Jarvis Markdown MCP
Local-first memory server for AI coding agents that stores work sessions, tasks, and durable memories in Markdown files, exposed through MCP tools for session management and memory retrieval.
README
Jarvis Markdown MCP
Jarvis is a small local-first memory server for AI coding agents. Codex or Claude supplies the reasoning, while durable memory remains ordinary Markdown on your computer.
This repository is the MVP: a dependable work-session loop with no database, cloud account, or model lock-in.
Read VISION.md for the product direction: a proactive, explainable productivity assistant that can eventually be accessed securely from anywhere.
What It Does
- Keeps the active work session in
~/.jarvis/NOW.md. - Stores pending and completed tasks in
~/.jarvis/REMINDERS.md. - Appends simple interaction summaries to
~/.jarvis/daily/YYYY-MM-DD.md. - Saves durable memories under
~/.jarvis/memories/. - Searches the Markdown vault without a database.
- Exposes everything to MCP-compatible clients through a local STDIO server.
- Optionally sends bounded morning, due-task, stale-work, and evening desktop check-ins on Linux.
It does not yet reorganize memory, run AI reasoning in the background, monitor files, sync devices, or provide voice and UI features.
Requirements
- Node.js 20 or newer
- An MCP client such as Codex CLI, Codex desktop, the Codex IDE extension, or Claude Code
- For proactive Linux notifications: systemd and
notify-send
Install
git clone https://github.com/ash25082003/jarvis-markdown-mcp.git
cd jarvis-markdown-mcp
npm ci
npm run build
The vault defaults to ~/.jarvis. To use another folder, set JARVIS_HOME before launching the server.
Codex
Connect Jarvis from the project directory:
codex mcp add jarvis --env JARVIS_HOME="$HOME/.jarvis" -- node "$(pwd)/dist/src/index.js"
On Windows PowerShell, use absolute paths for both values:
codex mcp add jarvis --env JARVIS_HOME="C:\Users\YOUR_NAME\.jarvis" -- node "C:\path\to\jarvis-markdown-mcp\dist\src\index.js"
Verify the connection:
codex mcp list
Claude Code
Connect Jarvis from the project directory:
claude mcp add jarvis -e JARVIS_HOME="$HOME/.jarvis" -- node "$(pwd)/dist/src/index.js"
Verify the connection:
claude mcp list
On Windows, use absolute paths for JARVIS_HOME and dist/src/index.js.
First Conversation
Start your AI client and say:
Use Jarvis. Show my current context, then help me choose one concrete work objective and start a work session. Ask me for a definition of done if it is unclear.
During work:
Log that I finished the first six evaluation tasks. Evidence:
results/.
At the end:
Finish this work session honestly as completed, partial, or blocked, and summarize what remains.
To save something durable:
Save this as a Jarvis memory: Markdown is the canonical source of truth, and model providers must remain replaceable.
To create a reminder:
Remind me to review the Jarvis roadmap at 11:00 tomorrow.
Proactive Check-ins
On Linux, install the optional user-level timers:
npm run checkins:install
The default schedule is:
- Morning planning at 09:00.
- Due-task and stale-work checks once per hour.
- Evening review at 18:00.
- Quiet hours from 20:00 through 08:00.
- At most three notifications per day.
Settings live in ~/.config/jarvis/check-ins.env. After changing them, the next check uses the new values.
Preview a check-in without sending or recording it:
npm run check-in -- --kind morning --dry-run
Disable the timers while keeping your settings:
npm run checkins:uninstall
Proactive Check-ins v1 uses deterministic local rules, not unattended model calls. This makes each notification explainable and avoids background token usage.
MCP Tools
initialize_vaultget_current_contextstart_worklog_progressfinish_workadd_reminderlist_reminderscomplete_remindersave_memorysearch_memory
Development
npm test
The next feature should be added only after using this basic work-session loop in real work.
How It Works
You -> Codex or Claude -> Jarvis MCP tools -> Markdown files on your computer
^
systemd timers -> relevance rules -> desktop notifications
The model decides when to call a Jarvis tool. Jarvis only validates the request and reads or writes the Markdown vault. Your memory remains usable without Jarvis because the files are plain text.
Roadmap
- Learn from real use of the work-session and proactive check-in loops.
- Add reminder feedback, snooze controls, and configurable schedules.
- Add optional memory organization and consolidation.
- Add authenticated remote access and multi-device use without giving up local ownership.
- Adopt MCP Apps and Tasks after the
2026-07-28specification and target clients support them.
Privacy
Jarvis does not send your vault anywhere. Your MCP client or model provider may process text returned by tools, so use the privacy settings appropriate for that client.
License
MIT
推荐服务器
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。
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。
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。
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。
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。
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。
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。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。