Nexus Shell Agent Bridge

The usual way to let an AI agent touch a server is to give it credentials: a private key path in a JSON config, an environment variable, or a raw shell it can type anything into. That works right up until it doesn't — and you find out from the audit log, if you kept one.

Agent Bridge inverts it. The agent getscapabilities, neversecrets. It asks Nexus Shell to run something on connectionabc123; Nexus Shell holds the key, opens a visible tab, runs it, and hands back the output. The agent never learns the credential, and you are looking at a GUI the whole time.

- No network port.Unix domain socket at~/Library/Application Support/NexusShell/agent-bridge.sock,chmod 0600. At the filesystem layer, only your user can reach it.
- Same-uid enforcement.Afteraccept,getpeereidmust report the caller's uid matches the app's own — otherwise the connection is droppedbefore any protocol logic runs.
- The app derives the agent's identity itself—LOCAL_PEERPID→ parent pid →proc_pidpath. Whatever the client claims about itself is treated as spoofable and used only for display. Consent is keyed on the path the app resolved.
- Per-agent consent.The first tool call from a given agent raises an approval dialog inside Nexus Shell. Revocable whenever you like.
- Secrets never cross the boundary.No tool can read a stored password or private key. Connections are referenced byconnection_id.
- Everything is audited.One JSONL record per tool call and connection event.password,passphrase,content,content_base64anddataare replaced with a redaction marker;commandandtexttruncate at 200 characters. Rotates at 5 MB, written0600.
- You can watch and take over.Terminals the agent opens are real tabs, badged as agent-opened.

- No create, edit or delete tools for monitors.
- No settings-mutation tools of any kind — an agent cannot reconfigure the app, and cannot turn off its own audit trail.
- list_session_logsreturns metadata only: server, title, time, duration, size. Never the recorded terminal content.

Turn onSettings → Agent Bridge. The panel shows a short instruction. Paste it into your agent and the agent registers the MCP server and links the skill folder itself — no hand-editing JSON, no copying socket paths.

Then talk to your agent the way you already do: "check why nginx is failing on the staging box", "pull the last 200 lines of the app log", "switch that host from password auth to a new ed25519 key".

macOS 14.2 or later on Apple Silicon. The direct-download or Homebrew build —brew install --cask viewer12/tap/nexus-shell. Any MCP client; we test against Claude Code and Codex.

Does the agent get my SSH passwords or private keys?No. Secrets stay inside Nexus Shell and are never returned over the protocol. Your agent references a server by itsconnection_idand never sees the credential behind it. This is enforced in the tool layer, not by convention.

Is there a network port open?No. It's a Unix domain socket with mode0600, so only local processes running as you can connect — and the same-uid check happens before any protocol parsing. Nothing is relayed through nexusshell.app.

Is this just a chatbot bolted onto a terminal?The opposite. Nexus Shell is theserver; you bring the agent. There's no model, no prompt and no vendor lock-in in this feature. (Nexus Shell does also have a separate built-in AI assistant on ⌘L / ⌘K that uses your own API key. Different feature.)

What happens if the agent does something dumb?You see it happen in a real terminal tab and can take over mid-command. Afterwards the JSONL audit log tells you which agent called what, when, and what came back — with secrets redacted. Agent Bridge reduces blast radius and makes actions reviewable; it does not make an agent correct, so point it at staging before you point it at production.

Is it stable?It ships marked experimental. The security boundary is the part we're most confident in; the ergonomics are still moving. Report problems tosupport@nexusshell.app.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

A SSH MCP Server written in python. Which builds upon a sophisticated tools and permission layer. Including Skills, Docker and Systemctl toolset and some runbooks.

Connect to, configure, and monitor Cisco network devices like routers and switches via SSH.

Production-ready MCP server for AI-driven console automation and monitoring. 40+ tools for session management, SSH, testing, and background jobs.

Hetzner Cloud MCP Server — (Cloud API + SSH)

Hetzner Cloud MCP Server — two management layers (Cloud API + SSH) with 60 tools. Manage server power, snapshots, firewalls, DNS, plus SSH into servers for service control, log viewing, Nginx management, MySQL queries, and system monitoring. Self-hosted PHP, MIT licensed.

Provides remote machine control capabilities, eliminating SSH overhead for token-efficient system operations.

Orchestrates remote server tasks via SSH and SFTP with a persistent queue. Ideal for DevOps and AI agents.

Securely execute remote commands and perform file operations over SSH, with support for both password and key-based authentication.

An MCP server providing read-only server monitoring tools to AI assistants. Runs predefined diagnostic commands over SSH and passes only the results to the LLM - your server credentials and shell are never exposed.

MCP server that exposes an SSH server list from a TOML config file