Skip to main content
Glama

getWhiteboard

Retrieve and analyze Heptabase whiteboard data by specifying a whiteboard ID, with options to include cards, connections, and depth of analysis for enhanced insights.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
depthNo
includeCardsNo
includeConnectionsNo
whiteboardIdYes

Implementation Reference

  • The primary handler for the 'getWhiteboard' MCP tool. Ensures data service initialization, fetches whiteboard data with options, generates a formatted text summary of the whiteboard, cards, and connections, and handles errors gracefully.
    this.tools.getWhiteboard = {
      inputSchema: getWhiteboardSchema,
      handler: async (params) => {
        try {
          await this.ensureDataServiceInitialized();
    
          const options = {
            includeCards: params.includeCards || false,
            includeConnections: params.includeConnections || false,
            depth: params.depth
          };
    
          const result = await this.dataService!.getWhiteboard(params.whiteboardId, options);
          
          let text = `Whiteboard: ${result.whiteboard.name} (ID: ${result.whiteboard.id})\n`;
          text += `Created: ${result.whiteboard.createdTime}\n`;
          text += `Last edited: ${result.whiteboard.lastEditedTime}\n`;
          
          if (result.cards) {
            text += `\nCards: ${result.cards.length}\n`;
            result.cards.forEach(card => {
              text += `- ${card.title || 'Untitled'} (ID: ${card.id})\n`;
            });
          }
          
          if (result.connections) {
            text += `\nConnections: ${result.connections.length}\n`;
          }
    
          return {
            content: [{
              type: 'text',
              text
            }]
          };
        } catch (error) {
          console.error('Error in getWhiteboard:', error);
          const errorMessage = error instanceof Error ? error.message : 'Unknown error';
          return {
            content: [{
              type: 'text',
              text: `Error: ${errorMessage}`
            }]
          };
        }
      }
    };
  • Zod input schema validation for the getWhiteboard tool, requiring whiteboardId and optionally including cards, connections, and depth.
    const getWhiteboardSchema = z.object({
      whiteboardId: z.string(),
      includeCards: z.boolean().optional(),
      includeConnections: z.boolean().optional(),
      depth: z.number().optional()
    });
  • src/server.ts:462-464 (registration)
    MCP server registration of the getWhiteboard tool, linking the schema and handler.
    this.server.tool('getWhiteboard', getWhiteboardSchema.shape, async (params) => {
      return this.tools.getWhiteboard.handler(params);
    });
  • Helper method in HeptabaseDataService that retrieves a whiteboard by ID, optionally populating associated cards and connections from the loaded data structures.
    async getWhiteboard(
      whiteboardId: string,
      options: { includeCards?: boolean; includeConnections?: boolean } = {}
    ): Promise<WhiteboardResult> {
      const whiteboard = this.data.whiteboards[whiteboardId];
      if (!whiteboard) {
        throw new Error('Whiteboard not found');
      }
    
      const result: WhiteboardResult = { whiteboard };
    
      if (options.includeCards) {
        const instances = Object.values(this.data.cardInstances).filter(
          instance => instance.whiteboardId === whiteboardId
        );
        const cardIds = instances.map(instance => instance.cardId);
        result.cards = cardIds.map(id => this.data.cards[id]).filter(Boolean);
      }
    
      if (options.includeConnections) {
        result.connections = Object.values(this.data.connections).filter(
          connection => connection.whiteboardId === whiteboardId
        );
      }
    
      return result;
    }
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/heptabase-mcp'

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