Skip to main content
Glama
0xjcf
by 0xjcf

visualize-code-structure

Generate visual diagrams of code structure to analyze classes, methods, and attributes in repositories or files using ASCII, Mermaid, or DOT formats.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
repositoryUrlNo
filePathNo
fileContentNo
showMethodsNo
showAttributesNo
formatNomermaid

Implementation Reference

  • Handler function that invokes generateCodeStructureVisualization with parameters and returns MCP-formatted response or error.
    async ({ repositoryUrl, filePath, fileContent, showMethods, showAttributes, format }) => {
      try {
        const visualization = await generateCodeStructureVisualization({
          repositoryUrl,
          filePath,
          fileContent,
          showMethods,
          showAttributes,
          format
        });
        
        return {
          content: [{
            type: "text",
            text: visualization,
            _metadata: format === "mermaid" ? { format: "mermaid" } : undefined
          }]
        };
      } catch (error) {
        return {
          content: [{
            type: "text",
            text: `Error generating visualization: ${(error as Error).message}`
          }],
          isError: true
        };
      }
    }
  • Zod input schema defining optional repositoryUrl/filePath/fileContent, booleans for showing methods/attributes, and format enum.
    {
      repositoryUrl: z.string().optional(),
      filePath: z.string().optional(),
      fileContent: z.string().optional(),
      showMethods: z.boolean().default(true),
      showAttributes: z.boolean().default(true),
      format: z.enum(["ascii", "mermaid", "dot"]).default("mermaid")
    },
  • Registration of the 'visualize-code-structure' tool on the MCP server within registerVisualizationFeatures, including schema and handler.
    server.tool(
      "visualize-code-structure",
      {
        repositoryUrl: z.string().optional(),
        filePath: z.string().optional(),
        fileContent: z.string().optional(),
        showMethods: z.boolean().default(true),
        showAttributes: z.boolean().default(true),
        format: z.enum(["ascii", "mermaid", "dot"]).default("mermaid")
      },
      async ({ repositoryUrl, filePath, fileContent, showMethods, showAttributes, format }) => {
        try {
          const visualization = await generateCodeStructureVisualization({
            repositoryUrl,
            filePath,
            fileContent,
            showMethods,
            showAttributes,
            format
          });
          
          return {
            content: [{
              type: "text",
              text: visualization,
              _metadata: format === "mermaid" ? { format: "mermaid" } : undefined
            }]
          };
        } catch (error) {
          return {
            content: [{
              type: "text",
              text: `Error generating visualization: ${(error as Error).message}`
            }],
            isError: true
          };
        }
      }
    );
  • Core helper function that fetches/uses code content, analyzes structure with analyzeCode, and generates visualization in ascii/mermaid/dot format.
    export async function generateCodeStructureVisualization(options: {
      repositoryUrl?: string;
      filePath?: string;
      fileContent?: string;
      showMethods: boolean;
      showAttributes: boolean;
      format: string;
    }): Promise<string> {
      const { repositoryUrl, filePath, fileContent, showMethods, showAttributes, format } = options;
      
      // Get the code to analyze
      let code: string;
      let language: string = "";
      
      if (repositoryUrl) {
        const repoPath = await getRepository(repositoryUrl);
        
        if (!filePath) {
          throw new Error("filePath must be provided when repositoryUrl is specified");
        }
        
        const fullPath = path.join(repoPath, filePath);
        code = fs.readFileSync(fullPath, 'utf8');
        language = path.extname(filePath).slice(1);
      } else if (fileContent) {
        code = fileContent;
      } else {
        throw new Error("Either repositoryUrl with filePath, or fileContent must be provided");
      }
      
      // Analyze the code structure
      const analysis = analyzeCode(code, language);
      
      // Generate the visualization in the requested format
      switch (format) {
        case "mermaid":
          return generateMermaidClassDiagram(analysis, { showMethods, showAttributes });
        case "dot":
          return generateDotClassDiagram(analysis, { showMethods, showAttributes });
        case "ascii":
          return generateAsciiClassDiagram(analysis, { showMethods, showAttributes });
        default:
          throw new Error(`Unsupported format: ${format}`);
      }
    }
  • Helper function to generate Mermaid class diagram from code analysis, showing classes, methods, attributes (placeholders).
    function generateMermaidClassDiagram(analysis: any, options: { showMethods: boolean, showAttributes: boolean }): string {
      const { classes, functions } = analysis;
      const { showMethods, showAttributes } = options;
      
      let mermaid = "classDiagram\n";
      
      // Add classes
      for (const className of classes) {
        mermaid += `  class ${className} {\n`;
        
        // Add attributes and methods if available and requested
        if (showAttributes) {
          mermaid += `    +attribute: type\n`;  // Placeholder - would need actual analysis
        }
        
        if (showMethods) {
          mermaid += `    +method()\n`;  // Placeholder - would need actual analysis
        }
        
        mermaid += "  }\n";
      }
      
      // Add standalone functions if no classes
      if (classes.length === 0 && functions.length > 0) {
        mermaid += `  class Functions {\n`;
        
        for (const func of functions) {
          mermaid += `    +${func}()\n`;
        }
        
        mermaid += "  }\n";
      }
      
      return mermaid;
    }
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

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/0xjcf/MCP_CodeAnalysis'

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