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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.