"OpenAI's Web Retrieval Infrastructure" matching MCP servers:

Enables AI agents to fetch, crawl, extract, and search web content through a unified set of tools, with automatic routing to specialized backends.

An open-source MCP server providing AI agents with neural web search via Exa and tiered web fetch (Exa, local browser, Firecrawl) as a drop-in replacement for built-in web tools, preserving provenance and guarding against SSRF.

Enables MCP-capable agents to perform reliable web search and content fetching through a single server that automatically fails over across multiple providers. It handles keyed or keyless authentication automatically and returns clean Markdown or text results.

Enables AI agents to parse PDFs and search local document context through multimodal extraction and vector-based retrieval, all exposed as MCP tools.

Enables retrieval-augmented generation by embedding queries with a chosen provider (e.g., OpenAI) and searching supported vector stores (Pinecone, pgvector) to return relevant content.

An evaluation harness that probes MCP-based retrieval servers for calibration, relevance, coverage, citation integrity, and more, also exposing the probes as MCP tools for assistants and CI agents.

Enables AI agents to manage virtualization, Active Directory, Windows hosts via WinRM, PostgreSQL databases, and shell/SSH environments through Model Context Protocol tools.

Enables retrieval and cleaning of official documentation content for popular AI/Python libraries (uv, langchain, openai, llama-index) through web scraping and LLM-powered content extraction. Uses Serper API for search and Groq API to clean HTML into readable text with source attribution.

Enables AI agents to search and retrieve over 89K skills on-demand at runtime, eliminating the need to manually install skills upfront.

Enables web search using DuckDuckGo and content retrieval from URLs, returning markdown with pagination support.

Enables Claude AI to automatically audit AWS cloud resource configurations, diagnose security vulnerabilities, and generate high-availability optimization reports.

An MCP server that retrieves relevant PDF chunks via local embeddings and returns them to IDE agents (Cursor, Kiro, Claude Code) for answer generation.

Enables Terraform HCL plan generation, drift detection, and strict human confirmation approval barriers for cloud infrastructure management.

Enables Codex to send text tasks to ChatGPT web, await responses, continue conversations, choose reasoning effort, and manage projects through MCP tools on macOS.

MCP server providing free, IP-direct tools for web search, crawling, anti-detect browsing, and structured data from Wikipedia, Wikidata, GitHub, and YouTube.

Enables a locally-run LLM to search the web, fetch pages as markdown, make arbitrary HTTP requests, and optionally render pages with headless Chromium.

Enables AI agents to drive a logged-in ChatGPT web session over CDP, including managing projects and chats, sending messages with file attachments, and retrieving long Pro replies.

A local MCP server for semantic search over RSS/Atom feeds, providing tools for ranked search, trending topics, digests, and feed health monitoring without requiring an API key.

A local MCP server providing web search, page extraction, and safe browser automation tools for Hermes, Claude Code, and other MCP clients.

Bridges AI agents with watsonx.data document libraries, enabling natural language queries and intelligent retrieval from document libraries.