wsctl-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@wsctl-mcpsearch my workspace for tasks tagged preview"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
wsctl
一个用于 AI 开发工作区的通用管理原型:
用
.wsctl/保存 Git 友好的 Markdown/YAML 管理数据;用 Python 包和 CLI 提供统一服务;
用 MCP 让支持 MCP 的 AI 开发工具发现和调用;
用 SQLite/FTS5 做本地检索索引,索引可随时重建;
不内置构建、测试、部署或烧写逻辑。
当前版本是外部实验原型,用来验证通用管理面能否适配现有工作流。
快速开始
python3 -m pip install -e '.[mcp]'
wsctl init /tmp/my-project
wsctl --root /tmp/my-project workspace add /tmp/my-project --allow-write
wsctl --root /tmp/my-project projects create demo --name "Demo Project"
wsctl --root /tmp/my-project create task \
--title "写下第一条通用任务" \
--project demo \
--tag preview
wsctl --root /tmp/my-project list task --json
wsctl --root /tmp/my-project context --project demo --query 任务 --jsonRelated MCP server: sourcebook
适配现有工作区
原型提供了一个只读预览命令,把旧工作区映射到新的 .wsctl/:
wsctl legacy preview \
--source /path/to/old-workspace \
--out /path/to/preview-workspace \
--project my-project它不会修改旧工作区。项目、知识、决策和证据会写入预览目录的 .wsctl/,并抽取一个演示任务用于验证任务上下文。
MCP
wsctl-mcp --list-tools
wsctl-mcp --workspace /path/to/preview-workspace默认所有工作区只读;写入需要在注册时显式开启:
wsctl workspace add /path/to/project --allow-write接入当前 Buildroot 工作区
外部原型可以给现有 Buildroot 工作区增加一组只读/计划型 MCP 工具:
wsctl-mcp \
--legacy-workspace /path/to/buildroot-workspace-framework \
--list-tools这些工具通过当前仓库已有的 wsctl 源码读取真实事实,不修改当前仓库:
legacy_doctorlegacy_project_listlegacy_project_contextlegacy_source_statuslegacy_branch_statuslegacy_worktree_statuslegacy_historylegacy_knowledge_listlegacy_knowledge_verifylegacy_agent_statuslegacy_build_planlegacy_test_planlegacy_deploy_planlegacy_release_show
构建、测试、部署只生成计划,不执行。legacy_deploy_plan 会只读探测板卡运行槽。
Codex/Claude 等 MCP 客户端的配置值示例:
{
"command": "/home/cj/Tech/wsctl/.venv/bin/wsctl-mcp",
"args": [
"--legacy-workspace",
"/home/cj/buildroot-workspace-framework"
]
}也可以直接生成宿主配置片段:
wsctl setup mcp --host codex \
--legacy-workspace /path/to/buildroot-workspace-framework该命令只输出配置,不修改用户配置。Codex 片段包含:
default_tools_approval_mode = "approve"这只适用于当前只暴露只读/计划工具的 legacy-only MCP server。以后如果同时暴露写入或执行工具,应按工具单独设置审批模式。
当前边界
包含:
workspace 注册表;
project/task/knowledge/decision/evidence;
context 与全文检索;
CLI 和 MCP;
wsctl init与 legacy preview。
不包含:
构建、测试、部署、烧写;
外部 SaaS 同步;
远程 HTTP 服务;
多用户权限系统;
自动 Git commit。
This server cannot be deployed
Maintenance
Related MCP Connectors
Verified component catalog over remote MCP: agents pick component ids and get a stamped project repo that builds. Connect at https://www.botkelp.com/mcp. Auth: MCP OAuth 2.1, or a Bearer bk_live_ API key; initialize and tools/list are open.
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Hosted markdown project wikis your team's AI assistants read, search, and update over MCP.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Related MCP Servers
- AlicenseAqualityAmaintenanceRepository-native protocol and MCP server for coordinating work items, documentation, changelogs, and project memory between humans and AI agents, using Markdown files in a Git repository as the canonical data source.303MIT
- AlicenseNot gradedqualityBmaintenanceMCP server that gives AI coding agents a git-backed markdown wiki to read and update, enabling search, read, write, verify, ingest, promote, and lint operations on versioned knowledge documents with schema validation, staleness tracking, and contradiction detection.4MIT
- AlicenseCqualityBmaintenanceLocal-first MCP runtime for coding agents with bounded workspace access, content-preconditioned writes, AST search, LSP navigation and diagnostics, and Git status/diff. Designed to give coding agents useful repository access without treating unrestricted shell access as the default integration boundary.133MIT
- AlicenseAqualityCmaintenanceEnables AI coding agents to retrieve cited git-history explanations for files and tickets, compile a Team Engineering Contract from repository artifacts, and follow guided Understand/Build workflows over MCP stdio. It lets clients such as Grok, Claude Code, Codex, Kiro, and Cursor share the same tools for evidence-backed repository understanding.13 npmApache 2.0