How it works

• Every tool drives OneNote through a small, fixed PowerShell program that uses the OneNote.Application COM object. User data is passed only via JSON temp files (no string interpolation), and the COM object is released after each call. The only external requirement beyond OneNote is Windows PowerShell (always present on Windows).
• Reads that can be large (page text, raw XML, hierarchies, search results, binary content) are paginated: text/XML use offset + max_chars; lists use offset + limit. Each response returns next_offset / has_more, and full documents are cached so paging does not re-hit OneNote.

Requirements

• Windows 10 / 11 with the Microsoft OneNote desktop app (the traditional Office app, not the Store/UWP "OneNote for Windows 10").
• LM Studio with the lms CLI available (lms bootstrap once if it isn't on PATH).
• OneMore add-in for OneNote (optional) — only required if you write content with content_format: "markdown". Set ONENOTE_MANAGER_MARKDIG_DLL if OneMore is installed in a non-standard location.

Installation

Install the plugin from this link:

https://lmstudio.ai/morxeton/onenote-manager

If you'd like to work on the development of this plugin for yourself or to contribute, execute these commands in the folder where you saved the source files (onenote-manager):

npm install     # installs dependencies and creates package-lock.json (required by LM Studio)
lms dev         # loads the plugin into LM Studio and hot-reloads on changes

Run non-elevated. Launch LM Studio (and lms dev, if you use it) without administrator rights, at the same privilege level as OneNote. A privilege mismatch makes the OneNote COM object fail to start (0x80080005).

Then, in a chat, enable the onenote-manager plugin and ask it to work with OneNote.

Tools

All tools list alphabetically in LM Studio. Reads marked (paged) accept offset/max_chars (text/XML) or offset/limit (lists).

Write, structural, and app-control tools can create, modify, delete, and export your OneNote content. Enable the plugin only in chats where you want the model to have that access.

Highlighted commands

Tables

Every table tool identifies a table the same way: by its objectID (from get_page_objects or the page XML — either the table's own objectID or the objectID of the outline element that contains it) or by its 1-based position on the page ("1" = first table).

• get_page_table_xml / replace_page_table_xml — read a table's raw <one:Table>…</one:Table>, or replace it wholesale. To hand-edit, fetch, modify the returned XML, and pass it back.
• insert_row_into_table — add a row with values (text per column). Existing formatting is preserved by cloning an existing row's cell styles (choose which with template_row_index, default = last row). index sets the 1-based position (default: append).
• replace_table_cell_text — replace one cell's text by 1-based row/column; the cell's formatting is kept.
• delete_row_from_table — remove a row by 1-based row_index, or by matching first_column_text (case-insensitive; wins if both are given).
• clone_table_schema — clone column headers (horizontal mode) or row labels (vertical mode) from a source table into a target table, reordering and adding/deleting as needed while preserving existing data cells. Works across pages. Useful for keeping character sheets aligned to a master schema.

Row and column numbers are 1-based (row 1 is the first/top row, which is often a header).

Outlines

OneNote lays out content in floating Outline boxes positioned by x/y. Identify an outline by its objectID or 1-based index ("1" = first outline).

• get_page_outline_xml — read one outline's raw <one:Outline> XML.
• insert_page_outline_xml — insert a <one:Outline> (or loose one:OE content, which is auto-wrapped) into a page, positioned automatically after all existing outlines at the far bottom (default) or far right. Fresh object IDs are assigned.
• duplicate_page_outline — clone an existing outline and place the copy at the far bottom or right.
• save_page_outline_xml_to_file — extract one outline's raw <one:Outline> XML and write it to a file. The file is named after the page title with _outline_<index>.xml unless you pass file_name. Optional output_dir, overwrite. Defaults its directory to the plugin's Default export directory setting.
• insert_page_outline_xml_from_file — read an Outline XML from a local .xml file and insert it into a page, positioned automatically at the far bottom (default) or far right. Fresh object IDs are assigned.

Adding to outlines:

• add_outline_to_page — create a new floating outline on the page from content (plain / html / markdown). (This is the command formerly named append_to_page.)
• add_content_to_page_outline — add content (plain / html / markdown) to an outline identified by objectID or 1-based index. If outline_id is omitted the first outline is used, and if the page has no outline, one is created automatically.
• add_todo_items_to_page_outline — add one or more To Do (checkbox) items to an outline in a single call. It creates the page's To Do TagDef if the page has none (and reuses it otherwise). If outline_id is omitted the first outline is used, and if the page has no outline, one is created. Each item's text is interpreted per content_format (plain, html, or markdown), so items can carry hyperlinks or inline formatting — e.g. a onenote: link from generate_onenote_hyperlinks_xml, or markdown [text](url) (block structure collapses to line breaks). Each entry in items has its own text, optional completed, and optional indent_level (0 = top level, 1 = indented under the previous item, …; an item can go at most one level deeper than the one before it, and deeper values are clamped). By default the batch is appended (continuing the list); pass position (1-based) to insert the batch between existing items at the first item's indent level.

Outline spacing — add_buffer_between_page_outlines

Cleans up pages where outlines have drifted, overlapped, or are too close together by ensuring they are separated by a minimum buffer amount. Buffer is specified in pixels.

• Identifies all outlines on the page and adjusts their positions based on adjustment_mode.
• buffer_pixels: Minimum spacing between outlines (e.g. 10–50 is typical).
• adjustment_mode (default: "only_overlapped"):
  • "only_overlapped" — least intrusive; only moves outlines that actually overlap with another. When an outline overlaps on both axes, it moves along whichever axis has the smaller overlap (the "easier" direction to separate them). If overlaps are equal, horizontal movement is prioritized.
  • "all_directions" — ensures all outlines that are close to each other (within buffer distance) are separated by at least the buffer gap, preserving multi-column layouts and relative positions. Only adjusts outlines that would otherwise touch or overlap; does not rearrange the entire page into a single column/row.
  • "top_to_bottom" — adds vertical spacing between outlines that share horizontal space (same column), pushing lower ones down. Preserves separate columns.
  • "left_to_right" — adds horizontal spacing between outlines that share vertical space (same row), pushing rightward ones over. Preserves separate rows.

Example: ensure all outlines on a page have at least 20 pixels of spacing between them:

add_buffer_between_page_outlines(
  page_identifier="My Section/My Page",
  buffer_pixels=20,
  adjustment_mode="only_overlapped"
)

Uniform outline width — set_all_outlines_width_on_page

Sets all outlines on a page to the same target width while preserving their relative vertical spacing. Outlines that vertically overlap with neighbors are shifted horizontally so they don't collide after resizing. If an outline contains tables, each table's column widths are also adjusted so the table fills the new outline width.

• target_width_pixels: Desired width for all outlines in pixels (e.g. 400–800 is typical).
• target_table_index (default: last column): Which column within each embedded table to adjust when resizing tables inside outlines. Specify a 1-based column index; if the value exceeds a table's actual column count, that table's last column is used instead. Set to 0 to disable automatic table width adjustments entirely.

Example: set all outlines on a page to 600 pixels wide and adjust each embedded table's last column:

set_all_outlines_width_on_page(
  page_identifier="My Section/My Page",
  target_width_pixels=600,
  target_table_index=9999 // uses the last column of each table
)

Reusable snippets — generate_onenote_hyperlinks_xml / generate_todo_tag_xml

These generate XML only (they don't modify a page); insert the result with another command.

• generate_onenote_hyperlinks_xml resolves one or more target pages' links and returns an array of results, each with inline_html (for add_outline_to_page / add_content_to_page_outline with content_format: "html") plus one_t_xml / one_oe_xml for raw insertion (e.g. inside insert_page_outline_xml). Supports bold/italic/underline/strikethrough per item and web (https link vs onenote: link).
• generate_todo_tag_xml returns a To Do checkbox tag: tag_def_xml (a page-level one:TagDef — add once via update_page_xml if the page has none), tag_xml (the one:Tag that goes first inside a one:OE), and, if you pass text, a ready one_oe_xml.

Hyperlinks on existing text — set_hyperlink_on_object

Turns existing plain text into clickable hyperlinks without replacing the text itself.

• Finds all occurrences of search_text on a page (or within an optional container object) and wraps each with <a href="hyperlink_url">...</a>.
• Preserves existing inline formatting (bold/italic/etc.) around matched text.
• Works inside tables, outlines, cells — anywhere OneNote stores text in <one:T> elements.
• Optional container_object_id scopes the search to a specific object (table, cell, outline) from get_page_objects.

Example: add glossary links to terms on character sheets:

set_hyperlink_on_object(
  page_identifier="Characters/My Character Sheet",
  search_text="Dragon",
  hyperlink_url="onenote:...glossary-dragon-page...",
  container_object_id="{table-cell-object-id}" // optional: limit to one cell/table
)

add_todo_items_to_page_outline — hyperlinks in To Do items

Each item's text is interpreted per content_format, so you can embed hyperlinks directly. For example, use the inline_html from generate_onenote_hyperlinks_xml:

add_todo_items_to_page_outline(
  page_identifier="My Section/My Page",
  content_format: "html",
  items: [
    { text: "<a href=\"onenote:...\">Review glossary entry</a>" }
  ]
)

duplicate_page

Copies a page (for example a template) into a new page. By default the copy lands in the source page's own section; you may pass target_section_identifier and/or new_title. OneNote assigns fresh object IDs to the copy.

save_page_xml_to_file / save_all_notebook_pages_xml_to_file

• save_page_xml_to_file writes one page's raw XML; the file is named after the page title (.xml) unless you pass file_name.
• save_all_notebook_pages_xml_to_file reads an entire notebook by name and writes one XML file (named <notebook>.xml) that mirrors the section-group / section / page structure, with each page's raw OneNote XML embedded inline. Optional output_dir, page_info, overwrite.
• Both default their directory to the plugin's Default export directory setting, or the plugin working directory if unset. Files are written on the machine running OneNote.

save_all_notebook_pages_xml_to_file reads every page via GetPageContent, which loads them into OneNote. For very large notebooks this can make OneNote sluggish — restart OneNote afterward if needed.

Configuration

Troubleshooting

• 0x80080005 / focus flips to OneNote then times out — a privilege-level mismatch. Run LM Studio non-elevated, at the same level as OneNote. Make sure OneNote isn't running elevated either.
• First call is slow / times out — OneNote is starting up. Raise OneNote operation timeout and retry.
• Reads look cut off — lower Default page size (characters); the model pages the rest via next_offset.
• Markdown content fails — install the OneMore add-in, or set ONENOTE_MANAGER_MARKDIG_DLL to its Markdig.Signed.dll. Plain and HTML content need no add-in.
• OneNote gets sluggish after many reads — reads are cached and page GUIDs skip a full-store scan, but reading many distinct pages still loads them into OneNote; restart OneNote periodically for long sessions.
• Logs — messages prefixed [onenote-manager] appear in LM Studio's developer/plugin logs.

Project layout

onenote-manager/
├── manifest.json
├── package.json
├── tsconfig.json
└── src/
    ├── index.ts            # registers config + tools provider
    ├── configSchematics.ts # settings UI
    ├── toolsProvider.ts    # all tools (returned alphabetically)
    ├── onenote.ts          # high-level OneNote operations
    ├── bridge.ts           # PowerShell OneNote COM bridge
    ├── markdown.ts         # Markdown → HTML via OneMore's Markdig
    ├── htmlToOneNote.ts    # plain/HTML/Markdown → OneNote XML
    ├── pageXml.ts          # page-update XML builders
    ├── parseXml.ts         # hierarchy/page parsing, tables, page-clone
    ├── htmlText.ts         # OneNote one:T → plain text
    ├── imageSize.ts        # native image dimensions
    ├── pagination.ts       # text/item slicing + LRU cache
    └── notebookDump.ts     # structured notebook XML export

License

MIT (this plugin). See local-onenote-mcp for the original project's license and terms.

How it works

• Every tool drives OneNote through a small, fixed PowerShell program that uses the OneNote.Application COM object. User data is passed only via JSON temp files (no string interpolation), and the COM object is released after each call. The only external requirement beyond OneNote is Windows PowerShell (always present on Windows).
• Reads that can be large (page text, raw XML, hierarchies, search results, binary content) are paginated: text/XML use offset + max_chars; lists use offset + limit. Each response returns next_offset / has_more, and full documents are cached so paging does not re-hit OneNote.

Requirements

• Windows 10 / 11 with the Microsoft OneNote desktop app (the traditional Office app, not the Store/UWP "OneNote for Windows 10").
• LM Studio with the lms CLI available (lms bootstrap once if it isn't on PATH).
• OneMore add-in for OneNote (optional) — only required if you write content with content_format: "markdown". Set ONENOTE_MANAGER_MARKDIG_DLL if OneMore is installed in a non-standard location.

Installation

Install the plugin from this link:

https://lmstudio.ai/morxeton/onenote-manager

If you'd like to work on the development of this plugin for yourself or to contribute, execute these commands in the folder where you saved the source files (onenote-manager):

npm install     # installs dependencies and creates package-lock.json (required by LM Studio)
lms dev         # loads the plugin into LM Studio and hot-reloads on changes

Run non-elevated. Launch LM Studio (and lms dev, if you use it) without administrator rights, at the same privilege level as OneNote. A privilege mismatch makes the OneNote COM object fail to start (0x80080005).

Then, in a chat, enable the onenote-manager plugin and ask it to work with OneNote.

Tools

All tools list alphabetically in LM Studio. Reads marked (paged) accept offset/max_chars (text/XML) or offset/limit (lists).

Write, structural, and app-control tools can create, modify, delete, and export your OneNote content. Enable the plugin only in chats where you want the model to have that access.

Highlighted commands

Tables

Every table tool identifies a table the same way: by its objectID (from get_page_objects or the page XML — either the table's own objectID or the objectID of the outline element that contains it) or by its 1-based position on the page ("1" = first table).

• get_page_table_xml / replace_page_table_xml — read a table's raw <one:Table>…</one:Table>, or replace it wholesale. To hand-edit, fetch, modify the returned XML, and pass it back.
• insert_row_into_table — add a row with values (text per column). Existing formatting is preserved by cloning an existing row's cell styles (choose which with template_row_index, default = last row). index sets the 1-based position (default: append).
• replace_table_cell_text — replace one cell's text by 1-based row/column; the cell's formatting is kept.
• delete_row_from_table — remove a row by 1-based row_index, or by matching first_column_text (case-insensitive; wins if both are given).
• clone_table_schema — clone column headers (horizontal mode) or row labels (vertical mode) from a source table into a target table, reordering and adding/deleting as needed while preserving existing data cells. Works across pages. Useful for keeping character sheets aligned to a master schema.

Row and column numbers are 1-based (row 1 is the first/top row, which is often a header).

Outlines

OneNote lays out content in floating Outline boxes positioned by x/y. Identify an outline by its objectID or 1-based index ("1" = first outline).

• get_page_outline_xml — read one outline's raw <one:Outline> XML.
• insert_page_outline_xml — insert a <one:Outline> (or loose one:OE content, which is auto-wrapped) into a page, positioned automatically after all existing outlines at the far bottom (default) or far right. Fresh object IDs are assigned.
• duplicate_page_outline — clone an existing outline and place the copy at the far bottom or right.
• save_page_outline_xml_to_file — extract one outline's raw <one:Outline> XML and write it to a file. The file is named after the page title with _outline_<index>.xml unless you pass file_name. Optional output_dir, overwrite. Defaults its directory to the plugin's Default export directory setting.
• insert_page_outline_xml_from_file — read an Outline XML from a local .xml file and insert it into a page, positioned automatically at the far bottom (default) or far right. Fresh object IDs are assigned.

Adding to outlines:

• add_outline_to_page — create a new floating outline on the page from content (plain / html / markdown). (This is the command formerly named append_to_page.)
• add_content_to_page_outline — add content (plain / html / markdown) to an outline identified by objectID or 1-based index. If outline_id is omitted the first outline is used, and if the page has no outline, one is created automatically.
• add_todo_items_to_page_outline — add one or more To Do (checkbox) items to an outline in a single call. It creates the page's To Do TagDef if the page has none (and reuses it otherwise). If outline_id is omitted the first outline is used, and if the page has no outline, one is created. Each item's text is interpreted per content_format (plain, html, or markdown), so items can carry hyperlinks or inline formatting — e.g. a onenote: link from generate_onenote_hyperlinks_xml, or markdown [text](url) (block structure collapses to line breaks). Each entry in items has its own text, optional completed, and optional indent_level (0 = top level, 1 = indented under the previous item, …; an item can go at most one level deeper than the one before it, and deeper values are clamped). By default the batch is appended (continuing the list); pass position (1-based) to insert the batch between existing items at the first item's indent level.

Outline spacing — add_buffer_between_page_outlines

Cleans up pages where outlines have drifted, overlapped, or are too close together by ensuring they are separated by a minimum buffer amount. Buffer is specified in pixels.

• Identifies all outlines on the page and adjusts their positions based on adjustment_mode.
• buffer_pixels: Minimum spacing between outlines (e.g. 10–50 is typical).
• adjustment_mode (default: "only_overlapped"):
  • "only_overlapped" — least intrusive; only moves outlines that actually overlap with another. When an outline overlaps on both axes, it moves along whichever axis has the smaller overlap (the "easier" direction to separate them). If overlaps are equal, horizontal movement is prioritized.
  • "all_directions" — ensures all outlines that are close to each other (within buffer distance) are separated by at least the buffer gap, preserving multi-column layouts and relative positions. Only adjusts outlines that would otherwise touch or overlap; does not rearrange the entire page into a single column/row.
  • "top_to_bottom" — adds vertical spacing between outlines that share horizontal space (same column), pushing lower ones down. Preserves separate columns.
  • "left_to_right" — adds horizontal spacing between outlines that share vertical space (same row), pushing rightward ones over. Preserves separate rows.

Example: ensure all outlines on a page have at least 20 pixels of spacing between them:

add_buffer_between_page_outlines(
  page_identifier="My Section/My Page",
  buffer_pixels=20,
  adjustment_mode="only_overlapped"
)

Uniform outline width — set_all_outlines_width_on_page

Sets all outlines on a page to the same target width while preserving their relative vertical spacing. Outlines that vertically overlap with neighbors are shifted horizontally so they don't collide after resizing. If an outline contains tables, each table's column widths are also adjusted so the table fills the new outline width.

• target_width_pixels: Desired width for all outlines in pixels (e.g. 400–800 is typical).
• target_table_index (default: last column): Which column within each embedded table to adjust when resizing tables inside outlines. Specify a 1-based column index; if the value exceeds a table's actual column count, that table's last column is used instead. Set to 0 to disable automatic table width adjustments entirely.

Example: set all outlines on a page to 600 pixels wide and adjust each embedded table's last column:

set_all_outlines_width_on_page(
  page_identifier="My Section/My Page",
  target_width_pixels=600,
  target_table_index=9999 // uses the last column of each table
)

Reusable snippets — generate_onenote_hyperlinks_xml / generate_todo_tag_xml

These generate XML only (they don't modify a page); insert the result with another command.

• generate_onenote_hyperlinks_xml resolves one or more target pages' links and returns an array of results, each with inline_html (for add_outline_to_page / add_content_to_page_outline with content_format: "html") plus one_t_xml / one_oe_xml for raw insertion (e.g. inside insert_page_outline_xml). Supports bold/italic/underline/strikethrough per item and web (https link vs onenote: link).
• generate_todo_tag_xml returns a To Do checkbox tag: tag_def_xml (a page-level one:TagDef — add once via update_page_xml if the page has none), tag_xml (the one:Tag that goes first inside a one:OE), and, if you pass text, a ready one_oe_xml.

Hyperlinks on existing text — set_hyperlink_on_object

Turns existing plain text into clickable hyperlinks without replacing the text itself.

• Finds all occurrences of search_text on a page (or within an optional container object) and wraps each with <a href="hyperlink_url">...</a>.
• Preserves existing inline formatting (bold/italic/etc.) around matched text.
• Works inside tables, outlines, cells — anywhere OneNote stores text in <one:T> elements.
• Optional container_object_id scopes the search to a specific object (table, cell, outline) from get_page_objects.

Example: add glossary links to terms on character sheets:

set_hyperlink_on_object(
  page_identifier="Characters/My Character Sheet",
  search_text="Dragon",
  hyperlink_url="onenote:...glossary-dragon-page...",
  container_object_id="{table-cell-object-id}" // optional: limit to one cell/table
)

add_todo_items_to_page_outline — hyperlinks in To Do items

Each item's text is interpreted per content_format, so you can embed hyperlinks directly. For example, use the inline_html from generate_onenote_hyperlinks_xml:

add_todo_items_to_page_outline(
  page_identifier="My Section/My Page",
  content_format: "html",
  items: [
    { text: "<a href=\"onenote:...\">Review glossary entry</a>" }
  ]
)

duplicate_page

Copies a page (for example a template) into a new page. By default the copy lands in the source page's own section; you may pass target_section_identifier and/or new_title. OneNote assigns fresh object IDs to the copy.

save_page_xml_to_file / save_all_notebook_pages_xml_to_file

• save_page_xml_to_file writes one page's raw XML; the file is named after the page title (.xml) unless you pass file_name.
• save_all_notebook_pages_xml_to_file reads an entire notebook by name and writes one XML file (named <notebook>.xml) that mirrors the section-group / section / page structure, with each page's raw OneNote XML embedded inline. Optional output_dir, page_info, overwrite.
• Both default their directory to the plugin's Default export directory setting, or the plugin working directory if unset. Files are written on the machine running OneNote.

save_all_notebook_pages_xml_to_file reads every page via GetPageContent, which loads them into OneNote. For very large notebooks this can make OneNote sluggish — restart OneNote afterward if needed.

Configuration

Troubleshooting

• 0x80080005 / focus flips to OneNote then times out — a privilege-level mismatch. Run LM Studio non-elevated, at the same level as OneNote. Make sure OneNote isn't running elevated either.
• First call is slow / times out — OneNote is starting up. Raise OneNote operation timeout and retry.
• Reads look cut off — lower Default page size (characters); the model pages the rest via next_offset.
• Markdown content fails — install the OneMore add-in, or set ONENOTE_MANAGER_MARKDIG_DLL to its Markdig.Signed.dll. Plain and HTML content need no add-in.
• OneNote gets sluggish after many reads — reads are cached and page GUIDs skip a full-store scan, but reading many distinct pages still loads them into OneNote; restart OneNote periodically for long sessions.
• Logs — messages prefixed [onenote-manager] appear in LM Studio's developer/plugin logs.

Project layout

onenote-manager/
├── manifest.json
├── package.json
├── tsconfig.json
└── src/
    ├── index.ts            # registers config + tools provider
    ├── configSchematics.ts # settings UI
    ├── toolsProvider.ts    # all tools (returned alphabetically)
    ├── onenote.ts          # high-level OneNote operations
    ├── bridge.ts           # PowerShell OneNote COM bridge
    ├── markdown.ts         # Markdown → HTML via OneMore's Markdig
    ├── htmlToOneNote.ts    # plain/HTML/Markdown → OneNote XML
    ├── pageXml.ts          # page-update XML builders
    ├── parseXml.ts         # hierarchy/page parsing, tables, page-clone
    ├── htmlText.ts         # OneNote one:T → plain text
    ├── imageSize.ts        # native image dimensions
    ├── pagination.ts       # text/item slicing + LRU cache
    └── notebookDump.ts     # structured notebook XML export

License

MIT (this plugin). See local-onenote-mcp for the original project's license and terms.