{"id":24161554,"url":"https://github.com/zcaceres/fetch-mcp","last_synced_at":"2026-08-27T18:04:57.930Z","repository":{"id":268958047,"uuid":"905004409","full_name":"zcaceres/fetch-mcp","owner":"zcaceres","description":"A flexible HTTP fetching Model Context Protocol server.","archived":false,"fork":false,"pushed_at":"2026-03-12T17:17:24.000Z","size":1096,"stargazers_count":811,"open_issues_count":5,"forks_count":122,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-08-17T09:17:58.693Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zcaceres.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-12-18T01:05:17.000Z","updated_at":"2026-08-14T13:15:43.000Z","dependencies_parsed_at":"2025-03-27T02:11:03.875Z","dependency_job_id":"0ca2d99a-054f-4689-995b-277fcc0c0711","html_url":"https://github.com/zcaceres/fetch-mcp","commit_stats":null,"previous_names":["zcaceres/fetch-mcp"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/zcaceres/fetch-mcp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zcaceres%2Ffetch-mcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zcaceres%2Ffetch-mcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zcaceres%2Ffetch-mcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zcaceres%2Ffetch-mcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zcaceres","download_url":"https://codeload.github.com/zcaceres/fetch-mcp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zcaceres%2Ffetch-mcp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":36945701,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-22T15:14:58.755Z","status":"online","status_checked_at":"2026-08-27T02:00:07.166Z","response_time":96,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-01-12T17:17:19.478Z","updated_at":"2026-08-27T18:04:57.925Z","avatar_url":"https://github.com/zcaceres.png","language":"TypeScript","funding_links":[],"categories":["Developer Tools","Contributing","Data Access \u0026 Integration MCP Servers","サーバー実装","TypeScript","📚 Projects (1974 total)","Community Servers","MCP 服务器精选列表","HarmonyOS","Table of Contents","Browser Automation","APIs and HTTP Requests","Legend","MCP Servers","🚀 DevOps Productivity","🌐 Web Development","🗂️ Extensions by Category","MCP Servers \u0026 Protocol","💻 Developer Tools (164 servers)","Server Implementations","可用服务","Agent Communication Protocols"],"sub_categories":["API Tools","🛠️ Utilities","🛠️ \u003ca name=\"developer-tools\"\u003e\u003c/a\u003e開発者ツール","MCP Servers","💻 开发与代码执行","Windows Manager","Other Tools and Integrations","How to Submit","💻 \u003ca name=\"developer-tools\"\u003e\u003c/a\u003eDeveloper Tools","💻 Developer Tools","🌐 Web Services","Other MCP Servers","网络","Model Context Protocol (MCP)"],"readme":"# Fetch MCP Server\n\n![fetch mcp logo](logo.jpg)\n\n[![npm version](https://img.shields.io/npm/v/mcp-fetch-server.svg)](https://www.npmjs.com/package/mcp-fetch-server)\n\nAn MCP server for fetching web content in multiple formats — HTML, JSON, plain text, Markdown, readable article content, and YouTube transcripts.\n\n\u003ca href=\"https://glama.ai/mcp/servers/nu09wf23ao\"\u003e\n  \u003cimg width=\"380\" height=\"200\" src=\"https://glama.ai/mcp/servers/nu09wf23ao/badge\" alt=\"Fetch Server MCP server\" /\u003e\n\u003c/a\u003e\n\n## Tools\n\nAll tools accept the following common parameters:\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| `url` | string | Yes | URL to fetch |\n| `headers` | object | No | Custom headers to include in the request |\n| `max_length` | number | No | Maximum characters to return (default: 5000) |\n| `start_index` | number | No | Start from this character index (default: 0) |\n| `proxy` | string | No | Proxy URL (e.g. `http://proxy:8080`) |\n\n- **fetch_html** — Fetch a website and return its raw HTML content.\n\n- **fetch_markdown** — Fetch a website and return its content converted to Markdown.\n\n- **fetch_txt** — Fetch a website and return plain text with HTML tags, scripts, and styles removed.\n\n- **fetch_json** — Fetch a URL and return the JSON response.\n\n- **fetch_readable** — Fetch a website and extract the main article content using [Mozilla Readability](https://github.com/mozilla/readability), returned as Markdown. Strips navigation, ads, and boilerplate. Ideal for articles and blog posts.\n\n- **fetch_youtube_transcript** — Fetch a YouTube video's captions/transcript. Uses `yt-dlp` if available, otherwise extracts directly from the page. Accepts an additional `lang` parameter (default: `\"en\"`) to select the caption language.\n\n## Installation\n\n### As an MCP server\n\nAdd to your MCP client configuration:\n\n```json\n{\n  \"mcpServers\": {\n    \"fetch\": {\n      \"command\": \"npx\",\n      \"args\": [\"mcp-fetch-server\"]\n    }\n  }\n}\n```\n\n### As a CLI\n\n```bash\nnpx mcp-fetch \u003ccommand\u003e \u003curl\u003e [flags]\n```\n\nOr install globally:\n\n```bash\nnpm install -g mcp-fetch-server\nmcp-fetch \u003ccommand\u003e \u003curl\u003e [flags]\n```\n\n## CLI Usage\n\n```\nmcp-fetch \u003ccommand\u003e \u003curl\u003e [flags]\n```\n\n### Commands\n\n| Command | Description |\n|---------|-------------|\n| `html` | Fetch a URL and return raw HTML |\n| `markdown` | Fetch a URL and return Markdown |\n| `readable` | Fetch a URL and return article content as Markdown (via Readability) |\n| `txt` | Fetch a URL and return plain text |\n| `json` | Fetch a URL and return JSON |\n| `youtube` | Fetch a YouTube video transcript |\n\n### Flags\n\n| Flag | Description |\n|------|-------------|\n| `--max-length \u003cN\u003e` | Maximum characters to return |\n| `--start-index \u003cN\u003e` | Start from this character index |\n| `--proxy \u003cURL\u003e` | Proxy URL |\n| `--lang \u003ccode\u003e` | Language code for YouTube transcripts (default: `en`) |\n| `--help` | Show help message |\n| `--version` | Show version |\n\n### Examples\n\n```bash\n# Fetch a page as markdown\nmcp-fetch markdown https://example.com\n\n# Extract article content without boilerplate\nmcp-fetch readable https://example.com/blog/post\n\n# Get a YouTube transcript in Spanish\nmcp-fetch youtube https://www.youtube.com/watch?v=dQw4w9WgXcQ --lang es\n\n# Fetch with a length limit\nmcp-fetch html https://example.com --max-length 10000\n\n# Fetch through a proxy\nmcp-fetch json https://api.example.com/data --proxy http://proxy:8080\n```\n\n## Environment Variables\n\n| Variable | Description |\n|----------|-------------|\n| `DEFAULT_LIMIT` | Default character limit for responses (default: `5000`, set to `0` for no limit) |\n| `MAX_RESPONSE_BYTES` | Maximum response body size in bytes (default: `10485760` / 10 MB) |\n\nExample with a custom limit:\n\n```json\n{\n  \"mcpServers\": {\n    \"fetch\": {\n      \"command\": \"npx\",\n      \"args\": [\"mcp-fetch-server\"],\n      \"env\": {\n        \"DEFAULT_LIMIT\": \"50000\"\n      }\n    }\n  }\n}\n```\n\n## Features\n\n- Fetch web content as HTML, JSON, plain text, or Markdown\n- Extract article content with Mozilla Readability (strips ads, nav, boilerplate)\n- Extract YouTube video transcripts (via `yt-dlp` or direct extraction)\n- Proxy support for requests behind firewalls\n- Pagination with `max_length` and `start_index`\n- Custom request headers\n- SSRF protection (blocks private/localhost addresses and DNS rebinding)\n- Response size limits to prevent memory exhaustion\n\n## Development\n\n```bash\nbun install\nbun run dev     # start with watch mode\nbun test        # run tests\nbun run build   # build for production\n```\n\n## License\n\nThis project is licensed under the MIT License.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzcaceres%2Ffetch-mcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzcaceres%2Ffetch-mcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzcaceres%2Ffetch-mcp/lists"}