power-automate-mcp-server
Enables MCP clients to manage and troubleshoot Power Automate cloud flows, including listing environments, flows, and runs, with optional write capabilities for triggering, enabling, disabling, and deleting flows.
README
power-automate-mcp-server
An MCP server that exposes Power Automate cloud-flow management and run troubleshooting to an MCP client (Claude Code, Claude Desktop, etc.).
It talks to the Power Automate management plane
(api.flow.microsoft.com, the Microsoft.ProcessSimple provider) using an
Entra token for the service.flow.microsoft.com audience. With delegated
auth (interactive / CLI) it needs no admin consent — it operates as the
signed-in user and sees the flows that user owns or is shared on.
Tools
Read (always on)
| Tool | Purpose |
|---|---|
list_environments |
List Power Platform environments and their name (used everywhere else). |
list_flows |
List cloud flows the caller can see in an environment. |
get_flow |
Full flow JSON — trigger/action definition and connection references. |
list_flow_runs |
Recent runs of a flow, newest first, with status/error; pages via nextLink. |
get_flow_run |
Full detail for one run, including per-action status and error payloads. |
Write (PA_MCP_MODE=write)
| Tool | Purpose |
|---|---|
run_flow |
Trigger an on-demand run of a manually-triggered flow. |
enable_flow |
Start a flow so its triggers fire. |
disable_flow |
Stop a flow so its triggers no longer fire. |
Every write call is audit-logged to stderr with timestamp, tool, target, and caller identity.
Destructive (PA_MCP_MODE=write and PA_MCP_ALLOW_DELETE=true)
| Tool | Purpose |
|---|---|
delete_flow |
Permanently delete a flow. Two-step dry_run → confirm_token → apply. |
The destructive tier is off by default. When enabled, each call is a plan first:
dry_run=true (the default) returns the flow that would be removed plus a
single-use confirm_token; only a second call with dry_run=false and that
token performs the delete, guarded by an If-Match ETag.
Setup
cd power-automate-mcp-server
npm install
Register it with your MCP client. Example .claude.json entry (delegated auth,
read-only):
{
"mcpServers": {
"power-automate": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/power-automate-mcp-server/index.js"],
"env": {
"AZURE_TENANT_ID": "<your-entra-tenant-id>",
"PA_AUTH_MODE": "interactive",
"PA_MCP_MODE": "read"
}
}
}
}
To allow triggering and enabling/disabling flows, set "PA_MCP_MODE": "write".
To also allow deletion, add "PA_MCP_ALLOW_DELETE": "true".
Set PA_DEFAULT_ENVIRONMENT to a value from list_environments if you want to
omit environment on every call.
See .env.example for the full list of environment variables,
including all supported auth modes.
Auth notes
- Delegated (recommended here):
interactive,device-code, orcli. No admin consent, but the caller only sees flows they own or are shared on. - Service principal: non-interactive, but an SP must be granted Power Platform admin consent before it can enumerate flows — a tenant-admin action.
Requirements
- Node.js >= 20
- An Entra identity that can sign in to Power Automate in the target tenant.
License
MIT — see LICENSE.
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。