"Conda-Forge" matching MCP servers:

Enables AI assistants to interact with conda CLI commands through the Model Context Protocol, providing structured tools for built-in and plugin commands while enforcing configurable read-only, write, and exec policies.

MCP server to control Onda terminal from AI agents, providing tools for splitting panes, running commands, managing tabs and workspaces, and orchestrating multi-agent workflows across multiple windows.

A deliberately narrow, approval-gated workspace server that safely reads and writes files and runs allowlisted commands only inside one configured workspace, requiring visible approval for every write, process execution, and file read, with stale-overwrite protection and symlink-escape rejection.

Connects an MCP conversation to explicitly authorized user-owned machines over OpenSSH, enabling host discovery, operator-approved planning, command execution, and persistent receipts under controlled access.