Skip to main content
Glama
cablate

Simple Document Processing MCP Server

html_to_text

Convert HTML files to plain text while preserving document structure. Provide input path and output directory for the text file.

Instructions

Convert HTML to plain text while preserving structure

Input Schema

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

Implementation Reference

  • The main handler function for html_to_text. Reads an HTML file using JSDOM, extracts the body's textContent (preserving structure), and writes the plain text output to a uniquely-named .txt file in the specified output directory.
    export async function htmlToText(inputPath: string, outputDir: string) {
      try {
        console.error(`Starting HTML to text conversion...`);
        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;
    
        // 保留結構的文字轉換
        const text = document.body.textContent?.trim() || "";
        const outputPath = path.join(outputDir, `text_${uniqueId}.txt`);
        await fs.writeFile(outputPath, text);
        console.error(`Written text to ${outputPath}`);
    
        return {
          success: true,
          data: `Successfully converted HTML to text: ${outputPath}`,
        };
      } catch (error) {
        console.error(`Error in htmlToText:`, error);
        return {
          success: false,
          error: error instanceof Error ? error.message : "Unknown error",
        };
      }
    }
  • The Tool definition/schema for html_to_text. Defines the tool name as 'html_to_text', description, and input schema requiring 'inputPath' (path to HTML file) and 'outputDir' (directory for output text file).
    export const HTML_TO_TEXT_TOOL: Tool = {
      name: "html_to_text",
      description: "Convert HTML to plain text while preserving structure",
      inputSchema: {
        type: "object",
        properties: {
          inputPath: {
            type: "string",
            description: "Path to the input HTML file",
          },
          outputDir: {
            type: "string",
            description: "Directory where text file should be saved",
          },
        },
        required: ["inputPath", "outputDir"],
      },
    };
  • The tool is imported into the tools array (HTML_TO_TEXT_TOOL) which is exported and registered with the 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];
  • src/index.ts:168-184 (registration)
    The request handler in the MCP server that dispatches calls to 'html_to_text', extracts inputPath/outputDir from args, calls the htmlToText function, and returns the result.
    if (name === "html_to_text") {
      const { inputPath, outputDir } = args as {
        inputPath: string;
        outputDir: string;
      };
      const result = await htmlToText(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,
      };
    }
Behavior2/5

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

With no annotations, the description carries the full burden. It only states 'preserving structure' without explaining what that entails (e.g., handling of nested elements, CSS, scripts). No disclosure of side effects, performance characteristics, or error handling.

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

Conciseness2/5

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

The description is extremely short (one sentence), but it sacrifices necessary details for brevity. It is more under-specified than concise, missing important behavioral and usage information. Effective conciseness would be shorter without losing completeness, but here it is incomplete.

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 tool has 2 required parameters, no output schema, and no annotations, the description is insufficient. It does not explain what the tool returns (e.g., file path, confirmation), how it handles errors, or edge cases like empty files. Sibling context is not leveraged for differentiation.

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

Parameters2/5

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

Schema description coverage is 100%, so the baseline is 3. However, the description adds no additional meaning beyond the schema. It does not explain path formats, file extensions, or whether outputDir must exist. The description provides zero extra value for parameter understanding.

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 tool converts HTML to plain text, with a specific verb ('Convert') and resource ('HTML to plain text'). It mentions preserving structure, which adds context. However, it does not differentiate from siblings like 'html_to_markdown' or 'html_cleaner' that may also produce text output.

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 given on when to use this tool versus alternatives (e.g., html_to_markdown). There is no mention of prerequisites, preferred scenarios, or when to avoid the tool. The description fails to help the agent select this tool over others.

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