board-mcp
MCP bulletin board server for coordinating file ownership across multiple AI coding agents (Claude Code, Codex, OpenCode, Trae). It enables agents to claim files, check conflicts, and post decisions before starting work to prevent collisions.
README
board-mcp
一个MCP小工具,MCP公告板,可以让ai工具协调工作。
多终端 AI 协作公告板 MCP 服务器。让并行工作的 Claude Code / Codex / OpenCode / Trae 在撞车前协调好"谁在改哪个文件"。
安装(只注册 MCP 工具)
要求:Python 3.10+、uv,以及至少一个目标终端。
git clone https://github.com/maoxiangzhe/board-mcp.git
cd board-mcp
uv run python install.py # 自动建 .venv + 装依赖 + 检测已装 CLI 并注册
uv run python install.py --target all # 注册到全部 4 个终端
uv run python install.py --target codex # 只注册 Codex(可逗号分隔多个)
uv run python install.py --dry-run # 演练:只看不改
uv run python install.py --check # 检查注册状态
uv run 会自动创建 .venv、按 uv.lock 装依赖(唯一依赖 mcp SDK),
并用 .venv 里的 Python 注册服务器——不污染系统 Python。
| 终端 | MCP 注册位置 |
|---|---|
| Claude Code | claude mcp add board(幂等,路径不一致自动重注册) |
| Codex | ~/.codex/config.toml → [mcp_servers.board-mcp](保留 tools.* 权限子段) |
| OpenCode | ~/.config/opencode/opencode.json → mcp.board |
| Trae | %APPDATA%\Trae CN|Trae\User\mcp.json → mcpServers.board |
装完重启对应终端会话,即可使用 7 个工具:
get_board / claim_files / report_done / check_conflict / release_claim
/ post_decision / init_bulletin。
- 幂等可重复执行,改动前自动备份到
%TEMP%\board_install_backup\ --project只影响 Claude 的注册范围,其余终端按用户级安装
协作规则
每个项目第一次使用时调用 init_bulletin 初始化公告板,之后按流程走:
开工 get_board → 认领 claim_files → 干活 → 收尾 report_done。
项目根目录的 AGENTS.md / CLAUDE.md 会自动注入协作纪律(见 template.md)。
数据存放
- 公告板实体:
~/.board-mcp/boards/<项目ID>.md(所有终端共享同一份) - 日志:
~/.board-mcp/logs/server.log;心跳:~/.board-mcp/run/ - 可调环境变量:
BOARD_MCP_ROOT(数据目录)、BOARD_MCP_PROJECT(强制项目身份)、BOARD_CLAIM_TTL_MINUTES(认领过期,默认 120 分钟)
结构
board-mcp/
├── server.py # MCP 服务器(公告板引擎)
├── install.py # 多终端 MCP 注册安装器
├── test_demo.py # 自测(12 项断言,CI 自动跑)
├── template.md # 注入项目的协作规则模板
├── AGENTS.md # AI 协作纪律(本目录)
├── CLAUDE.md # Claude Code 规则副本
├── LICENSE # MIT
├── pyproject.toml # 项目元数据 + 依赖声明(mcp SDK)
├── uv.lock # 依赖锁(uv sync 精确还原环境)
└── .gitignore # 忽略 .venv / __pycache__ / 备份
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.