Skip to main content
Glama

download_chart

Generate and save chart images locally by providing Chart.js configurations, supporting various chart types like bar, line, and pie charts.

Instructions

Download a chart image to a local file

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
configYesChart configuration object
outputPathNoPath where the chart image should be saved. If not provided, the chart will be saved to Desktop or home directory.

Implementation Reference

  • Main execution logic for the download_chart tool: normalizes input config, generates chart URL using helpers, downloads image via axios, handles file paths (default to Desktop/home), saves PNG file, and returns success message.
    case 'download_chart': {
      try {
        const { config, outputPath: userProvidedPath } = request.params.arguments as { 
          config: Record<string, unknown>;
          outputPath?: string;
        };
        
        // Validate and normalize config first
        if (!config || typeof config !== 'object') {
          throw new McpError(
            ErrorCode.InvalidParams,
            'Config must be a valid chart configuration object'
          );
        }
        
        // Handle both direct properties and nested properties in 'data'
        let normalizedConfig: any = { ...config };
        
        // If config has data property with datasets, extract them
        if (config.data && typeof config.data === 'object' && 
            (config.data as any).datasets && !normalizedConfig.datasets) {
          normalizedConfig.datasets = (config.data as any).datasets;
        }
        
        // If config has data property with labels, extract them
        if (config.data && typeof config.data === 'object' && 
            (config.data as any).labels && !normalizedConfig.labels) {
          normalizedConfig.labels = (config.data as any).labels;
        }
        
        // If type is inside data object but not at root, extract it
        if (config.data && typeof config.data === 'object' && 
            (config.data as any).type && !normalizedConfig.type) {
          normalizedConfig.type = (config.data as any).type;
        }
        
        // Final validation after normalization
        if (!normalizedConfig.type || !normalizedConfig.datasets) {
          throw new McpError(
            ErrorCode.InvalidParams,
            'Config must include type and datasets properties (either at root level or inside data object)'
          );
        }
        
        // Generate default outputPath if not provided
        const fs = await import('fs');
        const path = await import('path');
        const os = await import('os');
        
        let outputPath = userProvidedPath;
        if (!outputPath) {
          // Get home directory
          const homeDir = os.homedir();
          const desktopDir = path.join(homeDir, 'Desktop');
          
          // Check if Desktop directory exists and is writable
          let baseDir = homeDir;
          try {
            await fs.promises.access(desktopDir, fs.constants.W_OK);
            baseDir = desktopDir; // Desktop exists and is writable
          } catch (error) {
            // Desktop doesn't exist or is not writable, use home directory
            console.error('Desktop not accessible, using home directory instead');
          }
          
          // Generate a filename based on chart type and timestamp
          const timestamp = new Date().toISOString()
            .replace(/:/g, '-')
            .replace(/\..+/, '')
            .replace('T', '_');
          const chartType = normalizedConfig.type || 'chart';
          outputPath = path.join(baseDir, `${chartType}_${timestamp}.png`);
          
          console.error(`No output path provided, using: ${outputPath}`);
        }
        
        // Check if the output directory exists and is writable
        const outputDir = path.dirname(outputPath);
        
        try {
          await fs.promises.access(outputDir, fs.constants.W_OK);
        } catch (error) {
          throw new McpError(
            ErrorCode.InvalidParams,
            `Output directory does not exist or is not writable: ${outputDir}`
          );
        }
        
        const chartConfig = this.generateChartConfig(normalizedConfig);
        const url = await this.generateChartUrl(chartConfig);
        
        try {
          const response = await axios.get(url, { responseType: 'arraybuffer' });
          await fs.promises.writeFile(outputPath, response.data);
        } catch (error: any) {
          if (error.code === 'EACCES' || error.code === 'EROFS') {
            throw new McpError(
              ErrorCode.InvalidParams,
              `Cannot write to ${outputPath}: Permission denied`
            );
          }
          if (error.code === 'ENOENT') {
            throw new McpError(
              ErrorCode.InvalidParams,
              `Cannot write to ${outputPath}: Directory does not exist`
            );
          }
          throw error;
        }
        
        return {
          content: [
            {
              type: 'text',
              text: `Chart saved to ${outputPath}`
            }
          ]
        };
      } catch (error: any) {
        if (error instanceof McpError) {
          throw error;
        }
        throw new McpError(
          ErrorCode.InternalError,
          `Failed to download chart: ${error?.message || 'Unknown error'}`
        );
      }
    }
  • src/index.ts:229-245 (registration)
    Tool registration in ListTools handler, defining name, description, and input schema for download_chart.
      name: 'download_chart',
      description: 'Download a chart image to a local file',
      inputSchema: {
        type: 'object',
        properties: {
          config: {
            type: 'object',
            description: 'Chart configuration object'
          },
          outputPath: {
            type: 'string',
            description: 'Path where the chart image should be saved. If not provided, the chart will be saved to Desktop or home directory.'
          }
        },
        required: ['config']
      }
    }
  • Input schema definition for download_chart tool, specifying config (required) and optional outputPath.
    inputSchema: {
      type: 'object',
      properties: {
        config: {
          type: 'object',
          description: 'Chart configuration object'
        },
        outputPath: {
          type: 'string',
          description: 'Path where the chart image should be saved. If not provided, the chart will be saved to Desktop or home directory.'
        }
      },
      required: ['config']
    }
  • Helper method to generate QuickChart URL from ChartConfig, used by download_chart handler.
    private async generateChartUrl(config: ChartConfig): Promise<string> {
      const encodedConfig = encodeURIComponent(JSON.stringify(config));
      return `${QUICKCHART_BASE_URL}?c=${encodedConfig}`;
    }
  • Helper method to validate and normalize chart configuration, handles special cases for chart types, used by download_chart.
    private generateChartConfig(args: any): ChartConfig {
      // Add defensive checks to handle possibly malformed input
      if (!args) {
        throw new McpError(
          ErrorCode.InvalidParams,
          'No arguments provided to generateChartConfig'
        );
      }
      
      if (!args.type) {
        throw new McpError(
          ErrorCode.InvalidParams,
          'Chart type is required'
        );
      }
      
      if (!args.datasets || !Array.isArray(args.datasets)) {
        throw new McpError(
          ErrorCode.InvalidParams,
          'Datasets must be a non-empty array'
        );
      }
      
      const { type, labels, datasets, title, options = {} } = args;
      
      this.validateChartType(type);
    
      const config: ChartConfig = {
        type,
        data: {
          labels: labels || [],
          datasets: datasets.map((dataset: any) => {
            if (!dataset || !dataset.data) {
              throw new McpError(
                ErrorCode.InvalidParams,
                'Each dataset must have a data property'
              );
            }
            return {
              label: dataset.label || '',
              data: dataset.data,
              backgroundColor: dataset.backgroundColor,
              borderColor: dataset.borderColor,
              ...(dataset.additionalConfig || {})
            };
          })
        },
        options: {
          ...options,
          ...(title && {
            title: {
              display: true,
              text: title
            }
          })
        }
      };
    
      // Special handling for specific chart types
      switch (type) {
        case 'radialGauge':
        case 'speedometer':
          if (!datasets?.[0]?.data?.[0]) {
            throw new McpError(
              ErrorCode.InvalidParams,
              `${type} requires a single numeric value`
            );
          }
          config.options = {
            ...config.options,
            plugins: {
              datalabels: {
                display: true,
                formatter: (value: number) => value
              }
            }
          };
          break;
    
        case 'scatter':
        case 'bubble':
          datasets.forEach((dataset: any) => {
            if (!Array.isArray(dataset.data[0])) {
              throw new McpError(
                ErrorCode.InvalidParams,
                `${type} requires data points in [x, y${type === 'bubble' ? ', r' : ''}] format`
              );
            }
          });
          break;
      }
    
      return config;
    }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but provides minimal behavioral information. It mentions saving to Desktop/home directory as a fallback, which is useful, but doesn't disclose important traits like file format, permissions needed, whether it overwrites existing files, error conditions, or what happens if the config is invalid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise - a single sentence that communicates the core functionality without any wasted words. It's front-loaded with the essential information and doesn't include unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no annotations, no output schema, and a nested object parameter (config), the description is insufficient. It doesn't explain what the chart configuration should contain, what image formats are supported, what happens on success/failure, or provide any context about the relationship with the sibling 'generate_chart' tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the baseline is 3. The description doesn't add any parameter information beyond what's already in the schema - it doesn't explain what a 'chart configuration object' should contain, provide examples, or clarify the outputPath behavior beyond what the schema already states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Download') and the resource ('a chart image to a local file'), making the purpose immediately understandable. However, it doesn't distinguish this tool from its sibling 'generate_chart' - it's unclear if 'download_chart' generates and downloads or just downloads an existing chart.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus alternatives. The description doesn't mention the sibling tool 'generate_chart' or explain the relationship between generating and downloading charts, leaving the agent to guess about appropriate usage contexts.

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/data-mindset/quickchart-mcp'

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