An interactive coding agent and MCP server that provides access to various AI models via the Tsinghua University lab proxy API. It enables users to inspect files and execute shell commands within their local directory using models like DeepSeek, GLM, and Qwen.
A Model Context Protocol (MCP) server with HTTP transport that implements JWT authentication, allowing secure tool execution and prompt handling with role-based access control.
An MCP server that intelligently filters and compresses tool outputs to reduce context window usage, saving up to 90% of tokens by removing noise such as passing tests and redundant information.
Enables autonomous forensic investigation of disk images by mounting evidence, scanning for malware, and generating courtroom-ready reports using SIFT Workstation tools.
Enables SSH command execution, file uploads/downloads, and multi-server management with zero-config inline credentials, supporting async jobs and AI-readable output.
Enables execution of ROS 2 CLI commands through the Model Context Protocol, supporting configurable timeouts, working directories, and secure command whitelisting.
Enables LLMs to interact with Discord channels by sending and reading messages through Discord's API, with a focus on maintaining user control and security.
A minimal MCP server that executes commands on remote hosts by delegating to the local ssh binary, supporting batch-mode execution and optional timeout.
Bypasses Claude Desktop sandbox network restrictions by providing tools to fetch any URL, execute network-capable CLI commands (yt-dlp, curl, ffmpeg), and read files created by those tools.