This MCP server is pre-implementation; it is intended to enable read-only agent interaction with Bitty debug and command protocols, with explicit fine-grained authorization.
An MCP server that gives an agent terminal and file-management capabilities, including running shell/Python commands, searching and reading files, and creating/editing/deleting files and folders.
An MCP server that enables agents to run commands interactively in live terminal panes a user can watch and type in, and to list, create, read from, and send keys to any session, window, or pane.
MCP server for permissioned, structured agent-to-agent communications, enabling agents to coordinate and negotiate through scoped, typed messages with authentication and audit logging.
Agent memory on a local SQLite file or on PostgreSQL with pgvector, with provenance, trust verdicts and explicit abstention when memory cannot support an answer.