微信4.0数据库解密工具 | WeChat 4.0 Database Decryptor — memory-based key extraction, real-time message monitoring, MCP Server for Claude AI

天锐绿盾（Tipray Green Shield）授权解密申请助手：Windows F8 快捷键 + 本机 MCP Server，支持文件/文件夹、官方审批链与 AI Agent 自动续跑。

微信本地聊天记录查询工具：解密本地 WeChat 数据库，提供命令行查询与 MCP 服务供 AI Agent 调用。WeChat local chat history query — decrypt local SQLCipher 4 databases, CLI + MCP server for AI agents. Pure Python, read-only, nothing leaves your machine.

MCP server giving AI agents local AES-256-GCM file encryption — encrypt/decrypt & passphrase gen (free), plus folder encrypt/decrypt (Pro). Keys & files never leave the machine.

MCP server for your personal LINE account — read, search and reply from Claude, Codex, Cursor… E2EE messages and media decrypted locally.

Invite an AI agent into a Pyunto diary: replies in the thread or serves Claude via MCP. Decrypts only on your machine.

Personal LINE MCP server for Claude and local AI agents. Read, reply, send images, and search LINE chats with local E2EE decryption.

A security-focused Model Context Protocol server for GnuPG: sign, verify, encrypt, decrypt and manage keys without exposing private key material to the agent.

Local WeChat (PC) chat data decryption & export tool — self-built SQLCipher 4 engine, zero DLL, zero network, zero license check. CLI + MCP Server.

Real-name identity for AI agents (国信智能体实名关联服务). Generates a local SM2 (Chinese national cryptography) keypair, links the agent to a real person via QR-code scan, claims a Verifiable Credential (VC), and generates/verifies SD-JWT Verifiable Presentations (VP) with selective disclosure. Also exposes SM2 sign/verify/encrypt/decrypt utilities. Keys and credentials never leave the machine — stored locally with SM4-CTR + SM3-HMAC encryption. 14 tools: identity_link, identity_status, identity_revoke, identity_vp, identity_verify_vp, vp_parse, vc_info, vc_raw, key_info, crypto_sign, crypto_verify, crypto_encrypt, crypto_decrypt, system_update. Runs locally via stdio (Node.js >= 18.13). Install: npm i -g realagent-mcp. Each agent requires a unique --agent-id (one agent-id = one identity = one SM2 keypair). Full docs: github.com/RedDateTech/RealAgentMCP

Read your Lumber logs in the terminal and from AI agents over MCP, decrypted on your own computer. Runs on macOS, Windows and Linux.

Lightweight MCP server demonstrating FF3 Format Preserving Encryption with multi-mode authentication. Shows how LLMs can securely encrypt/decrypt sensitive data while preserving format. Supports stdio and HTTP transports.

An email address for your AI agent. MCP server for Mailcycle: read, wait for and reply to mail, open attachments and send files, decrypted on your machine.

Apple Health MCP server for Claude Code & Claude Desktop — your AI agent reads your end-to-end-encrypted HealthKit data (sleep, HRV, cycle, weight, workouts), decrypted only on your machine.

All-in-one MCP server with 80+ developer tools — devutils, API, text, math, datetime, calculator, JSON diff/query, SQL format, epoch convert, AES encrypt/decrypt, RSA keygen, scrypt hash, regex replace, nanoid, CSV/JSON, hex encode, Unicode tools in a sin

An email address for your AI agent. Mailcycle lets an agent read, wait for and reply to mail at its own addresses: sign-up codes, verification links, support threads, attachments. Mail is decrypted on the machine running the agent. Mailcycle stores it sealed and can't read it. Needs a [Mailcycle](https://mailcycle.email/agents/) account on Scale or above, and Node 20 or later. ## Before you install: pair the agent On the machine the agent runs on: ```sh npx -y mailcycle-mcp pair --name "Support agent" ``` It prints a line starting with `MC1:`. In the Mailcycle app, open **AI agents**, paste the line, and give the agent an email address. The line carries the key the agent's mail is sealed to, so keep it private. It goes from your terminal to the app and never through Mailcycle. The server needs no other settings. It reads the key that pairing saved. ## Tools | Tool | What it does | |---|---| | `list_addresses` | The agent's addresses, and what it may send. | | `list_messages` | The newest messages, with a preview of each. | | `read_message` | One message in full, with its attachments numbered. | | `read_attachment` | Opens an attachment: text as text, images as images, anything else saved to a folder. | | `wait_for_message` | Waits for new mail, optionally from a sender or with a subject. Good for sign-up codes and verification links. | | `reply` | Replies to the sender of a message, threaded. Can attach files. | | `send_message` | Sends a new message, if the agent may send to anyone. Can attach files. | ## Sending Each agent has a send mode, set in the app: - **Reply only** (the default): it can answer whoever wrote to it, and no one else. - **Send to anyone**: up to 20 messages an hour per agent. - **Read only**: it cannot send. Mail an agent reads can contain instructions written by whoever sent it. Reply only limits what those can make it do. ## What sees what - **Mailcycle** stores mail sealed to keys it doesn't have. - **Your machine** holds the agent's key in `~/.config/mailcycle/agent.json`, readable only by your user. Remove the agent in the app to cut it off. - **Your model provider** sees whatever the agent reads. Also on npm as [`mailcycle-mcp`](https://www.npmjs.com/package/mailcycle-mcp) and the [official MCP Registry](https://registry.modelcontextprotocol.io) as `email.mailcycle/mailcycle`. Proprietary, © 2026 Northlab Studios Ltd. [Terms](https://mailcycle.email/legal/terms/).

Keyshade MCP - Model Context Protocol implementation for Keyshade