"An open-source backend service for web and app development" matching MCP servers:

Enables AI agents to read and create customers, jobs, estimates, invoices, calendar tasks, equipment, technicians, and reference data through the documented Service Fusion REST API, handling OAuth 2.0 and pagination automatically.

Closes the find-download-install loop for lutris-mcp by searching Prowlarr, downloading via qBittorrent, polling until complete, classifying the result, and returning a path for installation.

Bridges the editing capabilities of an already-open DingTalk document in the browser to any MCP host via standard stdio, forwarding tools to the page's internal MCP server over a local WebSocket. Supports read/write operations through suggested edits, pairing-based security, and zero runtime dependencies.

Enables web searches through DuckDuckGo without an API key and extracts readable main content from web pages.

MCP server for AI-powered web research — search (Google, Brave, Serper, SearXNG), scrape any page, extract PDFs/DOCX/YouTube transcripts, academic & patent search. Single Go binary. Works with Claude, Cursor, Copilot, and any MCP client.

Enables private web search and webpage content extraction using a local SearxNG instance, prioritizing user privacy and autonomy.

Enables AI-assisted user feedback collection and management via a web interface, with MCP integration for automated replies and tool execution.

An MCP server that enables AI assistants to perform web searches on Perplexity.ai using browser automation instead of an official API. It supports persistent authenticated sessions and returns search results along with cited sources directly to the client.

MCP server for querying Google Gemini Web from Claude Code and other MCP clients, using cookie-based authentication. Enables creating, continuing, listing, viewing, and deleting Gemini chat conversations with model and thinking mode control.

Provides an LLM client with self-hosted web scraping capabilities including scraping, crawling, mapping, searching, structured data extraction, browser interaction, and deep research, without reliance on paid proxy or CAPTCHA services.

Enables access to Hong Kong government's official open data portal (DATA.GOV.HK) through natural language queries. Supports searching datasets, browsing categories, and retrieving detailed information about Hong Kong's public data resources.

Provides a web search tool with citations by running Claude Code CLI in an isolated Docker container, enabling search even in environments without direct Anthropic web search support.

Enables querying Italian and EU law, case law, parliamentary data, open data portals, Eurostat statistics, PNRR projects, and migrant reception centers through 24 MCP tools, with citation-grounded legal answers.

MCP server for Godot Engine enabling AI to autonomously develop, test, and debug games with deterministic playtesting, multiplayer testing, DAP debugging, LSP integration, and token efficiency.

Exposes data query and auto-insights (anomaly detection) as MCP tools. Enables AI agents to query metrics, list columns, and get data insights directly from pandas.

Exposes a support-desk application through MCP tools and resources with populate/snapshot/restore hooks for reproducible RL training episodes.

Exposes OpenWebUI's admin REST API as an MCP server, enabling administrative operations on OpenWebUI through natural language via MCP tools.

Fetches a URL and returns the main content as clean Markdown, using plain HTTP when possible and headless Chromium for JavaScript-rendered or bot-protected pages.

A lean FastMCP server that wraps xAI's web_search and x_search tools for MCP hosts, enabling live web and X search with citations.

An open-source MCP server for live Apple App Store competitor research, enabling AI agents to search apps, fetch metadata, compare competitors, and retrieve reviews and top charts as structured JSON.