"sqlite" matching MCP servers:

A read-only MCP server that syncs only the Telegram chats, folders, and forum topics you explicitly mark (via Telegram folders or watch.py) into a local SQLite index using Telethon, then exposes 13 read-only tools to an agent. Enables listing watched topics with unread counts, fetching new messages since last read, paging and date-filtered history retrieval with context budgets, full-text search over years of history (SQLite FTS5/bm25), activity stats, link/mention extraction, digests, and extracted entities such as tasks, decisions, promises, and questions with overdue tracking — all through user-defined aliases. No tool writes to Telegram, keeping the integration strictly read-only.

Local-first personal memory for AI agents. Ships its own SQLite memory store, so it runs standalone: agents propose and recall confirmed memory, while only the human can confirm, from a separate CLI. Optionally uses the macOS Hive app for encrypted vaults. Also provides a shared board for coordinating several agents.

Lets separate coding-agent sessions coordinate through a shared, role-addressed mailbox instead of a human relaying every message, over a single local SQLite file or a hosted server with many isolated channels. Messages can be sent as tracked obligations that stay open until one side resolves and the other confirms, alongside threads, full-text search, work statuses, and an append-only versioned pin system where protected changes require recorded agreement from every declared role.

MCP coordination primitive for multi-agent workflows. Lets multiple AI coding agents (Claude Code, Cursor, n8n, custom clients) discover each other and exchange messages and tasks via a shared SQLite-backed message bus.

Local SQLite archive and MCP search service for the Telegram channel @markettwits, enabling users to query asset-specific twits by instrument and time range.

An MCP server that lets AI agents register a name and bio, discover one another, exchange messages, and be woken when mail arrives rather than polling, backed by a shared SQLite database over stdio for one machine or HTTP for a team.

Local-only MCP server that exposes Beeper Texts data (messages, chats, contacts) from the macOS Beeper Desktop SQLite database for AI assistants and automation tools, supporting search and media retrieval across multiple platforms.

Enables multiple AI agents and humans working in the same project to share status, exchange messages, and claim files through a local collaboration board. It supports project-specific enablement, conflict-aware file claims, and shared state via SQLite.

A Python MCP server that provides AgentRadio primitives (create_thread, send_message, wait_for_mention) for agents across different workspaces to collaborate over a shared radio channel via SQLite or HTTP hub.

Enables Claude and Codex sessions on the same host to communicate across different session systems via shared SQLite rooms, with named participants, durable ordered messages, offline delivery, and wait-based message handling.

A Model Context Protocol (MCP) server that empowers LLMs to schedule persistent background jobs on servers/NAS, recursively crawl web documentation into an offline SQLite RAG knowledge base, and dispatch smartphone push notifications with interactive approvals.

Lets you read WhatsApp history from the macOS app's own SQLite database without QR pairing or ban risk, with optional token-gated replying.

Provides access to Fellow.ai meeting data including transcripts, summaries, action items, and participants, with local SQLite caching for fast searches and offline access.

Full-featured personal WhatsApp MCP server: read and full-text search all chats, send, reply, react, edit and delete, media as raw files, groups and communities, multi-account and live notifications. Rust server with a Go whatsmeow bridge, local SQLite.

Enables MCP-capable agents to record, search, update, and export durable project notes from a local SQLite store and coordinate asynchronously through a shared blackboard, all over stdio without cloud infrastructure.

Provides local stdio MCP discovery, read-facing Telegram tool definitions, and an opt-in SQLite CRM for lead, group, and template management with quick-reply previews, while native authentication and all write actions remain gated and disabled.

A headless local stdio server that gives an MCP-compatible assistant durable relationship memory for LinkedIn contacts — resumable ingestion into SQLite, source-backed labels, organizations, opportunities and follow-ups, plus revision-checked draft preparation held in an outbox. It enables evidence-based classification and reply drafting from your own approved LinkedIn API access without any automatic sending, browser automation, or telemetry.

A demonstration MCP server that provides access to a SQLite employee database with tools for querying users and profiles, sending emails via Mailtrap, and proposing project teams based on employee skills.

Enables triaging incoming messages by classifying them into a small bounded set of action categories with a fast model, then routing each one to dismiss noise, send notifications for action items, or optionally auto-register calendar events. Users bring their own source, notifier, and calendar through small adapter interfaces, with verdicts and state kept in local SQLite storage.

Enables AI agents to interact with your personal WhatsApp account to search messages, list chats, and send messages. It stores all authentication and message data locally using SQLite for privacy and direct multi-device API connection.