Skip to main content
Glama
cdugo
by cdugo

fetch-url-docs

Fetch and extract comprehensive package documentation from programming language ecosystems like JavaScript, Python, and Java for LLMs without requiring API keys.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesURL of the library documentation to fetch

Implementation Reference

  • src/index.ts:133-171 (registration)
    Registration of the 'fetch-url-docs' tool, including inline input schema (URL validation with Zod) and handler function that fetches and returns documentation content from the given URL using ScraperService or handles errors.
    server.tool( "fetch-url-docs", { url: z.string().url().describe("URL of the library documentation to fetch"), }, async ({ url }) => { console.error(`Fetching documentation from URL: ${url}`); try { const documentationContent = await scraperService.fetchLibraryDocumentation(url); return { content: [ { type: "text", text: documentationContent, }, ], }; } catch (error) { console.error("Error fetching URL content:", error); const errorMessage = `Error fetching URL content: ${ error instanceof Error ? error.message : String(error) }`; return { content: [ { type: "text", text: errorMessage, }, ], isError: true, }; } } );
  • The inline handler function for 'fetch-url-docs' tool execution logic, which calls scraperService.fetchLibraryDocumentation(url) and formats the response as MCP content or error.
    async ({ url }) => { console.error(`Fetching documentation from URL: ${url}`); try { const documentationContent = await scraperService.fetchLibraryDocumentation(url); return { content: [ { type: "text", text: documentationContent, }, ], }; } catch (error) { console.error("Error fetching URL content:", error); const errorMessage = `Error fetching URL content: ${ error instanceof Error ? error.message : String(error) }`; return { content: [ { type: "text", text: errorMessage, }, ], isError: true, }; } }
  • Zod input schema for the tool defining the 'url' parameter as a valid URL.
    { url: z.string().url().describe("URL of the library documentation to fetch"), },
  • Core helper method implementing the documentation fetching logic: resolves URL if package name, extracts library name, crawls up to 5 relevant pages, compiles into structured Markdown with TOC, code examples, API refs, and adds LLM prompt instructions. Handles errors gracefully.
    public async fetchLibraryDocumentation( url: string, maxPages = 5 ): Promise<string> { try { // If input is not a URL, assume it's a package name if (!url.startsWith("http")) { url = `https://www.npmjs.com/package/${url}`; } // Extract library name from URL const libraryName = extractLibraryName(url); // Crawl documentation const pages = await this.crawlDocumentation(url, libraryName, maxPages); if (pages.length === 0) { throw new Error(`Failed to fetch documentation from ${url}`); } // Compile documentation into a single markdown document const documentation = this.compileDocumentation(pages, libraryName); // Include instructions for using the prompt const promptInstructions = ` --- šŸ” For better summarization, use the "summarize-library-docs" prompt with: - libraryName: "${libraryName}" - documentation: <the content above> Example: @summarize-library-docs with libraryName="${libraryName}" `; return documentation + promptInstructions; } catch (error) { console.error(`Error fetching URL content:`, error); // Extract library name from URL const libraryName = extractLibraryName(url); const errorMessage = `Error fetching URL content: ${ error instanceof Error ? error.message : String(error) }`; // Include error-specific prompt instructions const promptInstructions = ` --- šŸ” For information about this library despite the fetch error, use the "summarize-library-docs" prompt with: - libraryName: "${libraryName}" - errorStatus: "${error instanceof Error ? error.message : String(error)}" Example: @summarize-library-docs with libraryName="${libraryName}" and errorStatus="fetch failed" `; return errorMessage + promptInstructions; } }

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/cdugo/package-documentation-mcp'

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