Skip to main content
Glama
SAhmadUmass

Notion MCP Server

by SAhmadUmass

query-database

Retrieve and organize data from Notion databases by querying with filters and sorting options. Integrates with the Notion MCP Server to manage and extract information efficiently.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
databaseIdYes
filterNo
sortNo

Implementation Reference

  • src/index.ts:325-417 (registration)
    Registration of the 'query-database' tool using server.tool(), including inline schema and handler function.
    server.tool(
      "query-database",
      { 
        databaseId: z.string(),
        filter: z.any().optional(),
        sort: z.any().optional()
      },
      async ({ databaseId, filter, sort }) => {
        try {
          // Prepare query parameters
          const queryParams: any = {
            database_id: databaseId
          };
          
          // Add filter if provided
          if (filter) {
            queryParams.filter = filter;
          }
          
          // Add sort if provided
          if (sort) {
            queryParams.sorts = sort;
          }
          
          // Query the database
          const response = await notion.databases.query(queryParams);
          
          // Format the results
          const formattedResults = response.results.map((page: any) => {
            // Extract properties in a more readable format
            const formattedProperties: any = {};
            
            Object.entries(page.properties).forEach(([key, value]: [string, any]) => {
              // Handle different property types
              switch (value.type) {
                case 'title':
                  formattedProperties[key] = value.title.map((t: any) => t.plain_text).join('');
                  break;
                case 'rich_text':
                  formattedProperties[key] = value.rich_text.map((t: any) => t.plain_text).join('');
                  break;
                case 'number':
                  formattedProperties[key] = value.number;
                  break;
                case 'select':
                  formattedProperties[key] = value.select?.name || null;
                  break;
                case 'multi_select':
                  formattedProperties[key] = value.multi_select.map((s: any) => s.name);
                  break;
                case 'date':
                  formattedProperties[key] = value.date?.start || null;
                  break;
                case 'checkbox':
                  formattedProperties[key] = value.checkbox;
                  break;
                case 'url':
                  formattedProperties[key] = value.url;
                  break;
                case 'email':
                  formattedProperties[key] = value.email;
                  break;
                case 'phone_number':
                  formattedProperties[key] = value.phone_number;
                  break;
                default:
                  formattedProperties[key] = 'Unsupported property type: ' + value.type;
              }
            });
            
            return {
              id: page.id,
              properties: formattedProperties
            };
          });
          
          return {
            content: [{
              type: "text",
              text: JSON.stringify(formattedResults, null, 2)
            }]
          };
        } catch (error: any) {
          return {
            content: [{
              type: "text",
              text: `Error querying database: ${error.message}`
            }],
            isError: true
          };
        }
      }
    );
  • Input schema using Zod: databaseId (string, required), filter (any, optional), sort (any, optional).
    { 
      databaseId: z.string(),
      filter: z.any().optional(),
      sort: z.any().optional()
    },
  • Handler function that queries the Notion database with the given databaseId, applies optional filter and sort parameters, processes and formats the results by converting various Notion property types to simple JSON values, and returns the formatted results as a text content block or an error message.
    async ({ databaseId, filter, sort }) => {
      try {
        // Prepare query parameters
        const queryParams: any = {
          database_id: databaseId
        };
        
        // Add filter if provided
        if (filter) {
          queryParams.filter = filter;
        }
        
        // Add sort if provided
        if (sort) {
          queryParams.sorts = sort;
        }
        
        // Query the database
        const response = await notion.databases.query(queryParams);
        
        // Format the results
        const formattedResults = response.results.map((page: any) => {
          // Extract properties in a more readable format
          const formattedProperties: any = {};
          
          Object.entries(page.properties).forEach(([key, value]: [string, any]) => {
            // Handle different property types
            switch (value.type) {
              case 'title':
                formattedProperties[key] = value.title.map((t: any) => t.plain_text).join('');
                break;
              case 'rich_text':
                formattedProperties[key] = value.rich_text.map((t: any) => t.plain_text).join('');
                break;
              case 'number':
                formattedProperties[key] = value.number;
                break;
              case 'select':
                formattedProperties[key] = value.select?.name || null;
                break;
              case 'multi_select':
                formattedProperties[key] = value.multi_select.map((s: any) => s.name);
                break;
              case 'date':
                formattedProperties[key] = value.date?.start || null;
                break;
              case 'checkbox':
                formattedProperties[key] = value.checkbox;
                break;
              case 'url':
                formattedProperties[key] = value.url;
                break;
              case 'email':
                formattedProperties[key] = value.email;
                break;
              case 'phone_number':
                formattedProperties[key] = value.phone_number;
                break;
              default:
                formattedProperties[key] = 'Unsupported property type: ' + value.type;
            }
          });
          
          return {
            id: page.id,
            properties: formattedProperties
          };
        });
        
        return {
          content: [{
            type: "text",
            text: JSON.stringify(formattedResults, null, 2)
          }]
        };
      } catch (error: any) {
        return {
          content: [{
            type: "text",
            text: `Error querying database: ${error.message}`
          }],
          isError: true
        };
      }
    }
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

Related 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/SAhmadUmass/notion-mcp-server'

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