Skip to main content
Glama
0xjcf
by 0xjcf

visualize-dependencies

Generate dependency diagrams for codebases to visualize relationships between files and modules, supporting multiple output formats for analysis.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
repositoryUrlNo
filePathNo
pathNo
fileContentNo
formatNomermaid

Implementation Reference

  • Registration of the visualize-dependencies MCP tool, including input schema and the handler function.
    server.tool(
      "visualize-dependencies",
      {
        repositoryUrl: z.string().optional(),
        filePath: z.string().optional(),
        path: z.string().optional(),
        fileContent: z.string().optional(),
        format: z.enum(["ascii", "mermaid", "dot"]).default("mermaid")
      },
      async ({ repositoryUrl, filePath, path, fileContent, format }) => {
        try {
          const targetPath = path || repositoryUrl || filePath;
          
          const visualization = await generateDependencyGraph({
            repositoryUrl: targetPath,
            filePath,
            fileContent,
            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 handler logic for generating dependency graph visualizations from repositories, files, or code snippets by analyzing imports and producing Mermaid, DOT, or ASCII formats.
    export async function generateDependencyGraph(options: {
      repositoryUrl?: string;
      filePath?: string;
      fileContent?: string;
      format: string;
    }): Promise<string> {
      const { repositoryUrl, filePath, fileContent, format } = options;
      
      // Gather the dependency data
      let dependencies: Record<string, string[]> = {};
      
      if (repositoryUrl) {
        const repoPath = await getRepository(repositoryUrl);
        
        if (filePath) {
          // Analyze specific file
          const fullPath = path.join(repoPath, filePath);
          const code = fs.readFileSync(fullPath, 'utf8');
          const fileLanguage = path.extname(filePath).slice(1);
          const analysis = analyzeCode(code, fileLanguage);
          dependencies[filePath] = analysis.imports;
        } else {
          // Analyze all files in repository
          const files = listFiles(repoPath);
          dependencies = gatherDependencies(repoPath, files);
        }
      } else if (fileContent) {
        // Analyze provided code snippet
        const analysis = analyzeCode(fileContent);
        dependencies['snippet'] = analysis.imports;
      } else {
        throw new Error("Either repositoryUrl, filePath, or fileContent must be provided");
      }
      
      // Generate the visualization in the requested format
      switch (format) {
        case "mermaid":
          return generateMermaidDependencyGraph(dependencies);
        case "dot":
          return generateDotDependencyGraph(dependencies);
        case "ascii":
          return generateAsciiDependencyGraph(dependencies);
        default:
          throw new Error(`Unsupported format: ${format}`);
      }
    }
  • Input schema using Zod for validating parameters to the visualize-dependencies tool.
    {
      repositoryUrl: z.string().optional(),
      filePath: z.string().optional(),
      path: z.string().optional(),
      fileContent: z.string().optional(),
      format: z.enum(["ascii", "mermaid", "dot"]).default("mermaid")
  • Helper function to gather dependencies from all files in a repository by analyzing their code.
    function gatherDependencies(repoPath: string, files: string[]): Record<string, string[]> {
      const dependencies: Record<string, string[]> = {};
      
      for (const file of files) {
        try {
          const fullPath = path.join(repoPath, file);
          const code = fs.readFileSync(fullPath, 'utf8');
          const fileLanguage = path.extname(file).slice(1);
          const analysis = analyzeCode(code, fileLanguage);
          dependencies[file] = analysis.imports;
        } catch (error) {
          console.warn(`Error analyzing ${file}: ${(error as Error).message}`);
        }
      }
      
      return dependencies;
    }
  • Helper function to generate Mermaid format dependency graph from dependency data.
    function generateMermaidDependencyGraph(dependencies: Record<string, string[]>): string {
      let mermaid = "graph TD;\n";
      
      for (const [file, imports] of Object.entries(dependencies)) {
        const safeFile = sanitizeId(file);
        
        // Add the file node
        mermaid += `  ${safeFile}["${file}"];\n`;
        
        // Add dependencies
        for (const importItem of imports) {
          const safeImport = sanitizeId(importItem);
          mermaid += `  ${safeFile} --> ${safeImport}["${importItem}"];\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