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

DREAM LAUNCHERS INTERIORS PRIVATE LIMITED

Enables searching and accessing OCR text from millions of digitized documents in Gallica, the digital library of the Bibliothèque nationale de France, through MCP tools for text search, snippet retrieval, and full-text download.

Provides AI assistants with programmatic access to the National Library of Sweden's digitized historical newspapers, enabling full-text search, filtering, timelines, and image retrieval across over 2.2 million pages.

Provides access to the impresso corpus of digitized historical newspapers, enabling article search with keyword-in-context snippets, filtering, facets, and source metadata retrieval.

MCP server for Anime News Network, enabling search of anime and manga encyclopedia entries, retrieval of details like cast, staff, and episodes, and access to news feeds. No API key or configuration required.

Minimal MCP server exposing Espaciarte's public space discovery API to AI clients, enabling geo-search and retrieval of published space details.

MCP server with full coverage of the Gramps Web API REST endpoint functionality. Super-powers for your genealogy research with the help of AI.

Enables searching and reading digitized Nordic literature and encyclopedias from Project Runeberg, including full-text search, page reading, and work/chapter metadata retrieval.

Enables Claude to query the DocuSky digital humanities platform, providing full-text search across its databases, distribution and tag statistics, and full-text retrieval of individual documents, with optional credentials for accessing a user's own private collections.

Enables AI agents to interact with the Hooktheory API for chord progression generation, song analysis, and music theory data retrieval.

This server enables AI models to access the Städel Museum's digital collection via OAI-PMH, allowing harvesting of records, retrieval of multilingual metadata, and fetching of high-resolution images.

Provides access to ancient text corpora via stdio, enabling corpus listing, status checks, searching, and text/metadata retrieval with provenance envelopes.

Enables search and retrieval of Shakespeare monologue metadata including character, play, first line, and paraphrases through various tools.

Enables keyless search and retrieval of millions of openly-licensed Creative Commons images and audio, with ready-to-paste attribution and license-awareness built into every result.

Provides read-only access to ORACC open cuneiform data, enabling listing of projects, retrieval of metadata, manifests, and text excerpts, and searching of catalogues.

Enables AI assistants to query the MusicBrainz music database for artists, albums, recordings, and labels. It provides tools for advanced searches, detailed metadata retrieval, and accessing cover art information.

Enables searching and downloading images, videos, and multi-image galleries from e621, rule34, E-Hentai/ExHentai, and Pixiv, with support for batch downloads, URL-based retrieval, and optional animation conversion to GIF/MP4.

Serves a scholar-approved Islamic corpus of Qur'an and hadith passages to any MCP client with server-side refusal enforcement. Enables natural-language questioning, retrieval, policy checking, and honest corpus coverage reporting while preventing fabricated answers.

Provides access to Iconify's 200,000+ open source vector icons from 200+ icon sets, enabling search, browsing, and retrieval of icon data with framework usage examples.

Read-only Model Context Protocol server for the US National Archives Catalog API, enabling search and retrieval of archival records, child records, extracted text, comments, and tags.