Awesome MCPOther MCP Servers

serpapi/serpapi-mcp

⭐ 169 Python repository created 2025-03-04

SerpApi MCP Server is the official Model Context Protocol server for SerpApi, a commercial search results API. It is written in Python and gives an AI client access to search engine result pages from Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay and many other engines, along with the data SerpApi extracts from them such as answer boxes, organic results, news, images and shopping listings, plus weather forecasts and stock market data returned through ordinary search queries. The design centres on one tool called search that covers every engine. It takes a params object mirroring the SerpApi search API, where q is the query, engine selects the backend and defaults to google_light, and location applies a geographic filter; a separate mode argument switches between complete and compact JSON responses. Because parameters differ per engine, the per-engine schemas are exposed as MCP resources under serpapi://engines and serpapi://engines/, and a build-engines.py script regenerates them. Two opt-in extra tools implement the MCP Apps extension described in SEP-1865: search_table renders organic results as a sortable, searchable table and search_dashboard adds summary metrics, a source breakdown chart and an expandable detail panel, so bulk result JSON is rendered in the host UI instead of entering the model context. Hosts without MCP Apps support simply ignore them. The server runs as a hosted service at mcp.serpapi.com or can be self-hosted with uv or Docker on port 8000. Authentication takes the SerpApi key either in the URL path or as a bearer header, and the README lists ready-made setup commands for Claude Desktop, Claude Code, Codex, OpenClaw and Hermes plus install badges for VS Code and Cursor. Python 3.13 or newer is required and the project is MIT licensed.

https://github.com/serpapi/serpapi-mcp

mcpmcp-serverserpapisearchweb-searchgooglepythonmcp-apps

Also in Other MCP Servers

microsoft/markitdown

MarkItDown is a Python tool that converts various file formats into Markdown and integrates with LLM applications via an MCP server for enhanced text analysis and document processing.

punkpeye/awesome-mcp-servers

A curated collection of Model Context Protocol (MCP) servers that enable AI models to securely interact with local and remote resources through standardized server implementations.

modelcontextprotocol/servers

The Model Context Protocol Servers repository offers reference implementations and third-party integrations that demonstrate how MCP enables Large Language Models to securely access and interact with diverse tools and data sources.

koala73/worldmonitor

World Monitor is an AI-powered, real-time global intelligence dashboard aggregating news and monitoring geopolitical and infrastructure data for unified situational awareness.

headroomlabs-ai/headroom

Headroom is a context compression layer for AI agents, reducing token usage by 60-95% while preserving accuracy, implemented as a library, proxy, and MCP server.

diegosouzapw/OmniRoute

OmniRoute is a free AI gateway that connects various AI tools and models from over 230 providers through a single endpoint, featuring token compression, smart auto-fallback, and support for Model C...

rohitg00/ai-engineering-from-scratch

This comprehensive curriculum teaches AI engineering from scratch, focusing on building AI algorithms, agents, and MCP servers hands-on, covering everything from mathematical foundations to autonom...

every-app/open-seo

Open source, self-hostable SEO platform that exposes its keyword, rank, backlink and site-audit data to AI agents through an MCP server and a set of companion agent skills.