"Web search services that don't require an API key" matching MCP servers:

Provides local web search (Baidu, Bing, 360, Sogou), page scraping to markdown, and image description via LM Studio vision models, all without external APIs and with disk caching.

Enables capturing browser API traffic via CDP and turning any website into a ready-to-run FastMCP server, with no official API required.

A dual-transport MCP server enabling anonymous free web search via Parallel (default) or Exa (backup), with no API keys or DSH dependency, for Claude Code, Codex, and any MCP client.

Enables Tavily and Firecrawl MCP servers to operate with multiple API keys, automatically rotating to backup keys on quota exhaustion, rate limits, or invalid keys, while rewriting API endpoints to the local proxy.

An MCP Server that provides access to Google's Search Console API, allowing users to interact with website search performance data and manage search presence through natural language.

Enables interaction with MongoDB databases through CRUD operations, aggregation, and schema discovery, with automatic field validation and ObjectId conversion.

MCP Server for Git operations, agent templates, and project utilities.

Deployable remote MCP server on Cloudflare Workers without authentication, enabling custom tool integration with AI Playground and Claude Desktop.

MCP server for Cursor IDE offering tools for Human Design chart analysis, partner matching, n8n workflow management, and utility functions like UUID generation and calculation.

An MCP server that allows coding agents to search the Swift Package Index and retrieve GitHub READMEs without requiring an API key. It features comprehensive search filters for stars, platforms, and licenses, providing token-efficient responses optimized for LLM comprehension.

MCP server that lets AI editors execute JavaScript, read console output, and simulate clicks/input on static web pages. Supports multiple browser pages and can be deployed remotely via HTTP transport.

MCP server that searches npm packages and returns live registry data without an API key. Supports package search, detailed info, and side-by-side comparison of packages.

Provides Codex and other MCP clients a local web debugging server that coordinates a browser session, JavaScript debugger, bounded runtime evidence, and reproducible flow verification for vanilla HTML/JS projects.

Enables AI models to interact with IBM FileNet Content Manager for document management, folder operations, metadata handling, search, and content extraction through a standardized interface.

Enables programmatic interaction with ArchiveBox web archiving functionality through a comprehensive API wrapper. Supports adding URLs to archives, managing snapshots, and executing CLI commands with multiple authentication methods and policy-based access control.

Turn any API into an MCP server. Query in English. Get results—even when the API can't.

Enables interaction with Nullplatform's API endpoints for managing deployments, scopes, services, and other cloud resources through natural language using the official OpenAPI specification.

Enables users to select UI elements on localhost pages and send fix requests to MCP-compatible coding agents, which retrieve the captures and edit the code, with masking of sensitive values.

MCP server that enables AI agents to read and write records in a live REST API generated from pasted data, with tools for listing, querying, inserting, updating, and deleting records.

Provides an MCP server with a search tool for agents, backed by Cloudflare AI Search and a synced corpus of git repositories.