Provides LLMs with local filesystem operations (read/write files, list directories) and command execution via MCP, enabling file management and task automation within AI clients.
Provides local, read-only MCP tools that expose a specified workspace's directory listing, file contents, text search, git status, and git diff to AI clients.
Provides sandboxed file system tools (read, write, search, list, watch) over the Model Context Protocol, enabling resume matching and analysis workflows via an agent.
Exposes the agent's sandboxed file tool over stdio so any MCP client can retrieve the contents of a UTF-8 text file inside the working directory, with failures returned as recoverable error strings instead of exceptions. It lets the same ReAct loop swap in-process dispatch for an MCP hop without changing tool signatures.