Creates a new Notion database with the specified properties. Use this tool when you need to create a new database that doesn't exist yet. The database schema is defined through the "properties" object. If no title property is provided, one will be automatically added with the name "Name". Each pr...
Part of the Notion MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use notion-create-database to create or modify resources in Notion. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call notion-create-database repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Notion.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
notion-create-database:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Notion policy for all 24 tools.
Agents calling write-class tools like notion-create-database have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Creates a new Notion database with the specified properties. Use this tool when you need to create a new database that doesn't exist yet. The database schema is defined through the "properties" object. If no title property is provided, one will be automatically added with the name "Name". Each property should include a type and may have additional configuration based on the property type. Common property types: - title: The main property (required, cannot be deleted) - rich_text: Multi-line text - number: Numeric values with optional formatting - select: Single choice from options - multi_select: Multiple choices from options - date: Date with optional time - people: User references - checkbox: Boolean values - url: Web links - email: Email addresses - phone_number: Phone numbers - formula: Calculated values based on other properties - relation: Links to pages in another database - rollup: Aggregated values from related pages The tool returns a rendered Markdown representation of the created database including its structure, data source configuration with full schema details, and SQLite table definition. This provides complete visibility into the database that was created. Examples of creating databases: 1. Create a minimal database with auto-added title property: { "properties": {} } 2. Create a task database under a page: { "parent": {"page_id": "f336d0bc-b841-465b-8045-024475c079dd"}, "title": [{"text": {"content": "Project Tasks"}}], "properties": { "Status": { "type": "select", "select": { "options": [ {"name": "To Do", "color": "red"}, {"name": "In Progress", "color": "yellow"}, {"name": "Done", "color": "green"} ] } }, "Priority": { "type": "select", "select": { "options": [ {"name": "High", "color": "red"}, {"name": "Medium", "color": "yellow"}, {"name": "Low", "color": "green"} ] } }, "Due Date": {"type": "date", "date": {}}, "Assignee": {"type": "people", "people": {}} } } 3. Create a workspace-level database with various property types: { "title": [{"text": {"content": "Company Directory"}}], "properties": { "Name": {"type": "title", "title": {}}, "Email": {"type": "email", "email": {}}, "Phone": {"type": "phone_number", "phone_number": {}}, "Department": { "type": "select", "select": { "options": [ {"name": "Engineering", "color": "blue"}, {"name": "Sales", "color": "green"}, {"name": "Marketing", "color": "purple"} ] } }, "Start Date": {"type": "date", "date": {}}, "Is Active": {"type": "checkbox", "checkbox": {}}, "Notes": {"type": "rich_text", "rich_text": {}} } } 4. Create a database with relations (assuming target database exists): { "title": [{"text": {"content": "Tasks"}}], "properties": { "Project": { "type": "relation", "relation": { "database_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890", "type": "single_property", "single_property": {} } } } }. It is categorised as a Write tool in the Notion MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for notion-create-database. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Notion MCP server.
notion-create-database is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the notion-create-database rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for notion-create-database. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
notion-create-database is provided by the Notion MCP server (@notion-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept