Skip to main content
Glama

getCard

Retrieve and export data from Heptabase cards in JSON, Markdown, or HTML formats by specifying the card ID. The tool supports including related data for comprehensive insights.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cardIdYes
formatNo
includeRelatedNo

Implementation Reference

  • Main handler function for the getCard tool. Initializes data service if needed, calls dataService.getCard, and formats the output as a resource in JSON, Markdown, or HTML based on the format parameter. Handles related whiteboards and connections if requested.
    this.tools.getCard = {
      inputSchema: getCardSchema,
      handler: async (params) => {
        try {
          await this.ensureDataServiceInitialized();
    
          const result = await this.dataService!.getCard(params.cardId);
          const format = params.format || 'json';
          
          let text = '';
          
          if (format === 'markdown') {
            text = `# ${result.card.title || 'Untitled'}\n\n`;
            text += parseHeptabaseContentToMarkdown(result.card.content);
            
            if (params.includeRelated) {
              const instances = result.instances;
              if (instances.length > 0) {
                text += '\n## Appears on whiteboards:\n';
                for (const instance of instances) {
                  const wb = await this.dataService!.getWhiteboard(instance.whiteboardId);
                  text += `- ${wb.whiteboard.name}\n`;
                }
              }
              
              const connections = await this.dataService!.getConnections(params.cardId);
              if (connections.length > 0) {
                text += `\n## Related connections: ${connections.length}\n`;
              }
            }
            
            // Return as resource to bypass text size limits
            return {
              content: [{
                type: 'resource',
                resource: {
                  uri: `heptabase://card/${result.card.id}`,
                  mimeType: 'text/markdown',
                  text
                }
              }]
            };
          } else if (format === 'html') {
            text = `<h1>${result.card.title || 'Untitled'}</h1>\n`;
            text += parseHeptabaseContentToHtml(result.card.content);
            
            if (params.includeRelated) {
              const instances = result.instances;
              if (instances.length > 0) {
                text += '<h2>Appears on whiteboards:</h2><ul>';
                for (const instance of instances) {
                  const wb = await this.dataService!.getWhiteboard(instance.whiteboardId);
                  text += `<li>${wb.whiteboard.name}</li>`;
                }
                text += '</ul>';
              }
            }
            
            // Return as resource to bypass text size limits
            return {
              content: [{
                type: 'resource',
                resource: {
                  uri: `heptabase://card/${result.card.id}`,
                  mimeType: 'text/html',
                  text
                }
              }]
            };
          } else {
            // Default JSON format - return full card data as resource
            const cardData: any = {
              id: result.card.id,
              title: result.card.title,
              content: JSON.parse(result.card.content),
              createdTime: result.card.createdTime,
              lastEditedTime: result.card.lastEditedTime,
              instances: result.instances,
              isTrashed: result.card.isTrashed
          };
          
          if (params.includeRelated) {
            const connections = await this.dataService!.getConnections(params.cardId);
            cardData.connections = connections;
          }
          
          return {
            content: [{
              type: 'resource',
              resource: {
                uri: `heptabase://card/${result.card.id}`,
                mimeType: 'application/json',
                text: JSON.stringify(cardData, null, 2)
              }
            }]
          };
        }
        } catch (error) {
          console.error('Error in getCard:', error);
          const errorMessage = error instanceof Error ? error.message : 'Unknown error';
          return {
            content: [{
              type: 'text',
              text: `Error: ${errorMessage}`
            }]
          };
        }
      }
    };
  • Zod input schema for the getCard tool defining required cardId and optional format (json/markdown/html) and includeRelated flag.
    const getCardSchema = z.object({
      cardId: z.string(),
      format: z.enum(['json', 'markdown', 'html']).optional(),
      includeRelated: z.boolean().optional()
    });
  • src/server.ts:583-585 (registration)
    Registers the getCard tool with the MCP server, delegating to the defined handler.
    this.server.tool('getCard', getCardSchema.shape, async (params) => {
      return this.tools.getCard.handler(params);
    });
  • Helper method in HeptabaseDataService that retrieves the card by ID and all its instances across whiteboards from the loaded backup data.
    async getCard(cardId: string): Promise<CardResult> {
      const card = this.data.cards[cardId];
      if (!card) {
        throw new Error('Card not found');
      }
    
      const instances = Object.values(this.data.cardInstances).filter(
        instance => instance.cardId === cardId
      );
    
      return { card, instances };
    }
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