Provides full property type support for Notion database operations, including creating and updating rows with all property types, querying databases with filters and auto-pagination, appending blocks and markdown to pages, and retrieving database schemas.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@notion-enhanced query my Notion database named 'Tools' and list all entries"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Enhanced Notion MCP server with full property type support for database operations.
Full Property Type Support: Create and update database rows with all 24 Notion property types
Auto-Pagination: Query functions automatically fetch ALL results by default (no 100-item limit)
Block Operations: Append any block type (tables, callouts, code, etc.) to pages
Markdown Conversion: Convert markdown to Notion blocks
Schema Introspection: Get database schemas with property definitions
Related MCP server: MCP Notion Server (@suncreation)
get_database_schema(database_id) - Get database schema with property types and options
query_database(database_id, filter, sorts, page_size, start_cursor, fetch_all) - Query database with filters
fetch_all=True (default): Auto-paginates to fetch ALL results
fetch_all=False: Returns single page with next_cursor for manual pagination
create_database_row(database_id, properties, content) - Create row with any property types
update_database_row(page_id, properties) - Update row properties
get_page(page_id, include_content) - Get page with properties and content (auto-paginates content blocks)
search_pages(query, filter_type, page_size, start_cursor, fetch_all) - Search pages and databases
fetch_all=True (default): Auto-paginates to fetch ALL results
fetch_all=False: Returns single page with next_cursor for manual pagination
append_blocks(page_id, blocks) - Append blocks to page
append_markdown(page_id, markdown) - Append markdown content
Type | Example Value |
title |
|
rich_text |
|
number |
|
select |
|
multi_select |
|
date |
|
checkbox |
|
url |
|
| |
phone_number |
|
status |
|
files |
|
relation |
|
people |
|
uv tool install .Add to ~/.claude.json:
{
"mcpServers": {
"notion-enhanced": {
"type": "stdio",
"command": "notion-enhanced-mcp",
"args": [],
"env": {
"NOTION_TOKEN": "your_notion_token"
}
}
}
}By default, query_database and search_pages automatically paginate through ALL results. The Notion API limits responses to 100 items per request, but this MCP handles pagination transparently.
# Fetch ALL rows (auto-pagination, default behavior)
result = query_database(database_id="abc123...")
print(f"Total tools: {result['total_count']}") # e.g., 500
# Manual pagination (for large datasets or streaming)
result = query_database(database_id="abc123...", fetch_all=False)
while result.get('has_more'):
# Process current batch
process(result['results'])
# Fetch next page
result = query_database(
database_id="abc123...",
start_cursor=result['next_cursor'],
fetch_all=False
)# Create a tool row with full properties
create_database_row(
database_id="abc123...",
properties={
"Tool Name": "Morph LLM",
"URL": "https://morphllm.com",
"Tags": ["Coding", "AI", "Developers"],
"Rating": 2,
"Description": "Fast code editing AI"
}
)Append blocks to a Notion page.
Args: page_id: The ID of the page to append to blocks: List of block objects. Each block should have: - type: Block type (paragraph, heading_1, code, table, etc.) - Additional fields depending on type: - paragraph: {"text": "content"} - heading_1/2/3: {"text": "heading"} - bulleted_list_item: {"text": "item"} - numbered_list_item: {"text": "item"} - to_do: {"text": "task", "checked": false} - code: {"code": "content", "language": "python"} - quote: {"text": "quote"} - callout: {"text": "content", "emoji": "💡"} - divider: {} (no additional fields) - bookmark: {"url": "https://..."} - image: {"url": "https://..."} - table: {"rows": [["a", "b"], ["c", "d"]], "has_column_header": true} after_block_id: Optional block ID to insert after
Returns: List of created blocks
Inputs: blocks (required), page_id (required), after_block_id. Returns: object
Append markdown content to a Notion page.
Converts markdown to Notion blocks and appends them.
Args: page_id: The ID of the page to append to markdown: Markdown content to append
Returns: Number of blocks created
Inputs: page_id (required), markdown (required). Returns: object
Create a comment on a page or reply to a discussion thread.
Args: page_id: The ID of the page to comment on text: Comment text content discussion_id: Optional discussion thread ID to reply to
Returns: Created comment object
Inputs: text (required), page_id (required), discussion_id. Returns: object
Create a new database (as a child of a page).
Args: parent_page_id: The ID of the parent page title: Database title properties: Database property schema. Keys are property names, values are property config objects, e.g.: {"Name": {"title": {}}, "Tags": {"multi_select": {"options": []}}}
Returns: Created database with ID and URL
Inputs: title (required), properties (required), parent_page_id (required). Returns: object
Create a new row in a Notion database with full property type support.
Args: database_id: The ID of the Notion database properties: Dict of property_name -> value. Supported types: - title: str - rich_text: str - number: int or float - select: str (option name) - multi_select: list[str] (option names) - date: str (ISO 8601) or {"start": str, "end": str} - checkbox: bool - url: str - email: str - phone_number: str - status: str (status name) - files: list[str] (URLs) - relation: list[str] (page IDs) - people: list[str] (user IDs) content: Optional markdown content to add to the page body
Returns: Created page with ID and URL
Inputs: properties (required), database_id (required), content. Returns: object
Create a standalone page (not a database row).
For creating database rows, use create_database_row instead.
Args: parent_type: "page_id" or "workspace" (for top-level pages) parent_id: The ID of the parent page (ignored if workspace) title: Page title properties: Optional additional properties content: Optional markdown content for the page body
Returns: Created page with ID and URL
Inputs: title (required), parent_id (required), parent_type (required), content, +1 more. Returns: object
Delete (archive) a block.
Args: block_id: The ID of the block to delete
Returns: Deleted block object
Inputs: block_id (required). Returns: object
Retrieve a single block by ID.
Args: block_id: The ID of the block
Returns: Block object with type and content
Inputs: block_id (required). Returns: object
Retrieve children blocks of a block or page.
Args: block_id: The ID of the parent block or page page_size: Number of results per page (max 100) start_cursor: Cursor for pagination fetch_all: If True, auto-paginate all children. Default True.
Returns: Dict with results list and pagination info
Inputs: block_id (required), fetch_all, page_size, start_cursor. Returns: object
Get the schema of a Notion database with all property definitions.
Args: database_id: The ID of the Notion database
Returns: Dict with database title and properties schema
Inputs: database_id (required). Returns: object
Get a Notion page with its properties and optionally content.
Args: page_id: The ID of the page include_content: Whether to fetch page content blocks (auto-paginates all blocks)
Returns: Page info with properties and optionally content
Inputs: page_id (required), include_content. Returns: object
Get the bot user associated with the current token.
Returns: Bot user object with name, type, and workspace info
Inputs: no named parameters. Returns: object
Get a user by ID.
Args: user_id: The ID of the user
Returns: User object
Inputs: user_id (required). Returns: object
List all users in the workspace.
Args: page_size: Number of results per page (max 100) start_cursor: Cursor for pagination
Returns: List of user objects
Inputs: page_size, start_cursor. Returns: object
Move a page to a different parent.
Args: page_id: The ID of the page to move parent_type: "page_id" or "database_id" parent_id: The ID of the new parent
Returns: Moved page info
Inputs: page_id (required), parent_id (required), parent_type (required). Returns: object
Query a Notion database with optional filter and sorts.
Args: database_id: The ID of the Notion database filter: Optional Notion filter object (see Notion API docs) sorts: Optional list of sort objects page_size: Number of results per page (max 100) start_cursor: Cursor for pagination (from previous query's next_cursor) fetch_all: If True, auto-paginate to fetch ALL results. If False, return single page with pagination info. Default True.
Returns: Dict with: - results: List of database rows with parsed properties - total_count: Number of results returned - has_more: Whether more results exist (only when fetch_all=False) - next_cursor: Cursor for next page (only when fetch_all=False and has_more=True)
Inputs: database_id (required), sorts, filter, fetch_all, +2 more. Returns: object
Search Notion pages and databases.
Args: query: Search query filter_type: Optional filter - "page" or "database" page_size: Number of results per page (max 100) start_cursor: Cursor for pagination fetch_all: If True, auto-paginate to fetch ALL results. Default True.
Returns: Dict with: - results: List of matching pages/databases - total_count: Number of results - has_more: Whether more results exist (only when fetch_all=False) - next_cursor: Cursor for next page (only when fetch_all=False and has_more=True)
Inputs: query (required), fetch_all, page_size, filter_type, +1 more. Returns: object
Update a block's content or archive it.
Args: block_id: The ID of the block to update fields: Block fields to update. Pass the block type key with its content, e.g. {"paragraph": {"rich_text": [...]}} or {"archived": true} to archive.
Returns: Updated block object
Inputs: fields (required), block_id (required). Returns: object
Update properties on an existing Notion database row.
Args: page_id: The ID of the page/row to update properties: Dict of property_name -> value to update
Returns: Updated page info
Inputs: page_id (required), properties (required). Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 19 tools
Most tools are clearly distinct by resource and action. Minor confusion: append_markdown vs. append_blocks both append content to a page, though one accepts markdown and the other raw blocks. get_block vs. get_block_children are distinct but related; descriptions clarify their difference.
Consistent verb_noun pattern throughout (e.g., get_database_schema, query_database, create_database_row, update_database_row, append_blocks, etc.). No mixing of conventions or ambiguous names.
19 tools for a comprehensive Notion server is reasonable, covering core operations. Slightly heavy but each tool appears to have a distinct role with minimal redundancy.
The surface covers pages, databases, blocks, users, and comments well. Missing explicit delete operations for pages/databases (only blocks can be deleted) and no update for page properties (though update_database_row exists for rows). The get_self and user tools add workspace awareness, but gaps in deletion and page updates are notable.
MCP-native open-source Notion alternative: read & write pages, databases and kanban boards.
Hosted Notion MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
