LocalMcpTools
An MCP server that provides a workspace.inspect tool for VS Code agents such as codebuddy and GitHub Copilot, enabling them to inspect the workspace through the Model Context Protocol.
README
LocalMcpTools
A local Model Context Protocol (MCP) toolset for VS Code agents (codebuddy, GitHub Copilot, and others).
Status
Phase 3 (managed-process-and-ports). The stdio MCP server now includes
read-only environment/workspace/file/output inspection, controlled shell and
workspace presets, approval and deny-rule enforcement, and lifecycle-bound
development servers. See openspec/changes/ for the
contracts and docs/implementation-plan.md for
the full roadmap.
Quick start
# 1. Create a venv and install (editable, so src changes are live).
python -m venv .venv
.\.venv\Scripts\python.exe -m pip install -e .
.\.venv\Scripts\python.exe -m pip install -r requirements-dev.txt
# 2. Run the tests.
.\.venv\Scripts\python.exe -m pytest
# 3. Launch the server (it blocks on stdio, waiting for an MCP client).
.\.venv\Scripts\python.exe -m localmcptools
Connecting agents
Both codebuddy and VS Code's GitHub Copilot Chat discover MCP servers
through a JSON file the IDE watches. The sample files in
samples/ show the spike configuration; copy the relevant one
into the location your agent expects.
| Agent | Where the file goes (Windows) | Sample |
|---|---|---|
| codebuddy | %USERPROFILE%\.codebuddy\mcp.json |
samples/mcp.codebuddy.json |
| GitHub Copilot Chat (VS Code) | %USERPROFILE%\.vscode\mcp.json (workspace .vscode/mcp.json also works) |
samples/mcp.copilot.json |
The configuration is identical for both agents — both speak the standard MCP
stdio transport. Once codebuddy / Copilot reads the file, the tool list
includes the environment.*, workspace.*, fs.*, output.*, shell.*,
and process.* surfaces.
Managed development servers
process.start_dev_server accepts only the built-in python-uvicorn,
node-vite, node-next-dev, and dotnet-run presets. It requires a workspace
with the managed_process profile and a matching one-time approval. Use
process.get_status, process.list_managed, process.stop_managed,
process.list_listening_ports, and process.find_by_port to observe and stop
owned processes. Arbitrary process.kill(pid) is intentionally not exposed.
Managed process output is available immediately through the returned Artifact handle. On Windows, child trees are attached to a kill-on-close Job Object, so they are terminated when the MCP server exits.
Where the data goes
Runtime state (audit log, settings, logs) lives under
%APPDATA%\LocalMcpTools\ by default. Override with the
LMCP_DATA_DIR environment variable for tests or portable installs.
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
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。