"Exploring Memory Persistence in DeepSeek Technology" matching MCP servers:

Persistent encrypted memory for AI agents. E2E encrypted private vaults, shared knowledge commons, topic channels, and agent-to-agent DMs. 23 MCP tools, free, no API key needed.

Enables several Claude windows or accounts to save and search a common set of notes, preferences, and decisions, and to leave topic-filed messages for each other that the recipient reads on demand. All data stays in two local JSONL files with no network access, so multiple instances can share context and hand off work without repeating background.

Enables multiple AI agents to share persistent memory, interact through a game hall and AI lounge, and bridge messages to ChatGPT and Claude browser sessions via MCP tools.

An intelligent personal CRM that processes WhatsApp conversations to build a searchable knowledge base about contacts using diarization, transcription, and PII sanitization. It exposes MCP tools for semantic search, contact summaries, and reminder management within Claude Desktop.

Enables an AI assistant to place user-approved phone calls in the callee's language through your own Bland or Twilio account, with language detection, script generation, cost estimates, and safety guard rails. Includes a preview-then-confirm gate, plus call status, transcripts, and summaries.

Generate professional AI-powered presentations from a topic, raw text, or document file. Export to PPTX, PDF, image, or shareable link.

Enables agents to synthesize text with local IndexTTS zero-shot voice cloning and send the result as QQ voice messages through OneBot, with a health-check tool for service, model, and gateway status.

This server enables users to operate Claude Code functionalities 24/7 directly within Telegram. It provides advanced features including voice interaction, session memory persistence, and real-time Agentic Mode monitoring.

Wraps Claude Code as a server using the Model Context Protocol (MCP), allowing teams to interact with Claude Code through a Slack bot interface.

Enables conversational expense tracking via Telegram, allowing natural language registration, querying, and summarization of expenses, with persistence in PostgreSQL and support for multiple LLM providers.

Enables AI agents to search and act on Telegram conversations, groups, channels, files, and links, with semantic search, AI-powered knowledge extraction, human-in-the-loop approvals, and PostgreSQL/pgvector persistence.

MCP server that enables AI agents to send messages, photos, polls, and receive replies via Telegram with persistence and rate limiting.

Enables local agents to coordinate in IRC-style channels via stateless MCP, with a human webview and sqlite persistence.

Enables remote control of the Cursor AI agent via chat platforms like GitHub Issues or Telegram, allowing users to start sessions and receive summaries and prompts in a chat thread.

Enables AI chat sessions to exchange messages and structured data with each other, preserving provenance and conversation threads, so work in one chat can be reused in another without manual copying.

Enables AI assistants to publish, edit, search, and manage messages in Telegram channels via a set of MCP tools.

Lets AI agents notify people through a self-hosted Cue server: per-person budgets for each agent, quiet hours in the recipient's time zone, digests, importance ceilings and human approval with expiry, over push, e-mail, SMS, Telegram, Slack and webhooks.

A minimal MCP server for sending Slack messages, supporting both bot and user tokens with concurrent safety and an AI bot signature in user-token mode.

Send texts (SMS) and sign-in codes from your own Android phone and your own number from any AI app, check whether they went out, and read replies.

Enables MCP clients to send plain-text messages to a preconfigured WeCom group chat bot through a single send tool. It validates content size, restricts delivery to the configured webhook, and returns platform acceptance or error status without retries or persistence.

Enables AI agents and scripts to read and manage events on your account — guest lists with questionnaire answers, CSV export, check-in, approvals, invites and Text Blasts — through your own signed-in Chrome session, with no public API or official integration required. Runs locally over stdio, streamable HTTP, a REST API with OpenAPI docs, and a Python client.

Enables AI coding agents in different harnesses, projects, or machines to share encrypted peer-to-peer rooms and exchange messages directly, without any central server or account.

Enables AI agents to manage SimRelay SIMs: list, lock, release, read SMS history, and stream incoming messages in real-time via WebSocket.

Email for AI agents. Send and receive as markdown with human oversight.

Enables AI to send expressive stickers based on conversation context, with a built-in UI for managing stickers.

Enables MCP clients to read, search, organise, and manage IMAP mailbox messages, including saving attachments and drafting replies, while treating mail content as untrusted and keeping write capabilities opt-in.

Official MCP server for PushNotif.biz.id. Enables AI agents to register websites, generate one-line SDK snippets, and broadcast or schedule Web Push (VAPID), Android FCM, iOS APNs, In-App Popups, Live Activity Toasts, and automated RSS push notifications with real-time CTR analytics.

Human-in-the-loop approval inbox for AI agents: an agent proposes an action (send email, post comment, run a command), a human approves, rejects, or edits it from a web, mobile, or Slack/Discord/Telegram inbox, and the agent only runs on approval. Full audit trail, self-hostable (MIT).

Enables an AI agent to wait for and retrieve SMS verification codes forwarded from your iPhone, returning each code once, and to list recent texts for login links or non-numeric messages. It runs in your own Cloudflare account and deletes stored texts after 15 minutes.

Lets any MCP client drive the recruiting workflow in natural language: create roles, screen CVs, schedule and manage candidate interviews, and read back scored reports with transcripts.