Exactly-once execution for irreversible agent actions: an agent claims the right to run an effect, and a retry after a lost response returns the sealed result instead of charging again. 12 tools over stdio, including a gateway mode where the agent holds a single-use ticket and never the provider key.
Remote execution layer for agentic systems exposing 64 production tools via MCP for file, network, system, text, git, crypto, and monitoring operations.
Enables SSH command execution, file uploads/downloads, and multi-server management with zero-config inline credentials, supporting async jobs and AI-readable output.
A toolset for executing commands and transferring files or directories on remote servers via SSH. It supports both direct connection parameters and pre-configured server profiles for seamless remote infrastructure management.
Enables a standard authenticated MCP client to dispatch three controlled operations — command execution and scoped file reads/writes — to a remote lightweight agent through Vercel, with encrypted relaying, atomic writes, and Redis-backed audit logging.
