Skip to main content
Glama
SunCreation

MCP Notion Server (@suncreation)

by SunCreation

notion_query_database

Retrieve and filter data from Notion databases using queries, sorting, and pagination to extract specific information for analysis or integration.

Instructions

Query a database in Notion

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
database_idYesThe ID of the database to query.It should be a 32-character string (excluding hyphens) formatted as 8-4-4-4-12 with hyphens (-).
filterNoFilter conditions
sortsNoSort conditions
start_cursorNoPagination cursor for next page of results
page_sizeNoNumber of results per page (max 100)
formatNoSpecify the response format. 'json' returns the original data structure, 'markdown' returns a more readable format. Use 'markdown' when the user only needs to read the page and isn't planning to write or modify it. Use 'json' when the user needs to read the page with the intention of writing to or modifying it.markdown

Implementation Reference

  • Main handler for notion_query_database tool in the switch statement. Validates required arguments (database_id) and calls the NotionClientWrapper.queryDatabase method with filter, sorts, start_cursor, and page_size parameters.
    case "notion_query_database": {
      const args = request.params
        .arguments as unknown as args.QueryDatabaseArgs;
      if (!args.database_id) {
        throw new Error("Missing required argument: database_id");
      }
      response = await notionClient.queryDatabase(
        args.database_id,
        args.filter,
        args.sorts,
        args.start_cursor,
        args.page_size
      );
      break;
    }
  • Actual implementation of queryDatabase in NotionClientWrapper class. Constructs the request body with optional filter, sorts, start_cursor, and page_size, then makes a POST request to Notion's /databases/{id}/query endpoint.
    async queryDatabase(
      database_id: string,
      filter?: Record<string, any>,
      sorts?: Array<{
        property?: string;
        timestamp?: string;
        direction: "ascending" | "descending";
      }>,
      start_cursor?: string,
      page_size?: number
    ): Promise<ListResponse> {
      const body: Record<string, any> = {};
      if (filter) body.filter = filter;
      if (sorts) body.sorts = sorts;
      if (start_cursor) body.start_cursor = start_cursor;
      if (page_size) body.page_size = page_size;
    
      const response = await fetch(
        `${this.baseUrl}/databases/${database_id}/query`,
        {
          method: "POST",
          headers: this.headers,
          body: JSON.stringify(body),
        }
      );
    
      return response.json();
    }
  • Tool schema definition for notion_query_database. Defines the tool name, description, and inputSchema with properties for database_id (required), filter, sorts, start_cursor, page_size, and format parameters.
    export const queryDatabaseTool: Tool = {
      name: "notion_query_database",
      description: "Query a database in Notion",
      inputSchema: {
        type: "object",
        properties: {
          database_id: {
            type: "string",
            description: "The ID of the database to query." + commonIdDescription,
          },
          filter: {
            type: "object",
            description: "Filter conditions",
          },
          sorts: {
            type: "array",
            description: "Sort conditions",
            items: {
              type: "object",
              properties: {
                property: { type: "string" },
                timestamp: { type: "string" },
                direction: {
                  type: "string",
                  enum: ["ascending", "descending"],
                },
              },
              required: ["direction"],
            },
          },
          start_cursor: {
            type: "string",
            description: "Pagination cursor for next page of results",
          },
          page_size: {
            type: "number",
            description: "Number of results per page (max 100)",
          },
          format: formatParameter,
        },
        required: ["database_id"],
      },
    };
  • TypeScript interface defining the QueryDatabaseArgs type with types for all parameters: database_id, filter, sorts, start_cursor, page_size, and optional format field.
    export interface QueryDatabaseArgs {
      database_id: string;
      filter?: Record<string, any>;
      sorts?: Array<{
        property?: string;
        timestamp?: string;
        direction: "ascending" | "descending";
      }>;
      start_cursor?: string;
      page_size?: number;
      format?: "json" | "markdown";
    }
  • Tool registration in the ListToolsRequestSchema handler where schemas.queryDatabaseTool is added to the allTools array, making it available to MCP clients.
    schemas.queryDatabaseTool,
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but only states the basic operation. It doesn't disclose whether this is a read-only operation (implied but not stated), what permissions are needed, how pagination works, rate limits, or what the response contains. For a query tool with 6 parameters, this is insufficient behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero wasted words. It's appropriately sized for a tool with good schema documentation, though this conciseness comes at the expense of helpful context that would benefit an AI agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a query tool with 6 parameters, nested objects, no output schema, and no annotations, the description is incomplete. It doesn't explain what the tool returns, how results are structured, pagination behavior, or error conditions. The agent must rely entirely on the input schema without guidance on output expectations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds no additional parameter semantics beyond what's in the schema. The baseline score of 3 reflects adequate coverage through schema alone, though the description contributes nothing extra.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Query a database in Notion' clearly states the action (query) and resource (database), but it's vague about scope and doesn't differentiate from sibling tools like 'notion_retrieve_database' or 'notion_search'. It lacks specificity about what kind of query operation this performs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus alternatives like 'notion_retrieve_database' (which fetches metadata) or 'notion_search' (which searches across all content). The description offers no context about appropriate use cases or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SunCreation/mcp-notion-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server