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

MCP server that provides web search via LLM API gateways with server-side search, returning cited answers and multi-provider fallback.

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.

MCP gateway for GREEN-API WhatsApp that lets AI agents send messages, manage instances, and receive notifications via WhatsApp using the Model Context Protocol.

Provides fully local, privacy-preserving semantic search over file names and paths via MCP, using BGE embeddings for fuzzy matching and supporting incremental updates, watch mode, and a loopback-only HTTP server.

Records Chrome network requests and responses for LLM knowledge bases, and exposes query and browser control capabilities via MCP tools like list_sessions, navigate, and evaluate.

Use Tavily Search to search for news pages or images.

Enables AI agents to explore and, when writes are enabled, modify a Langfuse deployment — traces, observations, sessions, prompts, datasets, scores, metrics and more — through the full Langfuse public API. Supports Langfuse Cloud in any region and self-hosted instances, including corporate networks that re-sign TLS traffic with their own certificate authority.

Provides read-only access to Chinese A-share stock market data such as quotes, K-lines, financials, capital flows, news, and research reports via a stdio MCP server for DeepSeek Harness and other MCP clients.

Model Context Protocol (MCP) server for the Royal Spanish Academy (RAE) API. It allows language models to interact with RAE's dictionary and linguistic resources.

An MCP front-end for AnB. The tool surface is "use-don't-reveal": no tool returns a plaintext secret. Reveal paths require a TTY the server doesn't have, so the no-reveal guarantee is structural, not prompt-based — it holds even against a prompt-injected agent. Runs as a dedicated, narrowly-scoped AnB identity; exec is default-deny (only allowlist rules tagged scope=mcp run); command output

Turn any OpenAPI/Swagger/Postman spec into an MCP server — give your LLM live access to any API.

An MCP server providing web search, image search, and page scraping tools to LLMs without requiring API keys.

Unified MCP server for Gemini media generation --Nano Banana (images), Veo 3.1 (video), TTS, and Lyria 3 (music). Single Go binary, 12 tools, supports Gemini API key and Vertex AI.

An MCP server that lets AI publish markdown documents to a clean, themed web UI. One tool call creates a shareable doc.

Adds security capabilities like port scanning, TLS inspection, DNS enumeration, process monitoring, secrets scanning, HTTP header auditing, and CVE checking to Claude Code and Cursor.

MCP server that exposes any CashPilot instance to LLMs, enabling monitoring of passive income earnings, managing bandwidth-sharing services, and controlling fleet workers

The most powerful MCP server for Slack Workspaces. This integration supports both Stdio and SSE transports, proxy settings and does not require any permissions or bots being created or approved by Workspace admins 😏.

Enables AI editors and agents to publish, search, subscribe to, and lint semantic messages across named namespaces, and to check broker connectivity and API key health.

Live, reproducible crypto infrastructure benchmarks for AI agents: RPC latency, bridge fees, L1 finality, gas oracle accuracy, stablecoin pegs. Three tools (list_benchmarks, get_benchmark,query_prom), no API key, CC-BY-4.0 data.

Provides access to your VictoriaTraces instance and seamless integration with VictoriaTraces APIs and documentation for querying traces, services, and operations.