MCP server that enables AI assistants to download files from URLs to the local filesystem
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-url-downloader","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# MCP URL Downloader A Model Context Protocol (MCP) server that enables AI assistants to download files from URLs to the local filesystem. ## Features - Download single or multiple files from URLs - File size validation (configurable, default 500MB) - Automatic filename sanitization - Unique filename generation to prevent overwrites - Concurrent downloads with limits - **Security**: SSRF protection, path traversal protection, MIME type validation ## Installation ```bash # Using uvx (recommended) uvx mcp-url-downloader # Using pip pip install mcp-url-downloader # From source git clone https://github.com/dmitryglhf/mcp-url-downloader.git cd mcp-url-downloader uv sync ``` ## Configuration ### Claude Desktop Add to your configuration file: **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json` **Windows**: `%APPDATA%/Claude/claude_desktop_config.json` ```json { "mcpServers": { "url-downloader": { "command": "uvx", "args": ["mcp-url-downloader"] } } } ``` ## Usage ### `download_files` Download multiple files from URLs. ### `download_single_file` Download a single file with optional custom filename. ### Rate Limits - Maximum 100 URLs per `download_files` request - Maximum 10 concurrent downloads - URL length limited to 2048 characters - Timeout range: 1-300 seconds - File size range: 1-5000 MB ## Development ```bash # Run tests uv run pytest ```
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.