# How to integrate Notion MCP with Antigravity

```json
{
  "title": "How to integrate Notion MCP with Antigravity",
  "toolkit": "Notion",
  "toolkit_slug": "notion",
  "framework": "Antigravity",
  "framework_slug": "antigravity",
  "url": "https://composio.dev/toolkits/notion/framework/antigravity",
  "markdown_url": "https://composio.dev/toolkits/notion/framework/antigravity.md",
  "updated_at": "2026-05-12T10:20:23.194Z"
}
```

## Introduction

### How to integrate Notion MCP with Antigravity
Antigravity IDE is Google's agentic IDE, built on a VS Code-style editor and powered by models like Gemini 3.5 Flash, Gemini 3.1 Pro, Opus 4.6, and more. It treats the AI agent as a first-class teammate, planning, coding, and validating work through an Agent Manager dashboard with deep browser connectivity.
In this guide, I will explain the easiest and most secure way to connect your Notion account to Antigravity IDE via Composio Connect, so it can add meeting notes to project wiki page, create a new task database for Q3, archive completed sprint summary pages, and more without ever putting your account credentials at risk.

## Also integrate Notion with

- [ChatGPT](https://composio.dev/toolkits/notion/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/notion/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/notion/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/notion/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/notion/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/notion/framework/codex)
- [Cursor](https://composio.dev/toolkits/notion/framework/cursor)
- [VS Code](https://composio.dev/toolkits/notion/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/notion/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/notion/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/notion/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/notion/framework/cli)
- [Google ADK](https://composio.dev/toolkits/notion/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/notion/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/notion/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/notion/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/notion/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/notion/framework/crew-ai)

## TL;DR

### Why use Composio?
Composio provides:
- Access to 1,000+ managed apps from a single MCP endpoint. This makes it convenient for agents to run cross-app workflows.
- Programmatic tool calling. Allows LLMs to write code in a remote workbench to handle complex tool chaining. Reduces to-and-fro with LLMs for frequent tool calling.
- Large tool response handling outside the LLM context. This minimizes context bloat from large tool responses.
- Dynamic just-in-time access to thousands of tools across hundreds of apps. Composio loads the tools your agent needs, so LLMs are not overwhelmed by tools they do not need.

## Connect Notion to Antigravity

### Connect Notion to Antigravity
Antigravity does not ship with one-click custom MCP install links yet, so configuration goes through the IDE's raw config file. The process takes under a minute.
### 1. Open the MCP Config
Go to Antigravity Settings, open the Customizations tab, then click Open MCP Config to open mcp_config.json in the editor.
### 2. Get your API key
Go to the [Composio Dashboard](https://dashboard.composio.dev/~/org/connect/clients/) and copy your API key.
### 3. Add Composio to mcp_config.json
Paste the following configuration into the file:

```bash
{
  "mcpServers": {
    "remote-composio": {
      "serverUrl": "https://connect.composio.dev/mcp",
      "headers": {
        "x-consumer-api-key": "your-composio-api-key"
      }
    }
  }
}
```

## What is the Notion MCP server, and what's possible with it?

The Notion MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Notion account. It provides structured and secure access to your notes, docs, wikis, and tasks, so your agent can perform actions like creating pages, managing databases, adding content, commenting, and organizing your Notion workspace for you.
- Bulk content creation and formatting: Let your agent efficiently add and format multiple blocks of text, lists, or markdown content to Notion pages in one go.
- Automated page and database management: Have your agent create new pages, duplicate existing ones, or set up entire databases with custom properties—no manual setup required.
- Smart commenting and collaboration: Enable your agent to add comments to pages or discussion threads, making real-time collaboration smoother.
- Workspace organization and cleanup: Ask your agent to archive, delete, or restore pages and blocks, keeping your workspace tidy and up to date.
- Deep block and structure retrieval: Direct your agent to fetch metadata, list child blocks, or dig into nested content for analysis, reporting, or workflow automation.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `NOTION_ADD_MULTIPLE_PAGE_CONTENT` | Add multiple content blocks (bulk, user-friendly) | Bulk-add content blocks to Notion. Text >2000 chars auto-splits. Parses markdown formatting. ⚠️ PARENT BLOCK TYPES: Content is added AS CHILDREN of parent_block_id. - To add content AFTER a heading, use PAGE ID as parent + heading ID in 'after' param. - Headings CANNOT have children unless is_toggleable=True. Simplified format: {'content': 'text', 'block_property': 'paragraph'} Full format for code: {'type': 'code', 'code': {'rich_text': [...], 'language': 'python'}} Array format also supported (auto-normalized): [{"parent_block_id": "..."}, {block1}, {block2}] => proper request structure |
| `NOTION_APPEND_CODE_BLOCKS` | Append code blocks (code, quote, equation) | Append code and technical blocks (code, quote, equation) to a Notion page. Use for: - Code snippets and programming examples (code) - Citations and highlighted quotes (quote) - Mathematical formulas and equations (equation) Supported block types: - code: Code with syntax highlighting (70+ languages including Python, JavaScript, Go, Rust, etc.) - quote: Block quotes for citations - equation: LaTeX/KaTeX mathematical expressions ⚠️ Code content is limited to 2000 characters per text.content field. For longer code, split into multiple code blocks. For other block types, use specialized actions: - append_text_blocks: paragraphs, headings, lists - append_task_blocks: to-do, toggle, callout - append_media_blocks: image, video, audio, files - append_layout_blocks: divider, columns, TOC - append_table_blocks: tables |
| `NOTION_APPEND_LAYOUT_BLOCKS` | Append layout blocks (divider, TOC, columns) | Append layout blocks (divider, TOC, breadcrumb, columns) to a Notion page. Supported types: - divider: Horizontal line separator - table_of_contents: Auto-generated from headings - breadcrumb: Page hierarchy navigation - column_list: Multi-column layout (requires 2+ columns, each with 1+ child block) For multi-column layouts, create column_list with column children in one request. Each column must contain at least 1 child block. For other blocks, use: append_text_blocks, append_task_blocks, append_code_blocks, append_media_blocks, or append_table_blocks. |
| `NOTION_APPEND_MEDIA_BLOCKS` | Append media blocks (image, video, audio, files) | Append media blocks (image, video, audio, file, pdf, embed, bookmark) to a Notion page. Use for: - Images and screenshots (image) - YouTube/Vimeo videos or direct video URLs (video) - Audio files and podcasts (audio) - File downloads (file) - PDF documents (pdf) - Embedded content from Twitter, Figma, CodePen, etc. (embed) - Link previews with metadata (bookmark) All media blocks require external URLs. For other block types, use specialized actions: - append_text_blocks: paragraphs, headings, lists - append_task_blocks: to-do, toggle, callout - append_code_blocks: code, quote, equation - append_layout_blocks: divider, columns, TOC - append_table_blocks: tables |
| `NOTION_APPEND_TABLE_BLOCKS` | Append table blocks | Append table blocks to a Notion page. Use for structured tabular data like spreadsheets, comparison charts, and status trackers. Example: { "table_width": 3, "has_column_header": true, "rows": [ {"cells": [[{"type": "text", "text": {"content": "Col1"}}], [...], [...]]} ] } ⚠️ Cell content limited to 2000 chars per text.content field. |
| `NOTION_APPEND_TASK_BLOCKS` | Append task blocks (to-do, toggle, callout) | Append task blocks (to-do, toggle, callout) to a Notion page or block. Supported block types: - to_do: Checkbox items (checkable/uncheckable) - toggle: Collapsible sections - callout: Highlighted boxes with emoji icons All three types support nested children (up to 2 levels of nesting). block_id must be a page or block that supports children (e.g., page, toggle, paragraph, list items, quote, callout, to_do). Blocks like divider, breadcrumb, equation do NOT support children. Limits: 2000 chars per text.content, max 100 blocks per request. For other blocks: append_text_blocks, append_code_blocks, append_media_blocks, append_layout_blocks, append_table_blocks. |
| `NOTION_APPEND_TEXT_BLOCKS` | Append text blocks (paragraphs, headings, lists) | Append text blocks (paragraphs, headings, lists) to a Notion page. This is the most commonly used action for adding content to Notion. Use for: documentation, notes, articles, outlines, lists. Supported block types: - paragraph: Regular text - heading_1, heading_2, heading_3: Section headers - bulleted_list_item: Bullet points - numbered_list_item: Numbered lists ⚠️ Text content is limited to 2000 characters per text.content field. For other block types, use specialized actions: - append_task_blocks: to-do, toggle, callout - append_code_blocks: code, quote, equation - append_media_blocks: image, video, audio, files - append_layout_blocks: divider, columns, TOC - append_table_blocks: tables |
| `NOTION_ARCHIVE_NOTION_PAGE` | Archive Notion Page | Archives (moves to trash) or unarchives (restores from trash) a specified Notion page. Limitation: Workspace-level pages (top-level pages with no parent page or database) cannot be archived via the API and must be archived manually in the Notion UI. |
| `NOTION_CREATE_COMMENT` | Create comment | Adds a comment to a Notion page (via `parent_page_id`) OR to an existing discussion thread (via `discussion_id`); cannot create new discussion threads on specific blocks (inline comments). |
| `NOTION_CREATE_DATABASE` | Create Notion Database | Creates a new Notion database as a subpage under a specified parent page with a defined properties schema. IMPORTANT NOTES: - The parent page MUST be shared with your integration, otherwise you'll get a 404 error - If you encounter conflict errors (409), retry the request as Notion may experience temporary save conflicts - For relation properties, you MUST provide the database_id of the related database - Parent ID must be a valid UUID format (with or without hyphens), not a template variable Use this action exclusively for creating new databases. |
| `NOTION_CREATE_FILE_UPLOAD` | Create Notion file upload | Tool to create a Notion FileUpload object and retrieve an upload URL. Use when you need to automate attaching local or external files directly into Notion without external hosting. |
| `NOTION_CREATE_NOTION_PAGE` | Create Notion page | Creates a new page in a Notion workspace under a specified parent page or database. Supports creating pages with markdown content using the native markdown parameter, or as an empty page that can be populated later. PREREQUISITES: - Parent page/database must exist and be accessible in your Notion workspace - Use search_pages or list_databases first to obtain valid parent IDs LIMITATIONS: - Cannot create root-level pages (must have a parent) - May encounter conflicts if creating pages too quickly - Title-based parent search is less reliable than using UUIDs - The markdown parameter is mutually exclusive with children/content parameters |
| `NOTION_DELETE_BLOCK` | Delete a block | Archives a Notion block, page, or database using its ID, which sets its 'archived' property to true (like moving to "Trash" in the UI) and allows it to be restored later. Note: This operation will fail if the block has an archived parent or ancestor in the hierarchy. You must unarchive the ancestor before archiving/deleting its descendants. IMPORTANT LIMITATION: Workspace-level pages (top-level pages that are direct children of the workspace, not contained within other pages or databases) cannot be archived via the Notion API. This is a documented Notion API restriction. Only pages that are children of other pages or databases can be deleted through this action. |
| `NOTION_DUPLICATE_PAGE` | Duplicate page | Duplicates a Notion page, including all its content, properties, and nested blocks, under a specified parent page or workspace. |
| `NOTION_FETCH_ALL_BLOCK_CONTENTS` | Fetch All Notion Block Contents | Tool to fetch all child blocks for a given Notion block. Use when you need a complete listing of a block's children beyond a single page; supports optional recursive expansion of nested blocks. |
| `NOTION_FETCH_BLOCK_CONTENTS` | Fetch Notion Block Children | Retrieves a paginated list of direct, first-level child block objects along with contents for a given parent Notion block or page ID; use block IDs from the response for subsequent calls to access deeply nested content. |
| `NOTION_FETCH_BLOCK_METADATA` | Fetch Notion block metadata | Fetches metadata for a Notion block (including pages, which are special blocks) using its UUID. Returns block type, properties, and basic info but not child content. Prerequisites: 1) Block/page must be shared with your integration, 2) Use valid block_id from API responses (not URLs). For child blocks, use fetch_block_contents instead. Common 404 errors mean the block isn't accessible to your integration. |
| `NOTION_FETCH_COMMENTS` | Fetch comments | Fetches unresolved comments for a specified Notion block or page ID. The block/page must be shared with your Notion integration and the integration must have 'Read comments' capability enabled, otherwise a 404 error will be returned. |
| `NOTION_FETCH_DATA` | Fetch Notion Data | Fetches Notion items (pages and/or databases) from the Notion workspace, use this to get minimal data about the items in the workspace with a query or list all items in the workspace with minimal data |
| `NOTION_FETCH_DATABASE` | Fetch Database | Fetches a Notion database's structural metadata (properties, title, etc.) via its `database_id`, not the data entries; `database_id` must reference an existing database. |
| `NOTION_FETCH_ROW` | Fetch database row | Retrieves a Notion database row's properties and metadata; use fetch_block_contents for page content blocks. |
| `NOTION_GET_ABOUT_USER` | Get about user | Retrieves detailed information about a specific Notion user, such as their name, avatar, and email, based on their unique user ID. |
| `NOTION_GET_PAGE_MARKDOWN` | Get page markdown | Retrieve a Notion page's full content rendered as Notion-flavored Markdown in a single API call. Use when you need the readable content of a page without recursive block-children fetching. |
| `NOTION_GET_PAGE_PROPERTY_ACTION` | Get page property | Call this to get a specific property from a Notion page when you have a valid `page_id` and `property_id`; handles pagination for properties returning multiple items. |
| `NOTION_INSERT_ROW_DATABASE` | Insert row database | Creates a new page (row) in a specified Notion database. Prerequisites: - Database must be shared with your integration - Property names AND types must match schema exactly (case-sensitive) - Use NOTION_FETCH_DATA with fetch_type='databases' first to get exact property names and types - Each database has ONE 'title' property; other text fields are 'rich_text' - Database must NOT have multiple data sources (synced databases are not supported) Common Errors: - 404: Database not shared with integration - 400 "not a property": Wrong property name - 400 "expected to be X": Wrong property type - 400 "multiple_data_sources": Database uses multiple data sources (not supported) Note: Rich text content in child_blocks is automatically truncated to 2000 characters per Notion API limits. |
| `NOTION_INSERT_ROW_FROM_NL` | Insert Row From Natural Language | Creates a new row (page) in a Notion database from a natural language description. Fetches the database schema at runtime, uses an LLM to generate the correctly-formatted property payload, and creates the page. |
| `NOTION_LIST_DATA_SOURCE_TEMPLATES` | List data source templates | Tool to list all templates for a Notion data source. Use when needing to discover template IDs/names for bulk page creation. Use after confirming the data_source_id. |
| `NOTION_LIST_FILE_UPLOADS` | List Notion file uploads | Tool to retrieve file uploads for the current bot integration, sorted by most recent first. Use when you need to list all file uploads or paginate through file upload history. |
| `NOTION_LIST_USERS` | List users | Retrieves a paginated list of users (excluding guests) from the Notion workspace; the number of users returned per page may be less than the requested `page_size`. |
| `NOTION_MOVE_PAGE` | Move Page | Tool to move a Notion page to a new parent (page or database). Use when you need to reorganize page hierarchy. Important: To move to a database, use data_source_id (NOT database_id). Get the data source ID from the database object using NOTION_FETCH_DATABASE. |
| `NOTION_QUERY_DATABASE` | Query database | Queries a Notion database to retrieve pages (rows). In Notion, databases are collections where each row is a page and columns are properties. Returns paginated results with metadata. Important requirements: - The database must be shared with your integration - Property names in sorts must match existing database properties exactly (case-sensitive) - For timestamp sorting, use 'created_time' or 'last_edited_time' (case-insensitive) - The start_cursor must be a valid UUID from a previous response's next_cursor field - Database IDs must be valid 32-character UUIDs (with or without hyphens) Use this action to: - Retrieve all or filtered database entries - Sort results by database properties or page timestamps - Paginate through large result sets - Get database content for processing or display |
| `NOTION_QUERY_DATABASE_WITH_FILTER` | Query database with filter | Tool to query a Notion database with server-side filtering, sorting, and pagination. Use when you need to retrieve a subset of rows by property, date, status, or other conditions. |
| `NOTION_QUERY_DATA_SOURCE` | Query data source | Tool to query a Notion data source. Use when you need to retrieve pages or child data sources with filters, sorts, and pagination. Make paginated requests using cursors and optional property filters for efficient data retrieval. |
| `NOTION_REPLACE_PAGE_CONTENT` | Replace page content (with backup) | Safely replaces a page's child blocks by optionally backing up current content, deleting existing children, then appending new children in batches. Use when you need to rebuild a page without leaving partial states. Notion does not provide atomic transactions; this tool orchestrates a multi-step workflow with optional backup to reduce risk. |
| `NOTION_RETRIEVE_COMMENT` | Retrieve Comment | Tool to retrieve a specific comment by its ID. Use when you have a comment ID and need to fetch its details. |
| `NOTION_RETRIEVE_DATABASE_PROPERTY` | Retrieve Database Property | Tool to retrieve a specific property object of a Notion database. Use when you need to get details about a single database column/property. |
| `NOTION_RETRIEVE_FILE_UPLOAD` | Retrieve Notion file upload | Tool to retrieve details of a Notion File Upload object by its identifier. Use when you need to check the status or details of an existing file upload. |
| `NOTION_RETRIEVE_PAGE` | Retrieve page | Retrieve a Notion page's properties/metadata (not block content) by page_id. Use when you have a page URL/ID and need to access its properties; for page content use block-children tools. |
| `NOTION_SEARCH_NOTION_PAGE` | Search Notion pages and databases | Searches Notion pages and databases by title. Use specific search terms to find items by title (primary approach). KNOWN LIMITATIONS: (1) Search indexing is not immediate - recently shared items may not appear. (2) Search is not exhaustive - results may be incomplete. (3) Database pages return all custom properties with full nested structures, which can create large responses for databases with many properties - use filter_properties to reduce response size. FALLBACK STRATEGY: If a specific title search returns empty results despite knowing items exist, try an empty query to list all accessible items and filter client-side. |
| `NOTION_SEND_FILE_UPLOAD` | Send file upload | Tool to transmit file contents to Notion for a file upload object. Use after creating a file upload object to send the actual file data. |
| `NOTION_UPDATE_BLOCK` | Update block | Updates existing Notion block's text content. ⚠️ CRITICAL: Content limited to 2000 chars. Cannot change block type or archive blocks. Content exceeding 2000 chars will fail with validation error. For longer content, split across multiple blocks using add_multiple_page_content. |
| `NOTION_UPDATE_PAGE` | Update Page | Update page properties, icon, cover, or archive status. IMPORTANT: Property names are workspace-specific and case-sensitive. Use NOTION_FETCH_ROW or NOTION_FETCH_DATABASE first to discover exact property names and valid select/status options. Common errors: - "X is not a property that exists": Discover properties with NOTION_FETCH_ROW - "Invalid status option": Check valid options with NOTION_FETCH_DATABASE - "should be defined": Wrap values: {'Field': {'type': value}} Property formats: title/rich_text use {'text': {'content': 'value'}}, select/status use {'name': 'option'} |
| `NOTION_UPDATE_ROW_DATABASE` | Update Database Row (Page) | Updates a specific row/page within a Notion database by its page UUID (row_id). IMPORTANT CLARIFICATION: This action updates INDIVIDUAL ROWS (pages) in a database, NOT the database structure. - To update a ROW/PAGE: Use THIS action with `row_id` (the page UUID) - To update DATABASE SCHEMA (columns, properties, title): Use NOTION_UPDATE_SCHEMA_DATABASE with `database_id` REQUIRED: `row_id` is MANDATORY. This is the UUID of the specific page/row to update. Do NOT pass `database_id` to this action - that parameter does not exist here. Common issues: (1) Use UUID from page URL, not the full URL (2) Ensure page is shared with integration (3) Match property names exactly as in database (4) Use 'status' type for Status properties, not 'select' (5) Retry on 409 Conflict errors (concurrent updates) Supports updating properties, icon, cover, or archiving the row. |
| `NOTION_UPDATE_SCHEMA_DATABASE` | Update database schema | Updates an existing Notion database's schema including title, description, and/or properties (columns). IMPORTANT NOTES: - At least one update (title, description, or properties) must be provided - The database must be shared with your integration - Property names are case-sensitive and must match exactly - When changing a property to 'relation' type, you MUST provide the database_id of the target database - Removing properties will permanently delete that column and its data - Use NOTION_FETCH_DATA first to get the exact property names and database structure Common errors: - 'database_id' missing: Ensure you're passing the database_id parameter (not page_id) - 'data_source_id' undefined: When changing to relation type, database_id is required in PropertySchemaUpdate - Property name mismatch: Names must match exactly including case and special characters |
| `NOTION_UPSERT_ROW_DATABASE` | Upsert database rows | Tool to upsert rows in a Notion database by querying for existing rows and creating or updating them. Use when you need to sync data to Notion without creating duplicates. Each item is matched by a filter, then either created (if no match) or updated (if match found). Supports bulk operations with per-item error handling. |

## Supported Triggers

| Trigger slug | Name | Description |
|---|---|---|
| `NOTION_ALL_PAGE_EVENTS_TRIGGER` | All Page Events | Triggers when any Notion page is created or updated across the workspace. |
| `NOTION_COMMENT_CREATED` | Comment Created | Triggers when a new comment is created in Notion. Optional `page_id` filter scopes to comments on a specific page. When omitted, fires for any new comment in the workspace the integration has access to. Requires the 'Read comments' capability on the Notion integration. If a connection was authorized before that capability was enabled, the user must re-authorize the connection for comment events to flow. |
| `NOTION_COMMENTS_ADDED_TRIGGER` | New Comment | Triggers when a new comment is added to a specified Notion block or page. |
| `NOTION_DATABASE_CREATED` | Database Created | Triggers when a new Notion database (the container) is created. A database is the post-2025-09-03 container that holds one or more data sources. This trigger fires for the container's creation event (`database.created`), distinct from `NOTION_DATASOURCE_CREATED` which fires when a new data source is added to an existing database. Most customers calling Notion's `POST /v1/databases` (the legacy API) or creating a database via the Notion UI will see this event. Adding a new data source to an existing database fires `data_source.created` instead — use `NOTION_DATASOURCE_CREATED` for that. Notion's payload puts `entity.type: "block"` (the container is a `child_database` block in the content tree) and `entity.id` is the database id. |
| `NOTION_DATASOURCE_CREATED` | Data Source Created | Triggers when a new Notion data source is created. Fires workspace-wide. The payload's `data.parent` carries the data source's tree parent (typically the teamspace) for downstream filtering. A single template-based database creation can fire multiple `data_source.created` events at once — one per data source the template instantiates. |
| `NOTION_DATASOURCE_SCHEMA_UPDATED` | Data Source Schema Updated | Triggers when a Notion data source's schema is updated. Fires on column add / remove / rename. Payload includes `data.updated_properties: [{id, name, action}]` so consumers can discriminate the kind of change downstream. Optional `data_source_id` filter scopes to schema changes on a single data source. When omitted, fires for any schema change in the workspace the integration has access to. Note: adding a column also fires `page.properties_updated` once per existing row in the data source. Customers wanting a single structural-change signal should use this trigger. |
| `NOTION_PAGE_ADDED_TO_DATABASE` | New Page | Triggers when a new page is added to a Notion database. |
| `NOTION_PAGE_ADDED_TRIGGER` | Page Added to Page | Fires when a new subpage (a `child_page` type block) is added under a specified parent Notion page. |
| `NOTION_PAGE_CONTENT_UPDATED` | Page Content Updated | Triggers when the body content of a Notion page is updated. Customer optionally scopes with at most one of: - data_source_id: any row in this data source - page_id: this specific page - parent_page_id: any page whose immediate parent is this page With none set, fires for any page content edit in the workspace the integration has access to. Notion aggregates content edits within a short window (~60s typical). |
| `NOTION_PAGE_CREATED` | Page Created | Triggers when a new Notion page is created. Customer optionally scopes with at most one of: - data_source_id: new row in this data source - parent_page_id: new sub-page under this page (immediate parent only) With neither set, fires for any new page in the workspace the integration has access to. Notion sends ~60s aggregation latency on most events. |
| `NOTION_PAGE_PROPERTIES_UPDATED` | Page Properties Updated | Triggers when properties of a Notion page are updated. Customer optionally scopes with at most one of: - data_source_id: any row in this data source - page_id: this specific page - parent_page_id: any page whose immediate parent is this page With none set, fires for any property change in the workspace the integration has access to. Adding a column to a data source fires this trigger once per existing row. Customers can branch on `data.updated_properties` (array of property IDs) to filter downstream. |
| `NOTION_PAGE_UPDATED_TRIGGER` | Page Updated | Triggers when any block within a specified Notion page is updated. |
| `NOTION_VIEW_CREATED` | View Created | Triggers when a new Notion view is created. Fires workspace-wide. The payload includes `data.view_type` (`table`, `board`, `gallery`, `calendar`, `list`, `timeline`, `gantt`) and `data.parent` pointing at the view's tree parent (typically the teamspace), so customers can filter downstream. |

## Creating MCP Server - Stand-alone vs Composio SDK

Once connected, Antigravity can access the Notion MCP server via Composio to run actions that you authorize directly from the agent panel.

## Complete Code

None listed.

## Conclusion

### Conclusion
You have successfully connected Notion to Antigravity using Composio Connect. Your agent can now use Notion securely without exposing credentials in prompts or local scripts.

## How to build Notion MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/notion/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/notion/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/notion/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/notion/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/notion/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/notion/framework/codex)
- [Cursor](https://composio.dev/toolkits/notion/framework/cursor)
- [VS Code](https://composio.dev/toolkits/notion/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/notion/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/notion/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/notion/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/notion/framework/cli)
- [Google ADK](https://composio.dev/toolkits/notion/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/notion/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/notion/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/notion/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/notion/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/notion/framework/crew-ai)

## Related Toolkits

- [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly.
- [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations.
- [Asana](https://composio.dev/toolkits/asana) - Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals.
- [Google Tasks](https://composio.dev/toolkits/googletasks) - Google Tasks is a to-do list and task management tool integrated into Gmail and Google Calendar. It helps you organize, track, and complete tasks across your Google ecosystem.
- [Linear](https://composio.dev/toolkits/linear) - Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity.
- [Jira](https://composio.dev/toolkits/jira) - Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently.
- [Clickup](https://composio.dev/toolkits/clickup) - ClickUp is an all-in-one productivity platform for managing tasks, docs, goals, and team collaboration. It streamlines project workflows so teams can work smarter and stay organized in one place.
- [Monday](https://composio.dev/toolkits/monday) - Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agiled](https://composio.dev/toolkits/agiled) - Agiled is an all-in-one business management platform for CRM, projects, and finance. It helps you streamline workflows, consolidate client data, and manage business processes in one place.
- [Ascora](https://composio.dev/toolkits/ascora) - Ascora is a cloud-based field service management platform for service businesses. It streamlines scheduling, invoicing, and customer operations in one place.
- [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place.
- [Beeminder](https://composio.dev/toolkits/beeminder) - Beeminder is an online goal-tracking platform that uses monetary pledges to keep you motivated. Stay accountable and hit your targets with real financial incentives.
- [Boxhero](https://composio.dev/toolkits/boxhero) - Boxhero is a cloud-based inventory management platform for SMBs, offering real-time updates, barcode scanning, and team collaboration. It helps businesses streamline stock tracking and analytics for smarter inventory decisions.
- [Breathe HR](https://composio.dev/toolkits/breathehr) - Breathe HR is cloud-based HR software for SMEs to manage employee data, absences, and performance. It simplifies HR admin, making it easy to keep employee records accurate and up to date.
- [Breeze](https://composio.dev/toolkits/breeze) - Breeze is a project management platform designed to help teams plan, track, and collaborate on projects. It streamlines workflows and keeps everyone on the same page.
- [Bugherd](https://composio.dev/toolkits/bugherd) - Bugherd is a visual feedback and bug tracking tool for websites. It helps teams and clients report website issues directly on live sites for faster fixes.
- [Canny](https://composio.dev/toolkits/canny) - Canny is a platform for managing customer feedback and feature requests. It helps teams prioritize product decisions based on real user insights.
- [Chmeetings](https://composio.dev/toolkits/chmeetings) - Chmeetings is a church management platform for events, members, donations, and volunteers. It streamlines church operations and improves community engagement.
- [ClickSend](https://composio.dev/toolkits/clicksend) - ClickSend is a cloud-based SMS and email marketing platform for businesses. It streamlines communication by enabling quick message delivery and contact management.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Notion MCP?

With a standalone Notion MCP server, the agents and LLMs can only access a fixed set of Notion tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Notion and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with Antigravity?

Yes, you can. Antigravity fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Notion tools.

### Can I manage the permissions and scopes for Notion while using Tool Router?

Yes, absolutely. You can configure which Notion scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Notion data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)