"A GitHub repository for a RAG documentation scraper" matching MCP servers:

An MCP server that gives an AI agent controlled access to a Selectel cloud account: OpenStack cloud servers, S3 object storage, and account billing.

Enables advanced semantic search and document management by integrating the GroundX API with Claude Desktop and GitHub Copilot. It supports local file uploads, website crawling, and Google Drive synchronization for RAG workflows.

Enables Google# MyData from (JSON (server name is

Connects any MCP client to a Nextcloud instance through official WebDAV and OCS APIs, enabling browsing, searching, uploading, downloading, copying, moving, and deleting files and folders, plus managing favorites, public links and user/group shares, and the trash bin. Authentication uses the browser-based Login Flow with a saved app password.

Enables retrieval-augmented generation search and chat over documents stored in Azure Blob Storage, with a Streamlit app for uploading files and interacting via a LangGraph agent.

Enables ChatGPT to work with a user's personal WPS cloud documents across Writer, Spreadsheets, Presentations, PDF, Smart Documents, Smart Forms, and Multi-dimensional Tables, performing authorized cloud operations and returning verifiable WPS links without local installation or an always-on computer.

Enables secure one-time encrypted file and note sharing by encrypting data locally before upload and providing tools for sending, listing, checking, and revoking links.

Enables AI agents to run citation-backed retrieval over a read-only, bounded knowledge base, exposing a ranked search tool, document resources, and a grounding prompt that labels retrieved text as untrusted. The corpus can be loaded from local disk or from AWS S3, Azure Blob Storage, or Google Cloud Storage through their official SDKs, with fail-closed startup if a provider cannot be reached.

Enables ChatGPT to list, search, and read files from a user's Google Drive—including Docs, Sheets, Slides, and text files—through read-only Google OAuth access.

A Model Context Protocol server that provides seamless access to multiple storage services including S3, Azure Blob Storage, and Google Cloud Storage through Apache OpenDAL™.

Enables MCP clients to append and create Markdown notes in a Git-backed GitHub repository (Obsidian-friendly), with tools for appending, creating, reading, and listing notes.

Enables ChatGPT users to search and browse a private photo library, inspect metadata, and receive real image previews through read-only tools, while keeping encrypted sessions server-side.

Enables editing existing Docs, Sheets, and Slides in place, plus commenting, sharing, moving, and exporting files with native Google URLs returned. Provides 29 tools across Drive, Docs, Sheets, and Slides, using OAuth keys kept locally in ~/.gdrive-mcp/.

Enables Claude to search, read, create, and edit a user's personal WPS cloud documents, spreadsheets, and presentations—including reading and writing cells, replacing text, and discovering and running any of 619 WPS capabilities, with explicit confirmation required for destructive or sensitive operations. It runs remotely with one-time OAuth authorization, so no local install is needed.

MCP server giving Claude access to Tuta mail, calendar, contacts and drive. Supports mail modes (dedicated/shared/folder), trusted sender filtering with E2E verification, and Docker-based setup.

Enables Antigravity IDE to directly interact with Google Docs, Sheets, Drive, Gmail, and Calendar, with token-optimized operations to reduce context usage by 70-90%.

Enables AI agents to open, read, and edit Word and Excel documents through a local bridge, create Word files in existing SharePoint folders, and work with document content via an Office add-in.

Lets a coding agent upload files from disk to a Stickafile portal and return a shareable link, with the bytes going straight from disk to storage without entering the model's context. Also lists the portals a token can push to.

Enables AI clients to search a cloud-drive resource search engine and turn selected results into saveable share links, using a two-step search-then-retrieve workflow.

Read-only access to a local Hiberden backup catalog: list projects, archives, tapes, and jobs, check 3-2-1 coverage, and verify a stored copy by reading it back and re-hashing it. Runs against the catalog on your own machine, so nothing leaves it.