Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sandraschi/onenote-mcp --skill onenotegit clone --depth 1 https://github.com/sandraschi/onenote-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sandraschi/onenote-mcp/onenote)<a href="https://agentmods.dev/skills/sandraschi/onenote-mcp/onenote"><img src="https://agentmods.dev/badge/skills/sandraschi/onenote-mcp/onenote/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sandraschi/onenote-mcp/onenote"><img src="https://agentmods.dev/badge/skills/sandraschi/onenote-mcp/onenote.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01024 |
| Opus 5.5 | $0.00000 | $0.00410 |
| Sonnet 5.5 | $0.00000 | $0.00205 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
onenote scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OneNote MCP — Skill
What this server does
OneNote MCP connects an AI assistant to Microsoft OneNote through the Microsoft
Graph API: browsing notebooks/sections/pages, reading full page content (HTML),
creating and appending pages, and title + full-text search across the user's notes. 26 tools + 1 prompt
(onenote_triage), dual transport (stdio + HTTP streamable on 10907).
Tool categories
| Category | Tools |
|---|---|
| Auth | authenticate, onenote_save_access_token |
| Discovery | onenote_list_notebooks, onenote_get_notebook, onenote_list_sections, onenote_list_pages, onenote_get_notebook_toc, onenote_recent (what changed) |
| Structure (create) | onenote_create_notebook, onenote_create_section, onenote_create_section_group, onenote_list_section_groups. Graph cannot rename or delete notebooks/sections. |
| Edit | onenote_update_page (element-level replace/insert/prepend/append, retitle; Graph cannot delete elements - blank with replace), onenote_delete_page (destructive: confirm with the user first) |
| Content | onenote_get_page (output_format="markdown" for readable text; include_ids=True for element IDs), onenote_create_page (pass section_id to choose the section; content_format="markdown" for Markdown, - [ ] becomes a OneNote to-do), onenote_append_page (plain text or Markdown), onenote_search_pages (mode title or fulltext), onenote_get_links (web + app link to share a page or notebook) |
| Backup | onenote_export, onenote_export_status (Markdown files under data/exports) |
| Index | onenote_index_start, onenote_index_status (local FTS5 over page bodies; build once, then full-text works) |
| Presentation | show_notebooks_card (in-chat Prefab card) |
| Guidance | onenote_triage prompt (discover/retrieve/map/capture steering) |
| System | onenote_help, shutdown_server |
Best practices
- Sign in first. If any tool returns
No access token available, the user signs in (webapp Notebooks page, browser auth-code flow) or the agent callsauthenticate()(device-code flow) before anything else. - Navigate top-down. Start with
onenote_list_notebooks(), thenonenote_get_notebook_toc(notebook_id=...)to see sections + pages in one call, thenonenote_get_page(page_id=...)for content. IDs are opaque Graph IDs - always pass them through, never truncate. - Creating pages takes HTML content:
onenote_create_page(notebook_id=..., title="Meeting Notes", content="<h1>...</h1><p>...</p>"). - Search (
onenote_search_pages) is a TITLE match across all notebooks (Microsoft removed full-text OneNote search; section-heavy accounts are walked TOC-by-TOC) - use it when the user describes a note instead of naming a notebook. For body text, build the index once (onenote_index_start) and searchmode="fulltext". - Page content is HTML. Read it as-is; render/sanitize before display (the webapp uses DOMPurify).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 17d ago Changed · +2 lines 1191dd1d1359
- 28d ago Changed · +14 lines 5c781dcd03c9
- 29d ago Changed 21baef28cedd
- 1mo ago First seen · 47 lines · 0 tokens per session scan A 2aa7b0c00944
onenote is a skill published in the GitHub repository sandraschi/onenote-mcp (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,024 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
servicenow-import-attachment-batch
ServiceNow data-ingest, file, and batched-REST surface — push rows through Import Sets (single and bulk), upload/get/delete record attachments, and bundle many REST calls into one batch request via the servicenow-api MCP server. Use when the agent must load external data through a transform-mapped import set, attach…
servicenow-knowledge
Read access to the ServiceNow Knowledge Management (KSM) API via the servicenow-api MCP server — search/list knowledge articles, fetch a single article, pull article attachments, and get featured or most-viewed articles. Use when the agent must find or retrieve published knowledge-base content to answer a question…
ocr-expert
You are connected to OCR-MCP, a FastMCP 3.4+ server with 14 OCR backends. This skill teaches you how to use it effectively.
source-ingest
Normalize a raw source — PDF, DOCX, XLSX, URL, article text, or transcript — into a structured source record compatible with SOURCEPOLICY.md evidence modes and per-claim provenance tags. Use before analysis when the user provides a document and you need to extract metadata, classify source type, pull key excerpts, and…
outline
Conventions and efficient workflows for Outline knowledge bases via mcp-outline tools. Use when creating, editing, restructuring, or diagramming Outline documents — covers Outline markdown quirks (mermaidjs code fences), document and collection structure, string-match editing, staged rewrites, batch operations, and…
swag
This skill should be used when the user says "add proxy config", "create reverse proxy", "SWAG config", "nginx proxy", "expose service", "proxy configuration", "subdomain config", "subfolder config", "configure SWAG", "list proxy configs", "view proxy config", "edit proxy config", "remove proxy config", "check proxy…