"A local vector-based search engine for personal documents" matching MCP servers:

Lets AI agents search and read your personal Telegram and WhatsApp conversations through a self-hosted, read-only MCP server backed by a single SQLite file.

Enables a trusted MCP assistant to access a personal Telegram account for finding existing chats and contacts, reading bounded history, preparing immutable message previews, and deliberately sending or replying only to explicitly authorized messages.

Enables connecting a personal WhatsApp number to any MCP client, providing tools to send, search, and manage WhatsApp messages, with an optional auto-reply feature.

An MCP server that wraps instagrapi to read, engage, and send DMs from a personal Instagram account, supporting 24 tools for auth, profile, engagement, and messages.

Local-first personal productivity MCP server bundling email, calendar, messaging, search, and image generation tools with BYOK and no cloud dependency.

Enables running the entire LinkedIn sales motion inside Claude Code, including content creation, audience warming, outreach, and booking calls.

Personal Gmail MCP (InternalBeyond external version) is a fully external Gmail MCP server compatible with any Streamable HTTP MCP client, offering 18 tools for searching, reading, composing, sending, and managing Gmail emails, threads, drafts, and labels via a secure OAuth flow deployed to Render.

Private MCP server for managing Gmail, custom IMAP/SMTP email, Slack notifications, and personal notes stored in SQLite.

A read-only MCP server that lets AI search and read both sides of a user's own LINE Desktop chat history on macOS using local database snapshots, without needing a LINE Official Account or altering unread state.

An MCP server that enables AI agents to pause and request human approval or information via Slack, Telegram, or macOS dialogs before proceeding with actions.

Enables searching Telegram messages and chats, retrieving recent messages, and extracting text from attached documents (PDF, TXT, MD, CSV) using your personal Telegram account.

Enables local import and querying of Tokopedia purchase data, including orders, shipments, payments, chats, and products, with record history, draft seller messages, and budget-aware purchase plans. It supports search, filtering, pagination, and atomic idempotent snapshots while keeping unsent drafts and unordered plans clearly marked.

Local tools that let your AI use Mail, Calendar, Contacts, Teams, Slack, WhatsApp (Mac), OneDrive, Google Drive, Notion, Outlook (Windows) and Office files on Mac and Windows. Runs on your computer.

Provides over 1,000 creative ways to decline requests across four categories (polite, humorous, professional, and creative). The MCP server wraps a REST API to help users craft professional rejections through natural language interactions.

Connects AI agents to anonymous strangers for asking and answering questions in character.

Enables MCP clients such as Claude, Cursor, and VS Code to work with personal Microsoft Teams accounts at teams.live.com, letting users list chats, read messages, find unread conversations, review recently sent messages, and send messages on request. It can be run locally over stdio or deployed as a remote HTTP server on Cloudflare Workers, with each user signing in through Microsoft's device-code flow.

Connect Claude to your personal Telegram account via MTProto to read messages, search chats, send replies, forward files, and more using your real account.

Provides Claude with read-only access to your WhatsApp chat history entirely on your local machine, enabling natural language search, summarization, and retrieval of messages without sending data to the cloud.

Enables MCP-capable AI clients to search both sides of a user's own macOS LINE Desktop chat history — listing chats, reading messages, searching text, and pulling recent activity from local read-only database snapshots. It never sends messages, marks chats read, clicks through the UI, or requires a LINE Official Account.

An archived MCP server providing 14 tools (bant_qualify, ocr_extract, asr_transcribe, etc.) originally built on Python/FastAPI/Cloud Run.