Skip to main content
Glama
0xjcf
by 0xjcf

export-knowledge-graph

Extract and export a codebase's knowledge graph from a repository URL in JSON, Mermaid, DOT, or Cypher format to visualize dependencies and relationships for analysis.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
repositoryUrlYes
formatNojson

Implementation Reference

  • The handler implementation for the 'export-knowledge-graph' MCP tool. It queries the full knowledge graph for the repository and exports it in the specified format (json, mermaid, dot, cypher) using the exportKnowledgeGraph helper.
    server.tool(
      "export-knowledge-graph",
      {
        repositoryUrl: z.string(),
        format: z.enum(["json", "mermaid", "dot", "cypher"]).default("json")
      },
      async ({ repositoryUrl, format }) => {
        try {
          // First query the graph to get all nodes and relationships
          const results = await queryKnowledgeGraph({
            query: "MATCH (n)-[r]-(m) WHERE n.repository = $repositoryUrl RETURN n, r, m",
            repositoryUrl
          });
          
          // Export in requested format
          const exported = await exportKnowledgeGraph(results, format);
          
          return {
            content: [{
              type: "text",
              text: exported,
              _metadata: format === "mermaid" ? { format: "mermaid" } : undefined
            }]
          };
        } catch (error) {
          return {
            content: [{
              type: "text",
              text: `Error exporting knowledge graph: ${(error as Error).message}`
            }],
            isError: true
          };
        }
      }
    );
  • Input schema for the export-knowledge-graph tool using Zod validation.
      repositoryUrl: z.string(),
      format: z.enum(["json", "mermaid", "dot", "cypher"]).default("json")
    },
  • Registration of the export-knowledge-graph tool on the MCP server within registerKnowledgeGraphFeatures.
    // Tool to export the knowledge graph
    server.tool(
      "export-knowledge-graph",
      {
        repositoryUrl: z.string(),
        format: z.enum(["json", "mermaid", "dot", "cypher"]).default("json")
      },
      async ({ repositoryUrl, format }) => {
        try {
          // First query the graph to get all nodes and relationships
          const results = await queryKnowledgeGraph({
            query: "MATCH (n)-[r]-(m) WHERE n.repository = $repositoryUrl RETURN n, r, m",
            repositoryUrl
          });
          
          // Export in requested format
          const exported = await exportKnowledgeGraph(results, format);
          
          return {
            content: [{
              type: "text",
              text: exported,
              _metadata: format === "mermaid" ? { format: "mermaid" } : undefined
            }]
          };
        } catch (error) {
          return {
            content: [{
              type: "text",
              text: `Error exporting knowledge graph: ${(error as Error).message}`
            }],
            isError: true
          };
        }
      }
    );
  • Helper function that performs the actual export formatting, called by the tool handler. Dispatches to format-specific exporters.
    export async function exportKnowledgeGraph(results: GraphQueryResult, format: string): Promise<string> {
      const { nodes, relationships } = results;
      
      switch (format) {
        case "json":
          return JSON.stringify({ nodes, relationships }, null, 2);
        
        case "mermaid":
          return exportToMermaid(nodes, relationships);
        
        case "dot":
          return exportToDot(nodes, relationships);
        
        case "cypher":
          return exportToCypher(nodes, relationships);
        
        default:
          throw new Error(`Unsupported export format: ${format}`);
      }
    }
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