Skip to main content
Glama
cablate

Simple Document Processing MCP Server

html_cleaner

Remove unnecessary HTML tags and attributes to clean document files for processing. Specify input file path and output directory to streamline HTML content.

Instructions

Clean HTML by removing unnecessary tags and attributes

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
inputPathYesPath to the input HTML file
outputDirYesDirectory where cleaned HTML should be saved

Implementation Reference

  • Core handler function implementing the html_cleaner tool logic: loads HTML with JSDOM, removes unwanted tags (script, style, etc.) and attributes (onclick, etc.), serializes cleaned HTML, saves to unique filename in output directory.
    export async function cleanHtml(inputPath: string, outputDir: string) {
      try {
        console.error(`Starting HTML cleaning...`);
        console.error(`Input file: ${inputPath}`);
        console.error(`Output directory: ${outputDir}`);
    
        // 確保輸出目錄存在
        try {
          await fs.access(outputDir);
          console.error(`Output directory exists: ${outputDir}`);
        } catch {
          console.error(`Creating output directory: ${outputDir}`);
          await fs.mkdir(outputDir, { recursive: true });
          console.error(`Created output directory: ${outputDir}`);
        }
    
        const uniqueId = generateUniqueId();
        const htmlContent = await fs.readFile(inputPath, "utf-8");
        const dom = new JSDOM(htmlContent);
        const { document } = dom.window;
    
        // 移除不必要的標籤和屬性
        const unwantedTags = ["script", "style", "iframe", "noscript"];
        const unwantedAttrs = ["onclick", "onload", "onerror", "style"];
    
        unwantedTags.forEach((tag) => {
          document.querySelectorAll(tag).forEach((el) => el.remove());
        });
    
        document.querySelectorAll("*").forEach((el) => {
          unwantedAttrs.forEach((attr) => el.removeAttribute(attr));
        });
    
        const cleanedHtml = dom.serialize();
        const outputPath = path.join(outputDir, `cleaned_${uniqueId}.html`);
        await fs.writeFile(outputPath, cleanedHtml);
        console.error(`Written cleaned HTML to ${outputPath}`);
    
        return {
          success: true,
          data: `Successfully cleaned HTML and saved to ${outputPath}`,
        };
      } catch (error) {
        console.error(`Error in cleanHtml:`, error);
        return {
          success: false,
          error: error instanceof Error ? error.message : "Unknown error",
        };
      }
    }
  • Schema definition for the html_cleaner tool, specifying name, description, and input parameters (inputPath and outputDir).
    export const HTML_CLEAN_TOOL: Tool = {
      name: "html_cleaner",
      description: "Clean HTML by removing unnecessary tags and attributes",
      inputSchema: {
        type: "object",
        properties: {
          inputPath: {
            type: "string",
            description: "Path to the input HTML file",
          },
          outputDir: {
            type: "string",
            description: "Directory where cleaned HTML should be saved",
          },
        },
        required: ["inputPath", "outputDir"],
      },
    };
  • Registers the html_cleaner tool (as HTML_CLEAN_TOOL) in the central tools array used for listing available tools in MCP server.
    import { HTML_CLEAN_TOOL, HTML_EXTRACT_RESOURCES_TOOL, HTML_FORMAT_TOOL, HTML_TO_MARKDOWN_TOOL, HTML_TO_TEXT_TOOL } from "./htmlTools.js";
    import { PDF_MERGE_TOOL, PDF_SPLIT_TOOL } from "./pdfTools.js";
    import { TEXT_DIFF_TOOL, TEXT_ENCODING_CONVERT_TOOL, TEXT_FORMAT_TOOL, TEXT_SPLIT_TOOL } from "./txtTools.js";
    
    export const tools = [DOCUMENT_READER_TOOL, PDF_MERGE_TOOL, PDF_SPLIT_TOOL, DOCX_TO_PDF_TOOL, DOCX_TO_HTML_TOOL, HTML_CLEAN_TOOL, HTML_TO_TEXT_TOOL, HTML_TO_MARKDOWN_TOOL, HTML_EXTRACT_RESOURCES_TOOL, HTML_FORMAT_TOOL, TEXT_DIFF_TOOL, TEXT_SPLIT_TOOL, TEXT_FORMAT_TOOL, TEXT_ENCODING_CONVERT_TOOL, EXCEL_READ_TOOL, FORMAT_CONVERTER_TOOL];
  • MCP server request handler that dispatches calls to 'html_cleaner' by invoking cleanHtml function and formatting the response.
    if (name === "html_cleaner") {
      const { inputPath, outputDir } = args as {
        inputPath: string;
        outputDir: string;
      };
      const result = await cleanHtml(inputPath, outputDir);
      if (!result.success) {
        return {
          content: [{ type: "text", text: `Error: ${result.error}` }],
          isError: true,
        };
      }
      return {
        content: [{ type: "text", text: fileOperationResponse(result.data) }],
        isError: false,
      };
    }
  • Helper utility to generate unique hexadecimal IDs for output filenames used in html_cleaner.
    function generateUniqueId(): string {
      return randomBytes(9).toString("hex");
    }
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions removing unnecessary tags and attributes but doesn't specify what constitutes 'unnecessary', whether the operation is destructive to the original file, what happens to errors, or the output format. This leaves significant gaps for a tool that modifies content.

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 a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded and every part earns its place, making it highly concise and well-structured.

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?

Given the complexity of an HTML cleaning operation with no annotations and no output schema, the description is incomplete. It lacks details on behavioral traits (e.g., what gets removed, error handling), output specifics, and usage context, making it inadequate for safe and effective tool invocation.

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?

Schema description coverage is 100%, so the schema already documents both parameters (inputPath and outputDir) with clear descriptions. The description adds no additional meaning beyond what the schema provides, such as file format expectations or directory creation behavior, meeting the baseline for high coverage.

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 verb ('clean') and resource ('HTML'), specifying the action of removing unnecessary tags and attributes. It distinguishes itself from siblings like html_formatter, html_to_markdown, and html_to_text by focusing on cleaning rather than formatting or conversion, though it doesn't explicitly name alternatives.

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?

The description provides no guidance on when to use this tool versus alternatives like html_formatter or html_to_text, nor does it mention prerequisites such as file accessibility or specific HTML standards. It implies usage for cleaning HTML but lacks explicit context or exclusions.

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/cablate/mcp-doc-forge'

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