Compare

Sallyport and Britive

Per-call approval for MCP tool calls, and only for MCP tool calls.

Britive comes from just-in-time cloud access and has brought a real approval step to agent tool calls. Time-boxed grants and continuous evaluation signals sit behind it. On MCP they are one of the few vendors doing the thing we do.

ThemSallyport
Per-call human approvalMCP tool callsMCP, HTTP and SSH, one policy across all three
Arbitrary HTTP hostNoYes, through the reverse proxy
SSH with per-call approvalNoYes, and the executor holds no private key
Time-boxed grantsYesYes, checked at the boundary of every call
Tamper-evident journalLoggingHash-chained, sealed, with an open verifier

Where they are ahead

Cloud entitlement depth. If your agents mostly need short-lived roles in AWS, Azure and GCP, that is their home ground and they have been on it for years.

Where the difference is

Agents do not stay inside one protocol. The same agent opens a pull request, calls a payment API and restarts a service over SSH in the same session. One broker across the three keeps one policy, one approval inbox and one journal instead of three.

Read the security page before you decide

It says what the design holds by construction and what your own catalogue decides, hop by hop.

Connect my first agent

Free for 10,000 calls a month. No card.