$ loading_
Fetch web pages for AI agents with fallback engines and clear block detection.
This MCP tool is described as a web-fetch server for agents, which implies normal tool capabilities such as code execution and network access. No credential requirement or obvious overreach is stated, but documentation is sparse, community adoption is low, and maintenance status is unknown, so caution is warranted.
The materials explicitly state that no keys or environment variables are required. There is no indication that API tokens, account credentials, or other sensitive authentication data must be provided, so credential exposure appears low.
Its stated function is fetching web pages, which inherently requires outbound network requests. Although no fixed remote endpoint is listed, it will send user-specified URLs/request targets to destination websites, creating normal data egress and destination visibility risk.
The system flags it as executes-code, indicating the tool runs local server/code to perform fetching. This is a normal MCP capability, but the materials do not detail which fetch engines are invoked or the exact system permission boundaries.
Based on the description, it mainly accesses web resources and does not explicitly claim local sensitive file read/write or broad system data permissions. However, as a locally running MCP service, its actual data access scope depends on implementation, and sparse documentation limits visibility.
Positive signals include being open source under Apache 2.0, making the code auditable in principle. However, it comes from a third-party registry, has only 0 GitHub stars, unknown maintenance status, and no README, so supply-chain maturity and maintenance confidence are limited.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "web-fetch-mcp" yet — see the docs or source repo.
Use web-fetch-mcp to fetch the main content of this page: https://example.com, and return the title, a body summary, and a list of extractable links.
Returns the page title, a summary, and links; if blocked, clearly indicates fetch blocking.
Use web-fetch-mcp to fetch the following 5 URLs one by one, and output each page's access status, title, and whether fetch blocking occurred.
Provides a summary for each URL, including success, failure, or blocked status.
Use web-fetch-mcp to fetch this set of reference pages, extract the key points from each page, and mark which pages could not be accessed due to blocking.
Outputs page-by-page key point summaries and a list of pages blocked from fetching.
Lets agents extract clean web text and send full HTTP requests efficiently.
Lets local LLMs search the web and extract clean page content.
Fetch web pages as markdown for LLM reading, analysis, and automation.
Fetch web content reliably with high performance and automatic fallback handling.
Fetch, search, batch-process, and summarize web content for research workflows.
Fetch, crawl, and search the web for AI agents in clean Markdown.