.com/MarcoPorcellato/matryca-plumber.git cd matryca-plumber make install
cd frontend && npm install && npm run build && cd ..
Copy .env.example to .env. The only required variable is your graph path:
LOGSEQ_GRAPH_PATH=/absolute/path/to/your/Logseq/graph
MATRYCA_LM_BASE_URL=http://localhost:1234/v1 # LM Studio or Ollama endpoint
MATRYCA_LM_MODEL=qwen2.5-coder-7b # Exact model name loaded
(See docs/ARCHITECTURE.md for advanced thermal pacing, context compression, and deep linter settings).
---
该项目是一个开源的MCP工具,使用Python开发,具有local-first background AI daemon的特性,适合Logseq OG的使用。
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。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:开源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 | matryca-plumber |
| 原始描述 | 开源MCP工具:local-first background AI daemon for Logseq OG. Turns your notes into an agentic。⭐19 · Python |
| Topics | mcpagentic-memoryai-agentsandrej-karpathyautonomous-agentsknowledge-graphpython |
| GitHub | https://github.com/MarcoPorcellato/matryca-plumber |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-05-24 · 更新时间:2026-05-30 · License:Apache-2.0 · 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