"Simple HTTP server or client implementation" matching MCP servers:

Enables fetching HTTP resources through the MCP protocol.

Empowers LLMs to scrape web pages and generate sitemaps through the Firecrawl Simple API, with support for JavaScript rendering and configurable options.

Enables MCP clients to perform HTTP GET requests to arbitrary URLs and receive response details.

Enables Google search with advanced options (date, language, country, safe search) and webpage content extraction via the Model Context Protocol.

Operates Tencent Docs spreadsheet cells by reading boundaries, clicking, and inputting text via Playwright MCP, with caching options for efficiency.

A minimal browser debugging MCP server that monitors Chrome Console logs and executes JavaScript. 97% lighter than full DevTools alternatives, providing just 4 essential tools for efficient debugging without consuming excessive context tokens.

A Model Context Protocol server that enables LLMs to interact with VS Code's Simple Browser, allowing for browser control, JavaScript execution, console monitoring, and navigation through natural language.

Fetches web pages from HTTP/HTTPS URLs and converts them to Markdown format. Supports both SSE and Stdio protocols for web deployments, Kubernetes environments, and desktop clients.

Enables Grok to send arbitrary HTTP requests with cookie session persistence and redirect tracking, designed for web/CTF scenarios.

Provides browser automation capabilities via HTTP endpoints by wrapping the official Playwright MCP package, enabling serverless deployments and cloud environments where STDIO-based communication is not possible.

Provides preflight checks and domain intelligence so agents can skip domains that will refuse them or charge a fee, covering robots.txt, edge refusals, and HTTP 402 paywalls.

Turns a logged-in ChatGPT Web conversation into an OpenAI-compatible HTTP endpoint, letting any compatible client send chat completions and responses without an API key. Native tool calls tunnel back to the local MCP server and execute under bubblewrap sandboxing with capability-bound session tokens, idempotent turns, and DOM-captured answers.

A server that provides a website fetching tool via SSE transport, allowing users to retrieve content from specified URLs.

An MCP server for automating browser tasks using the Browser Use API. Provides tools to run, monitor, and manage browser automation tasks.

A Model Context Protocol (MCP) server that provides Google Search functionality with StreamableHTTP transport support.

Enables web searches using TAVILY API with fallback to DuckDuckGo, datetime queries, and optional Ollama AI processing. Features HTTP transport with OAuth2 authentication for secure access to search capabilities.

Enables MCP-capable LLM clients to read browser screenshots captured by the SnapStack extension, stored locally and served over Streamable HTTP.

Web Content Retrieval (full webpage, filtered content, or Markdown-converted), Custom User-Agent, Multi-HTTP Method Support (GET/POST/PUT/DELETE/PATCH), LLM-Controlled Request Headers, LLM-Accessible Response Headers, and more.

Adds fdl-mcp-server — published on npm at https://www.npmjs.com/package/fdl-mcp-server Five tools any MCP client can call to analyze small business websites: * audit_website — deterministic 5-pillar scorecard (Performance, SEO, Mobile, Security, AEO) with a 0–100 score and specific findings * compare_websites — side-by-side scorecard of two sites with a winner * ai_visibility_check —

Enables capturing screenshots of web pages and local HTML files through a simple MCP tool interface using Puppeteer with configurable options for dimensions and output paths.