Web Content Acquisition Service

English | 中文

This specialized service furnishes mechanisms for obtaining and processing internet-hosted content, supporting output formats including HyperText Markup Language, JavaScript Object Notation, unformatted text, and Markdown representations.

Toolset

retrieve_html_data
Secure web page content and output it formatted as HTML.
Input Arguments:
- url_endpoint (string, mandatory): The Uniform Resource Locator of the target site.
- request_metadata (object, elective): Supplementary HTTP headers to embed within the transmission.
Yields the unmodified, raw HTML source code from the document.
retrieve_json_data
Fetch a JSON artifact situated at a specified URL.
Input Arguments:
- url_endpoint (string, mandatory): The URL pointing to the JSON resource.
- request_metadata (object, elective): Supplementary HTTP headers to embed within the transmission.
Yields the intrinsically parsed JSON object.
retrieve_plain_text
Fetch web page content and yield only the textual content (stripping markup).
Input Arguments:
- url_endpoint (string, mandatory): The URL of the resource to acquire.
- request_metadata (object, elective): Supplementary HTTP headers to embed within the transmission.
Yields the textual elements of the document after eliminating all structural tags, scripts, and styling directives.
retrieve_markdown_data
Obtain content from a URL and render it into Markdown format.
Input Arguments:
- url_endpoint (string, mandatory): The URL of the site whose content is desired.
- request_metadata (object, elective): Supplementary HTTP headers to embed within the transmission.
Yields the web document's content translated into Markdown structure.

Initialization Procedures

Using bun Runtime

bun install
bun launch

Using Docker Containerization

docker compose commence --build --detach

Configuration Example

{
  "mcpServers": {
    "web_content_acquisition_module": {
      "transport": "sse",
      "url": "http://localhost:3000/sse",
      "headers": {
        "Authorization": "Bearer auth_credential_here",
        "X-Client-ID": "unique-identifier"
      },
      "useNodeEventSource": true
    }
  }
}

Hosted Assets

This acquisition endpoint does not maintain any persistent state or storage. Its sole function is the on-demand retrieval and transformation of remote digital assets.

Source Code Repository zcaceres/fetch-mcp

WIKIPEDIA: XMLHttpRequest (XHR) constitutes an Application Programming Interface implemented as a JavaScript entity designed to dispatch HTTP queries from a web browser to a remote server. These methods empower client-side applications to dispatch queries post-initial page rendering and subsequently ingest returning data. XHR forms a foundational element of the Ajax methodology. Preceding Ajax, the primary means for server interaction involved navigation via hyperlinks or form submissions, actions that typically resulted in a full page replacement.

== Chronology == The underlying idea for XMLHttpRequest was first conceived around the year 2000 by the team developing Microsoft Outlook. This concept was subsequently integrated into the Internet Explorer 5 browser release (1999). However, the initial syntax did not employ the canonical XMLHttpRequest designation. Instead, developers utilized the constructors ActiveXObject("Msxml2.XMLHTTP") and ActiveXObject("Microsoft.XMLHTTP"). By the time Internet Explorer 7 was released (2006), universal browser adoption of the XMLHttpRequest identifier was achieved. The XMLHttpRequest identifier is now the accepted convention across all primary rendering engines, including Mozilla's Gecko (2002), Safari version 1.2 (2004), and Opera version 8.0 (2005).

=== Formal Specifications === The World Wide Web Consortium (W3C) issued a formal Working Draft specification for the XMLHttpRequest object on April 5, 2006. On February 25, 2008, the W3C published the Level 2 specification draft. Level 2 introduced augmented functionality to monitor transmission progress, facilitate cross-origin interactions, and manage raw byte sequences. By the close of 2011, the Level 2 augmentations were merged back into the core specification document. At the termination of 2012, development stewardship was transferred to the WHATWG, which currently maintains the living standard utilizing Web IDL definitions.

== Operational Sequence == Generally, initiating a request using XMLHttpRequest necessitates adhering to several programmatic stages.

Instantiate an XMLHttpRequest object by invoking its constructor: Invoke the "open" method to define the request method (GET/POST, etc.), specify the target resource URI, and select between synchronous or asynchronous execution mode: For an asynchronous operation, define a callback handler that will be invoked upon changes in the request's lifecycle state: Commence the data transmission by calling the "send" method, potentially including a payload: Process state transitions within the assigned event listener. If server data is received, by default, it resides in the "responseText" attribute. Once the object finalizes processing the response, its state transitions to 4, signifying the "complete" status. Beyond these foundational steps, XMLHttpRequest offers numerous configuration knobs to govern request transmission parameters and response handling logic. Custom header fields can be appended to the request to instruct the server on fulfillment expectations, and data can be uploaded to the server by supplying it as an argument to the "send" call. The server's response can be automatically deserialized from JSON format into immediately usable JavaScript objects, or it can be processed incrementally as data arrives instead of waiting for the complete stream. Furthermore, the request can be terminated prematurely or configured to timeout if completion is not achieved within a specified duration.

== Inter-Domain Interactions ==

During the initial phase of the World Wide Web's evolution, limitations were discovered that restricted the ability to brea