Skip to main content
Glama
BangyiZhang

Xmind Generator MCP Server

by BangyiZhang

generate-mind-map

Create structured XMind mind maps with hierarchical topic structures, including notes, labels, markers, and relationships, for effective visual organization and planning.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filenameYesThe filename for the XMind file (without path or extension)
outputPathNoOptional custom output path for the XMind file. If not provided, the file will be created in the temporary directory.
relationshipsNoOptional array of relationships between topics
titleYesThe title of the mind map (root topic)
topicsYesArray of topics to include in the mind map

Implementation Reference

  • The core handler function that executes the 'generate-mind-map' tool. It checks for dependencies, sanitizes inputs, builds the mind map structure recursively using xmind-generator library, writes the .xmind file to disk, optionally opens it, and returns success/error messages.
    async (params: GenerateMindMapParams) => {
      try {
        // Check if xmind-generator is available
        if (!xmindGeneratorInstalled) {
          return {
            content: [{
              type: 'text',
              text: 'The xmind-generator package is not properly installed. Please run: npm install xmind-generator@1.0.1 --save in the project directory.'
            }],
            isError: true
          };
        }
    
        // Import xmind-generator using the require function
        const xmindGenerator = require('xmind-generator');
        const { Topic, RootTopic, Workbook, writeLocalFile } = xmindGenerator;
    
        // Define the output path using the required filename parameter
        // Sanitize the filename to ensure it's valid for both Windows and Unix systems
        // Only filter out truly invalid characters: \ / : * ? " < > |
        const sanitizedFilename = params.filename.replace(/[\\/:*?"<>|]/g, '-');
    
        // Get output path with priority:
        // 1. Parameter provided in the tool call (params.outputPath)
        // 2. Environment variable (process.env.outputPath)
        // 3. Default temporary directory (TEMP_DIR)
        const baseOutputPath = params.outputPath || process.env.outputPath || TEMP_DIR;
    
        // If baseOutputPath is a directory, append the filename
        // If it's a file path (has extension), use it directly
        let outputPath: string;
        if (baseOutputPath.endsWith('.xmind')) {
          outputPath = baseOutputPath;
        } else {
          // Assume it's a directory path
          outputPath = path.join(baseOutputPath, `${sanitizedFilename}.xmind`);
        }
    
        // Ensure the output directory exists
        const outputDir = path.dirname(outputPath);
        if (!fs.existsSync(outputDir)) {
          fs.mkdirSync(outputDir, { recursive: true });
        }
    
        // Create root topic
        const rootTopic = RootTopic(params.title);
    
        // Add relationships if provided
        if (params.relationships && params.relationships.length > 0) {
          rootTopic.relationships(params.relationships.map(rel => {
            return xmindGenerator.Relationship(rel.title, { from: rel.from, to: rel.to });
          }));
        }
    
        // Helper function to build topics recursively
        function buildTopic(topicData: TopicData) {
          const topic = Topic(topicData.title);
    
          if (topicData.ref) {
            topic.ref(topicData.ref);
          }
    
          if (topicData.note) {
            topic.note(topicData.note);
          }
    
          if (topicData.labels && topicData.labels.length > 0) {
            topic.labels(topicData.labels);
          }
    
          if (topicData.markers && topicData.markers.length > 0) {
            // Convert marker strings to Marker objects
            const markers = topicData.markers.map((markerStr: string) => {
              const [category, name] = markerStr.split('.');
              return xmindGenerator.Marker[category]?.[name] || markerStr;
            });
            topic.markers(markers);
          }
    
          if (topicData.children && topicData.children.length > 0) {
            const children = topicData.children.map((child: TopicData) => buildTopic(child));
            topic.children(children);
          }
    
          return topic;
        }
    
        // Build children
        if (params.topics && params.topics.length > 0) {
          const children = params.topics.map((topic: TopicData) => buildTopic(topic));
          rootTopic.children(children);
        }
    
        // Create workbook
        const workbook = Workbook(rootTopic);
    
        // Write to file
        writeLocalFile(workbook, outputPath);
    
        // Check if we should automatically open the generated file
        // Default to true if environment variable is not set
        const autoOpenFile = process.env.autoOpenFile !== 'false';
    
        if (autoOpenFile) {
          // Open the generated file with default application
          const platform = process.platform;
          const openCommand = platform === 'win32' ? 'start' : platform === 'darwin' ? 'open' : 'xdg-open';
    
          exec(`${openCommand} "${outputPath}"`, (error) => {
            if (error) {
              console.error('Error opening file:', error);
            }
          });
        }
    
        return {
          content: [{
            type: 'text',
            text: `Mind map successfully generated and saved to: ${outputPath}`
          }]
        };
      } catch (error) {
        console.error('Error generating mind map:', error);
        return {
          content: [{
            type: 'text',
            text: `Error generating mind map: ${error instanceof Error ? error.message : String(error)}`
          }],
          isError: true
        };
      }
    }
  • Zod schemas defining the input structure for the generate-mind-map tool, including recursive TopicSchema, RelationshipSchema, and top-level GenerateMindMapSchema with descriptions for MCP tool schema.
    const RelationshipSchema = z.object({
      title: z.string().describe('The title of the relationship'),
      from: z.string().describe('The reference ID of the source topic'),
      to: z.string().describe('The reference ID of the target topic')
    });
    
    const TopicSchema: z.ZodType<any> = z.lazy(() => z.object({
      title: z.string().describe('The title of the topic'),
      ref: z.string().optional().describe('Optional reference ID for the topic'),
      note: z.string().optional().describe('Optional note for the topic'),
      labels: z.array(z.string()).optional().describe('Optional array of labels for the topic'),
      markers: z.array(z.string()).optional().describe('Optional array of markers for the topic (format: "Category.name", e.g., "Arrow.refresh")'),
      children: z.array(TopicSchema).optional().describe('Optional array of child topics'),
      relationships: z.array(RelationshipSchema).optional().describe('Optional array of relationships for the topic')
    }));
    
    const GenerateMindMapSchema = z.object({
      title: z.string().describe('The title of the mind map (root topic)'),
      topics: z.array(TopicSchema).describe('Array of topics to include in the mind map'),
      filename: z.string().describe('The filename for the XMind file (without path or extension)'),
      outputPath: z.string().optional().describe('Optional custom output path for the XMind file. If not provided, the file will be created in the temporary directory.'),
      relationships: z.array(RelationshipSchema).optional().describe('Optional array of relationships between topics')
    });
    
    type TopicData = z.infer<typeof TopicSchema>;
    type GenerateMindMapParams = z.infer<typeof GenerateMindMapSchema>;
  • src/index.ts:73-76 (registration)
    Registration of the 'generate-mind-map' tool on the MCP server using server.tool() with name, schema, and inline handler function.
    // Register the generate-mind-map tool
    server.tool(
      'generate-mind-map',
      GenerateMindMapSchema.shape,
  • Recursive helper function buildTopic used within the handler to construct Topic objects from input data, supporting nested children, notes, labels, markers, and refs.
    function buildTopic(topicData: TopicData) {
      const topic = Topic(topicData.title);
    
      if (topicData.ref) {
        topic.ref(topicData.ref);
      }
    
      if (topicData.note) {
        topic.note(topicData.note);
      }
    
      if (topicData.labels && topicData.labels.length > 0) {
        topic.labels(topicData.labels);
      }
    
      if (topicData.markers && topicData.markers.length > 0) {
        // Convert marker strings to Marker objects
        const markers = topicData.markers.map((markerStr: string) => {
          const [category, name] = markerStr.split('.');
          return xmindGenerator.Marker[category]?.[name] || markerStr;
        });
        topic.markers(markers);
      }
    
      if (topicData.children && topicData.children.length > 0) {
        const children = topicData.children.map((child: TopicData) => buildTopic(child));
        topic.children(children);
      }
    
      return topic;
    }
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/BangyiZhang/xmind-generator-mcp'

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