Skip to main content
Glama

extract_code

Extract code nodes from workflows into separate files for improved editing and organization.

Instructions

Extract code nodes to separate files in workflows/nodes/ for better editing

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workflowNoSpecific workflow to extract code from (optional, extracts all if not specified)

Implementation Reference

  • ToolHandler.handleTool switch case for 'extract_code': initializes NodeManager and calls extractNodes for specific workflow or extractAllNodes for all, returning formatted text response.
    case 'extract_code':
      const codeManager = new NodeManager(this.workflowsPath);
      await codeManager.initialize();
    
      const workflowToExtract = args?.workflow as string | undefined;
    
      if (workflowToExtract) {
        const workflowPath = path.join(this.workflowsPath, 'flows', `${workflowToExtract}.json`);
        const result = await codeManager.extractNodes(workflowPath);
        return {
          content: [{
            type: 'text',
            text: result.extracted.length > 0
              ? `✅ Extracted ${result.extracted.length} code nodes from ${workflowToExtract}\n\n` +
                result.extracted.map((n: any) => `• ${n.nodeName} → ${n.filePath}`).join('\n')
              : `📭 No code nodes found in ${workflowToExtract}`
          }]
        };
      } else {
        return await codeManager.extractAllNodes();
      }
  • Input schema for 'extract_code' tool: optional 'workflow' string parameter.
    inputSchema: {
      type: 'object',
      properties: {
        workflow: {
          type: 'string',
          description: 'Specific workflow to extract code from (optional, extracts all if not specified)',
        },
      },
    },
  • Registration of 'extract_code' tool in getToolDefinitions() array, including name, description, and inputSchema.
    {
      name: 'extract_code',
      description: 'Extract code nodes to separate files in workflows/nodes/ for better editing',
      inputSchema: {
        type: 'object',
        properties: {
          workflow: {
            type: 'string',
            description: 'Specific workflow to extract code from (optional, extracts all if not specified)',
          },
        },
      },
    },
  • NodeManager.extractNodes(): core logic to parse workflow, identify extractable nodes (code, LLM prompts, SQL, templates, JSON), extract content to files in workflows/nodes/, replace with file refs in workflow, update metadata.
    async extractNodes(workflowPath: string): Promise<{
      extracted: ExtractedNode[];
      modified: boolean;
    }> {
      const content = await fs.readFile(workflowPath, 'utf-8');
      const workflow = JSON.parse(content);
      const workflowName = path.basename(workflowPath, '.json');
      
      const extracted: ExtractedNode[] = [];
      let modified = false;
    
      if (!workflow.nodes) {
        return { extracted, modified };
      }
    
      for (const node of workflow.nodes) {
        let result: ExtractedNode | null = null;
        
        // Check node type and extract accordingly
        switch (node.type) {
          case 'n8n-nodes-base.code':
            result = await this.extractCodeNode(node, workflowName);
            break;
          
          case 'n8n-nodes-base.openAi':
          case '@n8n/n8n-nodes-langchain.openAi':
          case 'n8n-nodes-base.anthropic':
          case '@n8n/n8n-nodes-langchain.anthropic':
          case 'n8n-nodes-base.googleAi':
          case '@n8n/n8n-nodes-langchain.googleAi':
            result = await this.extractLLMNode(node, workflowName);
            break;
          
          case 'n8n-nodes-base.postgres':
          case 'n8n-nodes-base.mysql':
          case 'n8n-nodes-base.microsoftSql':
            result = await this.extractSQLNode(node, workflowName);
            break;
          
          case 'n8n-nodes-base.html':
          case 'n8n-nodes-base.emailSend':
            result = await this.extractTemplateNode(node, workflowName);
            break;
    
          case 'n8n-nodes-base.httpRequest':
            // Try to extract JSON configuration
            result = await this.extractJSONNode(node, workflowName);
            break;
        }
    
        if (result) {
          extracted.push(result);
          modified = true;
        }
      }
    
      if (modified) {
        // Save modified workflow with references
        await fs.writeFile(workflowPath, JSON.stringify(workflow, null, 2));
      }
    
      // Update metadata
      await this.updateMetadata(workflowName, extracted);
    
      return { extracted, modified };
    }
  • NodeManager.extractAllNodes(): iterates over all workflow JSON files, calls extractNodes on each, collects results and formats response for tool.
    async extractAllNodes(): Promise<any> {
      const flowsDir = path.join(this.workflowsPath, 'flows');
      const files = await fs.readdir(flowsDir);
      const results = [];
      
      for (const file of files) {
        if (file.endsWith('.json') && !file.includes('package.json')) {
          const filePath = path.join(flowsDir, file);
          const result = await this.extractNodes(filePath);
          if (result.extracted.length > 0) {
            results.push({
              workflow: file.replace('.json', ''),
              extracted: result.extracted
            });
          }
        }
      }
      
      return {
        content: [{
          type: 'text',
          text: this.formatExtractionResults(results)
        }]
      };
    }

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/mckinleymedia/mcflow-mcp'

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