About
Notion MCP Server integrates AI coding assistants with Notion workspaces through the Notion API. It provides tools to interact with pages, data sources (databases), and workspace content. Key capabilities include: - Query data sources with filters and sorts to retrieve specific database entries - Retrieve and update data source metadata and schemas - Create new data sources from scratch or using templates - Move pages between different parent locations in the workspace - Search across workspace content with filters for pages and data sources - Create new pages with support for both page and database parent types
README
Notion MCP Server
> [!NOTE] > > We’ve introduced Notion MCP, a remote MCP server with the following improvements: > > - Easy installation via standard OAuth. No need to fiddle with JSON or API tokens anymore. > - Powerful tools tailored to AI agents, including editing pages in Markdown. These tools are designed with optimized token consumption in mind. > > Learn more and get started at Notion MCP documentation. > > We are prioritizing, and only providing active support for, Notion MCP (remote). As a result: > > - We may sunset this local MCP server repository in the future. > - Issues and pull requests here are not actively monitored. > - Please do not file issues relating to the remote MCP here; instead, contact Notion support.
This project implements an MCP server for the Notion API.
---
⚠️ Version 2.0.0 breaking changes
Version 2.0.0 migrates to the Notion API 2025-09-03 which introduces data sources as the primary abstraction for databases.
What changed
Removed tools (3):
post-database-query - replaced by query-data-sourceupdate-a-database - replaced by update-a-data-sourcecreate-a-database - replaced by create-a-data-sourceNew tools (7):
query-data-source - Query a data source (database) with filters and sortsretrieve-a-data-source - Get metadata and schema for a data sourceupdate-a-data-source - Update data source propertiescreate-a-data-source - Create a new data sourcelist-data-source-templates - List available templates in a data sourcemove-page - Move a page to a different parent locationretrieve-a-database - Get database metadata including its data source IDsParameter changes:
data_source_id instead of database_id["page", "database"] to ["page", "data_source"]page_id and database_id parents (for data sources)Do I need to migrate?
No code changes required. MCP tools are discovered automatically when the server starts. When you upgrade to v2.0.0, AI clients will automatically see the new tool names and parameters. The old database tools are no longer available.
If you have hardcoded tool names or prompts that reference the old database tools, update them to use the new data source tools:
| Old Tool (v1.x) | New Tool (v2.0) | Parameter Change |
| -------------- | --------------- | ---------------- |
| post-database-query | query-data-source | database_id → data_source_id |
| update-a-database | update-a-data-source | database_id → data_source_id |
| create-a-database | create-a-data-source | No change (uses parent.page_id) |
> Note: retrieve-a-database is still available and returns database metadata including the list of data source IDs. Use retrieve-a-data-source to get the schema and properties of a specific data source.
Total tools now: 22 (was 19 in v1.x)
---
Installation
#### 1. Setting up integration in Notion
Go to https://www.notion.so/profile/integrations and create a new internal integration or select an existing one.
While we limit the scope of Notion API's exposed (for example, you will not be able to delete databases via MCP), there is a non-zero risk to workspace data by exposing it to LLMs. Security-conscious users may want to further configure the Integration's _Capabilities_.
For example, you can create a read-only integration token by giving only "Read content" access from the "Configuration" tab:
#### 2. Connecting content to integration
Ensure relevant pages and databases are connected to your integration.
To do this, visit the Access tab in your internal integration settings. Edit access and select the pages you'd like to use.
Alternatively, you can grant page access individually. You'll need to visit the target page, and click on the 3 dots, and select "Connect to integration".
#### 3. Adding MCP config to your client
##### Using npm
###### Cursor & Claude
Add the following to your .cursor/mcp.json or claude_desktop_config.json (MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json)
###### Option 1: Using NOTI
Related MCP Servers
AI Research Assistant
hamid-vakilzadeh
AI Research Assistant provides comprehensive access to millions of academic papers through the Semantic Scholar and arXiv databases. This MCP server enables AI coding assistants to perform intelligent literature searches, citation network analysis, and paper content extraction without requiring an API key. Key features include: - Advanced paper search with multi-filter support by year ranges, citation thresholds, field of study, and publication type - Title matching with confidence scoring for finding specific papers - Batch operations supporting up to 500 papers per request - Citation analysis and network exploration for understanding research relationships - Full-text PDF extraction from arXiv and Wiley open-access content (Wiley TDM token required for institutional access) - Rate limits of 100 requests per 5 minutes with options to request higher limits through Semantic Scholar
Linkup
LinkupPlatform
Linkup is a real-time web search and content extraction service that enables AI assistants to search the web and retrieve information from trusted sources. It provides source-backed answers with citations, making it ideal for fact-checking, news gathering, and research tasks. Key features of Linkup: - Real-time web search using natural language queries to find current information, news, and data - Page fetching to extract and read content from any webpage URL - Search depth modes: Standard for direct-answer queries and Deep for complex research across multiple sources - Source-backed results with citations and context from relevant, trustworthy websites - JavaScript rendering support for accessing dynamic content on JavaScript-heavy pages
Math-MCP
EthanHenrickson
Math-MCP is a computation server that enables Large Language Models (LLMs) to perform accurate numerical calculations through the Model Context Protocol. It provides precise mathematical operations via a simple API to overcome LLM limitations in arithmetic and statistical reasoning. Key features of Math-MCP: - Basic arithmetic operations: addition, subtraction, multiplication, division, modulo, and bulk summation - Statistical analysis functions: mean, median, mode, minimum, and maximum calculations - Rounding utilities: floor, ceiling, and nearest integer rounding - Trigonometric functions: sine, cosine, tangent, and their inverses with degrees and radians conversion support