grainjournal

grainjournal

An MCP-native journaling server that prompts one question per day and captures your responses verbatim, with no AI rewriting or analysis. It integrates with Claude Desktop, Cline, or cron scripts, storing everything as markdown in your vault.

Category
访问服务器

README

grainjournal

MCP-native journaling with verbatim capture.

A Model Context Protocol server that prompts you to journal one question per day and captures your answers verbatim — no AI reads your words, no AI rewrites them, nothing added.

Why

The journaling space has apps that ingest your raw material and give you back "insights." grainjournal does the opposite. It's a philosophical position: your journal is yours. We don't touch your words. We just make it easier to write and preserve exactly what you wrote.

  • MCP-native. Works as an MCP server — integrate it with Claude Desktop, Cline, your AI agent, or run it as a standalone cron job.
  • Prompt sequencing. One prompt per day from a curated sequence. Build a life narrative over weeks, not a firehose of generic questions.
  • Verbatim capture. When you write, we copy your exact words. Nothing summarized, nothing rewritten, nothing analyzed.
  • Markdown as platform. Prompts are .md files in your vault. Responses are .md files in your vault. Sync is whatever sync you already use.
  • Silence is fine. If you write nothing, nothing happens. No nudge, no guilt, no follow-up.

Quick Start

Prerequisites

  • Python 3.10+
  • An Obsidian vault (or any directory of markdown files)

Install

pip install grainjournal-mcp-server

Run as MCP Server

grainjournal --vault ~/my-vault/Journal

This starts the MCP server on stdio transport. Configure it as an MCP client tool in Claude Desktop, Cline, or any MCP-compatible agent.

Run as Cron Scripts

Two standalone scripts:

# Morning — writes today's prompt (run daily ~8AM)
grainjournal-prompt --vault ~/my-vault/Journal

# Evening — checks for written content (run daily ~10PM)
grainjournal-check --vault ~/my-vault/Journal

Or set the GRAINJOURNAL_VAULT environment variable:

export GRAINJOURNAL_VAULT=~/my-vault/Journal
grainjournal-prompt
grainjournal-check

MCP Tools

journal_prompt

Writes today's journal prompt note. One prompt per day from a curated sequence. Idempotent — safe to call multiple times.

Optional parameter: custom_prompt — override today's prompt with your own.

journal_check

Checks today's journal note for user-written content. If content exists beyond the header, captures it verbatim to the resume base. Silent if empty.

The Prompt Sequence

The initial sequence walks through a resume-gap meditation — one question per day:

  1. Your first job after college
  2. The bridge between disciplines
  3. Specific roles and what you did
  4. Education and study
  5. A turning-point project
  6. Your narrative thread — the story you tell yourself

After the sequence wraps, it cycles back with room for custom prompts.

Architecture

grainlocal/Journal/           ← Your Obsidian vault (or any .md directory)
├── 2026-07-12 Journal Prompt.md    ← Written by Cron A / journal_prompt
├── 2026-07-12 Journal.md           ← Written by you (in Obsidian)
├── 2026-07-13 Journal Prompt.md
├── 2026-07-13 Journal.md
└── .grainjournal-state.json        ← Tracking state (auto-managed)

grainjournal-mcp-server/
├── grainjournal/
│   ├── server.py          ← MCP server entrypoint
│   ├── vault.py           ← Obsidian vault read/write
│   ├── prompts.py         ← Prompt sequence + state tracking
│   └── scripts/
│       ├── write_prompt.py   ← Cron A
│       └── check_content.py  ← Cron B
└── pyproject.toml

Philosophy

The field is surprisingly empty where grainjournal sits:

  • MCP-native journaling doesn't exist yet. The entire ecosystem of MCP journal servers is 5 repos with zero stars.
  • Verbatim capture is a philosophical position. No tool in this space explicitly says "I will not touch your words."
  • Your existing tools, your way. Not a standalone app — works inside whatever you already have.

License

MIT — use it, fork it, build on it. That's the point.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选