sandraschisandraschi/onenote-mcp/CLAUDE.md

onenote-mcp

CLAUDE.md1 starsChanged 50 days agoMITView on GitHub

FastMCP 3.4 server for Microsoft OneNote via the Microsoft Graph API. - MCP tools are verb-led snake_case onenote_* with SOTA docstrings (## Return Format, ## Examples, Annotated[T, Field(...)] — no Args: blocks) - REST endpoints via @app.custom_route on the FastMCP app - Never pass the raw FastMCP object to uvicorn — always http_app/app.http_app() - CORS per mcp-central-docs/standards/CORS_STANDARD.md (tauri://localhost + Tailscale regex) You have access to OneNote notebooks via Microsoft Graph (26 tools). Before starting work on notes: onenote_list_notebooks() to find…

In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/general.mdCursor rule
- llms-full.txtllms.txt
- llms.txtllms.txt
- session-contextSkill

The file

We split this CLAUDE.md into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Never pass the raw FastMCP object to uvicorn — always http_app/app.http_app()
line 18
Very specific:
Before starting work on notes: onenote_list_notebooks() to find the notebook, then onenote_get_notebook_toc() for structure.
line 37

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

CLAUDE.md

onenote-mcp — Agent Guide

FastMCP 3.4 server for Microsoft OneNote via the Microsoft Graph API.

Quick Ref

Backend: uv run python -m onenote_mcp (stdio default; --http for streamable HTTP)
Backend port (HTTP/uvicorn): 10907 — ASGI target onenote_mcp.server:http_app
Webapp: cd web_sota && npm run dev (port 10906)
Tests: uv run pytest tests/ -q
Lint: just lint / just fix (ruff + biome)

Standards

MCP tools are verb-led snake_case onenote_* with SOTA docstrings (## Return Format, ## Examples, Annotated[T, Field(...)] — no Args: blocks)
REST endpoints via @app.custom_route on the FastMCP app
Never pass the raw FastMCP object to uvicorn — always http_app/app.http_app()
CORS per mcp-central-docs/standards/CORS_STANDARD.md (tauri://localhost + Tailscale regex)

Key Files

File	Purpose
`src/onenote_mcp/server.py`	FastMCP app, tools, REST routes, `http_app` export
`src/onenote_mcp/transport.py`	stdio/http/sse runner (uvicorn.Server on http_app)
`src/onenote_mcp/activity_log.py`	Ring-buffer log for the Logging page
`src/onenote_mcp/models.py`	Pydantic v2 models (Notebook, Page, Section, TOC)
`run_server.py`	PyInstaller entry (FastAPI shell + CORS + `/mcp` mount)
`web_sota/`	Vite React webapp (dashboard, notebooks, chat, logging)
`native/`	Tauri 2 wrapper (NSIS installer, embedded backend)
`fleet-start.config.ps1`	Fleet launcher config (ports + uvicorn target)

Session Context

You have access to OneNote notebooks via Microsoft Graph (26 tools). Before starting work on notes: onenote_list_notebooks() to find the notebook, then onenote_get_notebook_toc() for structure. At end of work: onenote_create_page() to persist notes; onenote_save_access_token() if auth is missing.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free