boardagent-mcp
BoardAgent
一个驻留在你电脑上的任务管理器——为你和你的 AI 代理服务。 终端 UI、REST API、MCP 服务器。免费、本地、无云端。
安装 (Windows)
你需要预编译的 exe 文件。 有两种获取方式:
选项 A — 使用发布二进制文件(最简单):
从 GitHub 下载最新版本 → 解压 → 双击 INSTALL.bat。
就这样。它会复制程序、设置开机自启、安装看门狗,并将应用添加到你的 PATH。
选项 B — 自行构建: 需要 Python 3.10+。
pip install -e . # installs the 3 CLI commands
python scripts/build_exes.py # builds boardagent.exe, boardagent-server.exe, boardagent-mcp.exe into dist/然后运行 INSTALL.bat。
Related MCP server: pith
运行
Windows(运行 INSTALL.bat 之后): 双击 boardagent.exe(或在终端中输入 boardagent)。后台服务器会在登录时自动启动。
任意位置(源码):
boardagent-server # terminal 1 — the background service
boardagent # terminal 2 — the task board UI首次使用提示:
按
c创建任务,按a进入 AI 模式,按q退出。完全键盘优先:方向键移动,空格选择/打开,回车激活。
设置选项卡:主题、不透明度、API 密钥、按键绑定。
让 AI 代理使用看板
将你的 MCP 主机(Claude Desktop、Cursor、Hermes)指向 boardagent-mcp:
{
"mcpServers": {
"boardagent": { "command": "C:\\path\\to\\boardagent-mcp.exe" }
}
}在 设置 → API 密钥 中创建 API 密钥,用于其他任何用途。
工作原理
REST API — 权威数据源,
http://127.0.0.1:7373。MCP 服务器 — 基于同一服务层的轻量适配器。
Textual TUI — 你看到的应用,通过 localhost 与服务通信。
数据存储在
~/.boardagent/boardagent.db(SQLite)中。一切都在本地。
文档
面向人类:
docs/human/— 简介、MCP 设置、主题、打包。面向 AI 代理:
docs/agent/— 面向 token 优化的 REST + MCP 参考。工程决策:
DECISIONS.md。
开发
python -m pytest
python scripts/generate_agent_docs.py # needs the server running
python scripts/build_exes.py # Windows exes into dist/许可证
MIT — 参见 LICENSE。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server for the Google Tasks API that enables AI agents to read, create, update, delete, and manage Google Tasks.280MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for task management that enables AI agents to read, create, update tasks, and track work sessions, allowing agents and humans to collaborate on the same task board.27MIT
- FlicenseNot gradedqualityCmaintenanceExposes task management (add, list, complete tasks) and document search (RAG) as MCP tools for AI agents.
- FlicenseAqualityCmaintenanceMCP server enabling AI agents to create, update, search, assign, and complete tasks on TaskLogger.io via the TaskLogger REST API, with secure local credential management and token persistence.17
Related MCP Connectors
Project management MCP for AI agents with safe task reads and writes.
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/0xAngel-Sec/boardagent'
If you have feedback or need assistance with the MCP directory API, please join our Discord server