jgador avatar

Websharp

jgador/websharp

Built in C# on .NET 9, this server pairs SearXNG metasearch with SmartReader content extraction to give your LLM structured web results and clean article text. The web_search tool hits SearXNG with query, limit, categories, and language parameters, returning both a readable summary and full JSON metadata including suggestions and engine status. The web_page_read tool fetches one or more URLs concurrently and strips them down to article content using SmartReader. Ships with Docker Compose so you can spin up both the MCP endpoint and a local SearXNG instance together. CORS is wide open by default and there's no auth on the HTTP transport, so treat this as a localhost tool or put it behind a proxy.

GitHub stars
1
tools
2
transport
HTTP
last updated
Sep 22, 2025

Tools

2 tools

Public tool metadata for what this MCP can expose to an agent.

web_searchFree-form search string submitted to the configured search backend (defaults to SearXNG), returning a text summary and structured JSON metadata.

Free-form search string submitted to the configured search backend (defaults to SearXNG), returning a text summary and structured JSON metadata.

No parameter schema in public metadata yet.

web_page_readFetches and parses one or more absolute HTTP/HTTPS URLs and returns their readable article content.

Fetches and parses one or more absolute HTTP/HTTPS URLs and returns their readable article content.

No parameter schema in public metadata yet.

Sponsors

Readme

WebSharp MCP HTTP Server

WebSharp is a Model Context Protocol (MCP) server written in C# (.NET 9) that exposes web search and readable page extraction tools over the streamable HTTP transport. It pairs a SearXNG metasearch instance with the SmartReader content extraction library and ships with Docker assets so you can run everything locally with one command.

Highlights

  • Streamable HTTP MCP endpoint served by ASP.NET Core via ModelContextProtocol.AspNetCore.
  • SearXNG-backed metasearch tool that returns both a readable summary and structured JSON metadata.
  • SmartReader-powered page reader tools for single URLs or batches, ideal for grounding and fact checking workflows.
  • Container-first development story with Docker Compose and an inspector-ready .mcp.json profile.

Available MCP tools


View the full README on GitHub

Details

Repository
github.com/jgador/websharp
Category
Search & Web Crawling
Package
docker.io/jessegador/websharp-mcp:v0.99.0-rc2
Transport
HTTP
Registry
MCP registry, active

Related Search & Web Crawling MCP servers

View all
1shawnnygoh avatarArXiv Scoutshawnnygoh/arxiv-scoutSearch and retrieve academic papers directly from arXiv with advanced query capabilities. Extract full text from PDFs to generate summaries, literature reviews,1stars
2reka avatarRekaai.reka/mcpUnderstand your videos with Reka AI — search, ask questions, and extract insights.0stars
3rainbowgore avatarRainbowgore Stealthee Mcp Toolsrainbowgore/stealthee-mcp-toolsSpot pre-launch products before they trend. Search the web and tech sites, extract and parse pages…0stars
4apexflowlabsllc avatarApex Flow 3D Scraperapexflowlabsllc/apex-flow-web-scraperScrape, crawl and monitor public pages as Markdown with change tracking and source receipts.0stars
5bobbyhouse avatarProject Gutenberg MCPbobbyhouse/project-gutenberg-mcpRead Project Gutenberg books via MCP. Search, fetch metadata, and retrieve text in passages.0stars
6carrasquelalex1 avatarWebscrape Mcpcarrasquelalex1/webscrape-mcpFetch any URL and get clean Markdown. Web scraping for AI agents.0stars