Skip to main content
Glama
SAhmadUmass

Notion MCP Server

by SAhmadUmass

get-page

Retrieve specific page data from Notion workspaces by providing the page ID. Enables Claude and other LLMs to access and interact with Notion content programmatically.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageIdYes

Implementation Reference

  • The main handler function for the 'get-page' tool. It retrieves a Notion page by ID using notion.pages.retrieve, fetches its child blocks with notion.blocks.children.list, extracts and formats the content from various block types (paragraphs, headings, lists), extracts the page title from properties, and returns markdown-formatted content or an error.
    async ({ pageId }) => {
      try {
        // Get the page
        const page = await notion.pages.retrieve({ page_id: pageId });
        
        // Get page blocks (content)
        const blocks = await notion.blocks.children.list({ block_id: pageId });
        
        // Extract text from blocks
        const content = blocks.results.map((block: any) => {
          if (block.type === 'paragraph') {
            return block.paragraph.rich_text.map((text: any) => text.plain_text).join('');
          }
          if (block.type === 'heading_1') {
            return `# ${block.heading_1.rich_text.map((text: any) => text.plain_text).join('')}`;
          }
          if (block.type === 'heading_2') {
            return `## ${block.heading_2.rich_text.map((text: any) => text.plain_text).join('')}`;
          }
          if (block.type === 'heading_3') {
            return `### ${block.heading_3.rich_text.map((text: any) => text.plain_text).join('')}`;
          }
          if (block.type === 'bulleted_list_item') {
            return `• ${block.bulleted_list_item.rich_text.map((text: any) => text.plain_text).join('')}`;
          }
          if (block.type === 'numbered_list_item') {
            return `1. ${block.numbered_list_item.rich_text.map((text: any) => text.plain_text).join('')}`;
          }
          return '';
        }).filter(Boolean).join('\n\n');
        
        // Safely extract title from page
        let titleText = 'Untitled';
        
        // Type assertion to access properties as any
        const pageAny = page as any;
        if (pageAny.properties) {
          // Find the first property that's a title
          const titleProp = Object.values(pageAny.properties).find(
            (prop: any) => prop.type === 'title'
          ) as any;
          
          if (titleProp?.title?.[0]?.plain_text) {
            titleText = titleProp.title[0].plain_text;
          }
        }
        
        return {
          content: [{
            type: "text",
            text: `# ${titleText}\n\n${content}`
          }]
        };
      } catch (error: any) {
        return {
          content: [{
            type: "text",
            text: `Error retrieving page: ${error.message}`
          }],
          isError: true
        };
      }
    }
  • src/index.ts:95-161 (registration)
    Registration of the 'get-page' tool using server.tool, specifying the name, input schema { pageId: z.string() }, and the handler function.
    server.tool(
      "get-page",
      { pageId: z.string() },
      async ({ pageId }) => {
        try {
          // Get the page
          const page = await notion.pages.retrieve({ page_id: pageId });
          
          // Get page blocks (content)
          const blocks = await notion.blocks.children.list({ block_id: pageId });
          
          // Extract text from blocks
          const content = blocks.results.map((block: any) => {
            if (block.type === 'paragraph') {
              return block.paragraph.rich_text.map((text: any) => text.plain_text).join('');
            }
            if (block.type === 'heading_1') {
              return `# ${block.heading_1.rich_text.map((text: any) => text.plain_text).join('')}`;
            }
            if (block.type === 'heading_2') {
              return `## ${block.heading_2.rich_text.map((text: any) => text.plain_text).join('')}`;
            }
            if (block.type === 'heading_3') {
              return `### ${block.heading_3.rich_text.map((text: any) => text.plain_text).join('')}`;
            }
            if (block.type === 'bulleted_list_item') {
              return `• ${block.bulleted_list_item.rich_text.map((text: any) => text.plain_text).join('')}`;
            }
            if (block.type === 'numbered_list_item') {
              return `1. ${block.numbered_list_item.rich_text.map((text: any) => text.plain_text).join('')}`;
            }
            return '';
          }).filter(Boolean).join('\n\n');
          
          // Safely extract title from page
          let titleText = 'Untitled';
          
          // Type assertion to access properties as any
          const pageAny = page as any;
          if (pageAny.properties) {
            // Find the first property that's a title
            const titleProp = Object.values(pageAny.properties).find(
              (prop: any) => prop.type === 'title'
            ) as any;
            
            if (titleProp?.title?.[0]?.plain_text) {
              titleText = titleProp.title[0].plain_text;
            }
          }
          
          return {
            content: [{
              type: "text",
              text: `# ${titleText}\n\n${content}`
            }]
          };
        } catch (error: any) {
          return {
            content: [{
              type: "text",
              text: `Error retrieving page: ${error.message}`
            }],
            isError: true
          };
        }
      }
    );
  • Input schema for the tool: requires a 'pageId' string parameter.
    { pageId: z.string() },
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