mcp-server-fetchplus by unclevicky - MCP Server

MCP-Server-FetchPlus is a specialized server application that implements the Model Context Protocol (MCP) to facilitate the retrieval and conversion of web content into Markdown format. This server is particularly useful for applications that require structured and easily readable text formats, such as documentation generation, content archiving, or data analysis. By converting web pages into Markdown, MCP-Server-FetchPlus ensures that the content is both human-readable and machine-processable, making it ideal for integration with large language models (LLMs) and other AI technologies. The server is designed to handle the complexities of web content, including the preservation of images and the automatic splitting of lengthy documents to fit within the context length limitations of LLMs. This functionality is crucial for maintaining the integrity and usability of the content when processed by AI models.

Features

Fetches web content based on user-provided URLs.
Converts web content into Markdown format for easy readability and processing.
Preserves images within the converted Markdown documents.
Automatically splits long documents to comply with LLM context length constraints.
Provides a simple API for integration with other applications and services.

Usages

usage with local development

python
mcp.run(transport='stdio')  # Tools defined via @mcp.tool() decorator

usage with remote deployment

python
mcp.run(transport='sse', host="0.0.0.0", port=8000)  # Specify SSE endpoint

usage with curl

bash
curl -X POST "http://localhost:8000/mcp/tool/fetch" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com"}'

Tools

fetch
Fetches the first block of content from a specified URL.