Skip to main content
Glama

getCardContent

Extract and process content from Heptabase backups using identified card IDs. Supports raw, markdown, and JSON formats for flexible data integration and analysis.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cardIdYes
formatNomarkdown

Implementation Reference

  • The core implementation of the getCardContent tool handler. Fetches card data, processes content based on format (raw, markdown, json), and returns as MCP resource.
    export async function getCardContentHandler(
      params: z.infer<typeof getCardContentSchema>,
      dataService: HeptabaseDataService
    ) {
      const result = await dataService.getCard(params.cardId);
      const card = result.card;
      
      if (!card) {
        throw new Error('Card not found');
      }
      
      let content: string;
      let mimeType: string = 'text/plain';
      
      switch (params.format) {
        case 'raw':
          content = card.content;
          mimeType = 'text/plain';
          break;
          
        case 'json':
          const cardData = {
            id: card.id,
            title: card.title,
            content: JSON.parse(card.content),
            createdTime: card.createdTime,
            lastEditedTime: card.lastEditedTime,
            instances: result.instances.length
          };
          content = JSON.stringify(cardData, null, 2);
          mimeType = 'application/json';
          break;
          
        case 'markdown':
        default:
          content = `# ${card.title || 'Untitled'}\n\n`;
          content += parseHeptabaseContentToMarkdown(card.content);
          content += `\n\n---\n`;
          content += `Created: ${card.createdTime}\n`;
          content += `Last edited: ${card.lastEditedTime}\n`;
          content += `Card ID: ${card.id}\n`;
          if (result.instances.length > 0) {
            content += `\nAppears on ${result.instances.length} whiteboard(s)\n`;
          }
          mimeType = 'text/markdown';
          break;
      }
      
      return {
        content: [{
          type: 'resource',
          resource: {
            uri: `heptabase://card/${card.id}`,
            mimeType,
            text: content
          }
        }]
      };
    }
  • Zod input schema for the getCardContent tool, defining cardId and optional format parameters.
    export const getCardContentSchema = z.object({
      cardId: z.string(),
      format: z.enum(['raw', 'markdown', 'json']).default('markdown')
    });
  • src/server.ts:587-616 (registration)
    Registration of the getCardContent tool on the MCP server. Defines schema, creates a wrapper handler that dynamically imports and calls the core implementation, and registers with this.server.tool.
    // getCardContent - returns full card content as resource to bypass text limits
    const getCardContentSchema = z.object({
      cardId: z.string(),
      format: z.enum(['raw', 'markdown', 'json']).default('markdown')
    });
    
    this.tools.getCardContent = {
      inputSchema: getCardContentSchema,
      handler: async (params) => {
        try {
          await this.ensureDataServiceInitialized();
          
          const handler = await import('./tools/getCardContent');
          return handler.getCardContentHandler(params, this.dataService!);
        } catch (error) {
          console.error('Error in getCardContent:', error);
          const errorMessage = error instanceof Error ? error.message : 'Unknown error';
          return {
            content: [{
              type: 'text',
              text: `Error: ${errorMessage}`
            }]
          };
        }
      }
    };
    
    this.server.tool('getCardContent', getCardContentSchema.shape, async (params) => {
      return this.tools.getCardContent.handler(params);
    });
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/LarryStanley/heptabse-mcp'

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