winrm-mcp
Enables running PowerShell and CMD commands on Windows hosts over WinRM, with multi-host inventory management.
README
winrm-mcp
A deliberately small MCP server for running PowerShell and CMD commands on Windows hosts over WinRM. It takes
the WinRM execution ideas from ssh-winrm-mcp, adds a focused multi-host inventory, and leaves out SSH,
persistent sessions, jobs, command groups, and file transfer.
Tools
winrm_test— verify authentication and connectivity.winrm_execute_powershell— execute PowerShell.winrm_execute_cmd— execute CMD.winrm_inventory_status,winrm_inventory_init,winrm_inventory_validate— manage inventory files.winrm_host_list,winrm_host_get,winrm_host_save,winrm_host_update,winrm_host_delete— manage reusable hosts.
Each tool accepts an optional connection object. Values in it override the process environment:
{
"host": "192.168.1.50",
"username": "Administrator",
"password_env": "MY_WINRM_PASSWORD",
"auth": "ntlm",
"ssl": true,
"cert_validation": false
}
ssl chooses HTTPS (normally port 5986) versus HTTP (normally port 5985). cert_validation=false is needed for
self-signed HTTPS listeners, but should only be used for trusted hosts.
Supported connection fields are host, username, password, password_env, port, ssl, auth,
cert_validation, encryption, path, connect_timeout, read_timeout, and operation_timeout.
Multi-host inventory
Hosts can be stored in either inventory scope:
user(default):${XDG_CONFIG_HOME:-~/.config}/winrm-mcp/inventory.jsonon Linux/macOS, or the matching%APPDATA%location on Windows.project:.winrm-mcp/inventory.jsonunder the current working directory.
Choose the process default with WINRM_MCP_INVENTORY_SCOPE=user or WINRM_MCP_INVENTORY_SCOPE=project.
Every inventory and host tool also accepts an explicit scope, and execution tools accept inventory_scope.
Project scope uses WINRM_MCP_PROJECT_DIR, then the launcher's logical PWD, then the process working directory.
It refuses temporary deepagents_server_* paths instead of silently saving disposable inventory data. Set
WINRM_MCP_PROJECT_DIR when the launcher working directory is not the desired project root. A fully custom file is
supported through WINRM_MCP_INVENTORY_FILE; it is used when a call does not explicitly select a scope.
Create a project inventory and save two hosts:
winrm_inventory_init(scope="project")
winrm_host_save(
name="epv1",
scope="project",
settings={
"host": "10.0.110.50",
"username": "Administrator",
"password_env": "EPV1_WINRM_PASSWORD",
"auth": "ntlm",
"ssl": true,
"cert_validation": false
}
)
winrm_host_save(
name="epv2",
scope="project",
settings={
"host": "10.0.110.51",
"username": "Administrator",
"password_env": "EPV2_WINRM_PASSWORD",
"auth": "ntlm",
"ssl": true,
"cert_validation": false
}
)
Use a saved host by name:
winrm_test(saved_host="epv1", inventory_scope="project")
winrm_execute_powershell(saved_host="epv1", inventory_scope="project", command="hostname")
winrm_execute_cmd(saved_host="epv2", inventory_scope="project", command="whoami")
The optional connection object overrides fields from the saved host for that call. Inventory writes are atomic,
and the inventory file is restricted to the current user (0600) on Unix-like systems. Inline passwords are
supported but stored as plaintext in that protected JSON file; prefer password_env.
Omit connection when no overrides are needed. For compatibility with agents that serialize an optional value as
text, connection="None", connection="null", and an empty connection string are treated as JSON null.
DeepAgents
DeepAgents can run the server directly from GitHub, so a local checkout is not required. Add the following
entry to your DeepAgents .deepagents/.mcp.json file:
{
"winrm": {
"type": "stdio",
"command": "uv",
"args": [
"tool",
"run",
"--with",
"mcp>=1.28,<2",
"--from",
"git+https://github.com/bigbatmanorg/winrm-mcp.git",
"winrm-mcp"
],
"env": {
"WINRM_MCP_HOST": "192.168.1.50",
"WINRM_MCP_USERNAME": "Administrator",
"WINRM_MCP_PASSWORD": "YOUR_SECRET",
"WINRM_MCP_PORT": "5986",
"WINRM_MCP_AUTH": "ntlm",
"WINRM_MCP_SSL": "true",
"WINRM_MCP_CERT_VALIDATION": "false",
"WINRM_MCP_INVENTORY_SCOPE": "project",
"WINRM_MCP_PROJECT_DIR": "${PWD}",
"WINRM_MCP_CONNECT_TIMEOUT": "30",
"WINRM_MCP_READ_TIMEOUT": "60",
"WINRM_MCP_OPERATION_TIMEOUT": "30"
}
}
}
For reproducible installations, pin the repository to a release tag or commit:
"git+https://github.com/bigbatmanorg/winrm-mcp.git@YOUR_TAG_OR_COMMIT"
The example uses HTTPS with certificate verification disabled for a trusted development host with a self-signed
certificate. Keep WINRM_MCP_CERT_VALIDATION=true when the listener certificate is trusted. Do not commit a real
password to source control; use your normal DeepAgents secret-injection workflow for WINRM_MCP_PASSWORD.
DeepAgents expands ${PWD} before launching the MCP server. Replace it with an absolute path if DeepAgents itself
is launched from somewhere other than the project root.
Install and run
uv sync --extra dev
uv run pytest
uv run winrm-mcp
The default transport is stdio. A client configuration can supply stable connection defaults without putting credentials in every tool call:
{
"servers": {
"winrm": {
"type": "stdio",
"command": "uv",
"args": ["--directory", "/home/toor/projects/winrm-mcp", "run", "winrm-mcp"],
"env": {
"WINRM_MCP_HOST": "192.168.1.50",
"WINRM_MCP_USERNAME": "Administrator",
"WINRM_MCP_PASSWORD_ENV": "MY_WINRM_PASSWORD",
"MY_WINRM_PASSWORD": "replace-me",
"WINRM_MCP_AUTH": "ntlm",
"WINRM_MCP_SSL": "true",
"WINRM_MCP_CERT_VALIDATION": "false"
}
}
}
}
Available environment defaults correspond to the connection fields and use the WINRM_MCP_ prefix. Server
settings are WINRM_MCP_TRANSPORT, WINRM_MCP_SERVER_HOST, and WINRM_MCP_SERVER_PORT. Inventory settings are
WINRM_MCP_INVENTORY_SCOPE, WINRM_MCP_PROJECT_DIR, and WINRM_MCP_INVENTORY_FILE.
For Kerberos or CredSSP support, install the matching optional extra:
uv sync --extra kerberos
uv sync --extra credssp
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。
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。
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。
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。