At a glance
Config blocks for both are in MCP config.
stdio: the CLI relay
phoneuse mcp --stdio (CLI 0.5.0 and later) gives a stdio-only client your
cloud phones. It reads MCP messages on standard input, sends each one to
https://mcp.phoneuse.com/mcp with your key, and writes the answers to
standard output. Nothing is interpreted on the way through, so every rule on
this page for HTTP applies: the key’s scopes decide which tools exist, and
there are no progress notifications or human takeover prompts. The CLI refuses
to send the key over plain http to anything but your own machine.
Nothing but the transport writes to standard output, because standard output
is the wire. Diagnostics go to standard error, which is where the startup line
you see comes from.
HTTP
The endpoint isPOST /mcp. It speaks JSON-RPC, in JSON response mode, and it
is stateless.
Stateless means a fresh server and transport are built for each request, and
that leases travel as explicit parameters rather than living in a session.
There is nothing to resume and nothing to tear down, which is why GET and
DELETE on the same path answer 405 with an Allow: POST header.
Two protections run on every request, and a client that trips either is
refused:
- Host checking. In hosted mode only the deployment’s public host is accepted. Locally only loopback hosts are.
- Origin refusal. Any request carrying a browser
Originheader is refused. Without this, a web page could rebind its own hostname to loopback and drive your device with no cross origin preflight standing in its way. Loopback binding stops callers on other machines; it does not stop this.
What stateless HTTP cannot carry
Two protocol features need a live bidirectional session, and this is the part worth reading before you design a loop around them. Progress notifications. An action blocks until the device commits. A client that sent a progress token would be told the action was dispatched and is awaiting device commit, but over stateless HTTP, and over the CLI relay in front of it, there is no channel for a mid request notification, so nothing arrives. The server does not fail the action over it: progress is a transport capability, never a promise the tool surface makes. Human takeover. Elicitation is a request from the server to the client, so it also needs a live session. Over stateless HTTP it never happens, and the caller sees a terminal outcome instead. The substitute for both is the same one, and it is not a workaround: pass anidempotencyKey with your action and use get_receipt to find out what
happened. That path works on every transport, survives a lost response, and
survives a restarted client. See
Progress and takeover.