Platform

The portal between your agents
and your fleet.

sshportal.ai sits between anything that speaks MCP and every server you own. Agents get nine purpose-built tools instead of a raw socket; you get a policy gate on every command, an approval queue for the risky ones, and a replayable record of all of it. Humans share the same fleet through a real browser terminal — same rules, same audit trail.

One URL in

Claude Code, claude.ai, Cursor, Codex, Gemini, Grok, your own tool loop — every client points at https://sshportal.ai/mcp. OAuth consent for browser connectors, a bearer token for CLIs. That's the entire integration.

Your rules in the middle

Scope decides which servers an agent can even see. Policy decides what runs, what's blocked, and what waits for a human. Both are re-checked on every single call — not once at connect time.

Every move recorded

Person or agent, every session lands in a hash-chained, tamper-evident audit log with full replay. "What did the agent do at 3 a.m.?" is a video, not a guess.

Nine tools.
A whole ops vocabulary.

Raw SSH gives an agent a socket and wishes it luck. The portal gives it a vocabulary that matches how agents actually work: discover what's in scope, run one-shot commands, or hold a full interactive session — install wizards, REPLs, htop, anything with a PTY.

Sessions are first-class: an agent can open one, keep state between steps, and your teammates can attach to the same PTY from the console and watch — or take over.

  • Discovery that respects scope. list_endpoints only ever returns the servers you attached to that agent.
  • One-shots and long-running work. run_command for the quick read, sessions for the stateful fix.
  • Approvals built into the loop. wait_for_approval lets the agent block politely until you click.
Get your MCP URL
tools/list · https://sshportal.ai/mcp
list_endpoints    servers this agent may touch
run_command       one command, one server, output back
open_session      interactive PTY on an endpoint
send_input        type into a live session
read_output       read what the session printed
list_sessions     this agent's live sessions
attach_session    rejoin one that's still running
close_session     tear it down cleanly
wait_for_approval block until a human decides
scope + policy re-checked on every call

A policy engine that sees
every command first

Rules are yours: regex or prefix patterns, org-wide or per-server, each ending in allow, deny, or require approval. Explicit rules always run first; the org-wide mode decides what happens to everything else.

  • Standard — built-in speed bumps catch the classics (reboots, rm -rf, schema drops) and send them to the queue; the rest runs.
  • Allow all — trusted-fleet mode: only your explicit rules intervene.
  • Approve all — zero-trust mode: everything not explicitly allowed waits for a click.

Approvals land in the console and the agent waits in-band. One click and it continues mid-conversation; deny it and the agent gets told no, with the reason on record.

policy · org: acme · mode: standard
allow             ^(df|du|free|uptime|systemctl status)
allow             ^journalctl  read the logs, always
require_approval  ^systemctl (restart|stop)
require_approval  ^(reboot|shutdown)
require_approval  ^apt(-get)? (upgrade|dist-upgrade)  prod only
deny              rm -rf /
deny              ^DROP (TABLE|DATABASE)

[queue] ops-bot on db-01: systemctl restart postgresql
[queue] ▸ Approve · Deny 
1 approval pending explicit rules run first, in priority order

Everything around
the shell.

The portal is more than the pipe. The console is a full operations room for the same fleet — for the humans on the team and the agents beside them.

A real terminal

Full xterm in the browser, keyless, on any server in the fleet. No VPN, no bastion hops, nothing to install on your laptop.

File transfers

Drag a file onto the terminal and it lands on the server; pull one back just as easily. Every transfer is logged with who, what and where.

Watch mode

Open any live session read-only and watch the agent work, keystroke by keystroke — or attach to the same PTY and drive beside it.

Replay & audit

Sessions are recorded into a hash-chained log. Scrub through any session after the fact and prove to anyone exactly what ran.

Hosted agent runs

Launch Claude Code, Codex, Gemini or Grok CLIs in a locked-down container we host. Its only network reach is your fleet, through the same scoped MCP tools.

Built-in AI chat

No agent of your own yet? Chat with your fleet straight from the console. Same scopes, same policy, same recordings — batteries included.

Dedicated egress IPs

Reach your servers from an address that's yours alone. Allowlist it in your firewall and port 22 goes dark to the rest of the internet.

Unlimited teammates

Invite the whole team — seats are free. Members get scoped access and the same keyless treatment; owners manage policy, approvals and billing.

Point an agent at it.
That's the setup.

Add a server, deploy an agent, paste one MCP URL into your tool of choice.

https://sshportal.ai/mcp
Get started · $9.95/mo