Microsoft Planner MCP Server
Enables MCP clients to list, view details of, and update Microsoft Planner tasks grouped by bucket.
README
Microsoft Planner MCP Server
An MCP server that exposes your Microsoft Planner tasks to MCP clients (Claude, GitHub Copilot, VS Code, and others). List your tasks grouped by bucket, drill into details/checklists/comments, and update task progress, all from your assistant.
Tools
| Tool | What it does |
|---|---|
get_planner_tasks |
Tasks assigned to you, grouped by bucket. Filter by bucket/priority; with_details=true adds description, checklist, and comments. |
update_planner_tasks |
Set progress (not_started / in_progress / completed) for one or more tasks. |
get_planner_buckets |
List your bucket names. |
Install
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env # then edit .env
Authentication
This server talks to Microsoft Graph with delegated permissions
(User.Read, Tasks.ReadWrite). Pick one of two methods via AUTH_METHOD in
.env.
Method 1: device code (default, recommended)
Uses your own Azure app registration. One-time portal setup:
-
Microsoft Entra ID, then App registrations, then New registration.
-
Authentication: add a Mobile and desktop applications platform and enable Allow public client flows.
-
API permissions: add delegated Microsoft Graph permissions
User.ReadandTasks.ReadWrite(and grant/consent for your account). -
Put the IDs in
.env:AUTH_METHOD=device CLIENT_ID=<application-client-id> TENANT_ID=<directory-tenant-id>
Then sign in once:
python login.py # prints a URL + code; open it and sign in
MSAL caches a refresh token and the server refreshes access tokens silently.
Method 2: browser fallback (no admin, locked-down tenants)
⚠️ Read this first. This method drives a headless Chromium that replays Graph Explorer's sign-in, borrowing the Graph Explorer first-party client to obtain tokens. Use it only if your tenant blocks app consent and you have no admin access and no way to register an app. It is unsupported, depends on undocumented Graph Explorer behavior (and may break without notice), and may be against your organization's policies, so check before using it. When you can, use Method 1 instead.
pip install playwright && playwright install chromium
# fetch the MSAL.js library used inside the browser:
mkdir -p vendor && curl -fsSL -o vendor/msal-browser.min.js \
https://cdn.jsdelivr.net/npm/@azure/msal-browser@2.38.4/lib/msal-browser.min.js
.env:
AUTH_METHOD=browser
TENANT_ID=<directory-tenant-id>
GRAPH_LOGIN_HINT=you@example.com # optional
Then:
python login.py # opens a browser window; sign in + MFA once
The signed-in session is saved in .browser_profile/, and the server fetches
tokens silently afterwards. Re-run login.py if the session ever lapses.
Connect an MCP client
Example (VS Code / Claude mcp.json-style config):
{
"mcpServers": {
"planner": {
"command": "/absolute/path/to/.venv/bin/python",
"args": ["/absolute/path/to/planner_mcp_server.py"]
}
}
}
Use with Claude
Once setup and sign-in are done, the simplest way is the Claude Code CLI. Register the server in one command (use absolute paths):
claude mcp add planner /absolute/path/to/.venv/bin/python /absolute/path/to/planner_mcp_server.py
That's it. Start claude and just ask in plain language, for example:
- "What are my Planner tasks?"
- "Show me the details of my in-progress tasks."
- "Mark Write the report as completed."
Claude calls the tools for you. Run claude mcp list to confirm it's connected,
or /mcp inside Claude Code to see its status.
For the Claude desktop app, add the same mcpServers block shown above to
your claude_desktop_config.json (Settings, then Developer, then Edit
Config) and restart the app.
Configuration reference
| Variable | Default | Notes |
|---|---|---|
AUTH_METHOD |
device |
device or browser |
CLIENT_ID |
(none) | Your app's client ID (device method) |
TENANT_ID |
organizations |
Your tenant GUID |
GRAPH_SCOPES |
User.Read Tasks.ReadWrite |
Space-separated delegated scopes |
GRAPH_LOGIN_HINT |
(none) | Pre-fill the sign-in account |
Security notes
Never commit .env, .token_cache.json, .msal_cache.json, or
.browser_profile/, since they hold credentials. They are in .gitignore.
Disclaimer
This is an independent, community project. It is not affiliated with, endorsed by, or sponsored by Microsoft. "Microsoft", "Microsoft Planner", and "Microsoft Graph" are trademarks of Microsoft Corporation, used here only to describe interoperability.
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。
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。