`hhstream-mcp serve --http` serves the surface over Streamable HTTP behind a bearer token, and `hhstream-mcp token mint|list|revoke|prune` issues those tokens. stdio stays the default and stays unauthenticated. The two are one feature, because neither works alone. A token checked by a process the caller spawned is a lock whose key is in the same pocket: over stdio the client starts the server and already holds the broker's 0660 control socket, which is why `mcp.enable`'s own option text says it "grants no access the `hhstream` CLI does not already grant". A port is the first time the caller is someone who passed no filesystem check on the way in, and that is the moment a credential starts meaning something. So the transport arrives with the credential, and the contract's "stdio, and only stdio" is rewritten rather than quietly broken. The store (`authorizations.py`) keeps SHA-256 digests, not tokens: nothing ever needs the secret back, so `authorizations.json` is not itself a credential. No salt and no KDF -- a token is 256 bits of `secrets`, so there is no dictionary to attack and a work factor would only slow the request path. Expiry is wall clock, the one place in this project where that is right: every broker deadline is CLOCK_BOOTTIME so an idle window survives an NTP step, but "valid for thirty days" is a calendar statement that has to outlive a reboot. Every read-modify-write takes a flock, because two processes write this file -- the server stamping `last_used` and an operator running `token mint` -- and the atomic replace alone prevents a torn read, not a lost update. `--toolsets` on a token, not just at launch, because the flag is per-process and one HTTP server has many callers: a per-process tool budget stops being a per-caller one the moment the transport is shared. The intersection applies, so a token cannot widen what the unit was started with. `server.build` takes a chooser instead of a fixed list to make that possible; the stdio path passes none and closes over its selection exactly as before. Three things in the request path are deliberate. `default_allowed_hosts` exists because the SDK's DNS-rebinding check is allowlist-only with no implicit localhost -- protection on with an empty list 421s *every* request -- so the allowlist is derived from the bind address rather than the protection being switched off to get a working default; a wildcard bind derives nothing and is refused, which makes binding every interface the case where the hostnames must be said out loud. The grant travels in the ASGI scope and not a contextvar, because in stateful mode the session manager runs the handler in a task owned by its own lifespan and a contextvar set in middleware would not be visible there. And a refusal is a 401 with an empty body that never echoes the token and never says which of unknown, revoked or expired it was -- the discipline `hhstream_live.server` already applies to a wrong phrase, with that app's own RateLimiter reused rather than a second one grown. This is NOT MCP's authorization specification, which is OAuth 2.1 plus RFC 9728 metadata discovery. A client that can only discover an authorization server will not connect; one that lets you set a header will. Documented as a limit rather than hidden, beside the two the SDK already imposes. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01KchcvnbfhhZhUHy83YL3Ya
hyprland-headless-stream-plugin
A Nix flake that runs a headless Hyprland session and publishes its frames on a persistent Unix socket, so any process that can open a socket can see the screen without owning a display.
Two parts:
- NixOS module —
services.hyprland-headless-stream: starts Hyprland with no physical monitor, and a small frame server beside it. - Package —
hhstream— the frame server (publishes frames) and its client (reads them). Pure Python standard library.
{
inputs.hhstream.url = "git+https://<host>/git/<owner>/hyprland-headless-stream-plugin.git";
# in your host config
imports = [ inputs.hhstream.nixosModules.default ];
services.hyprland-headless-stream = {
enable = true;
# Optional: the default is one 1280x720@30 rule with an empty name, which
# is Hyprland's wildcard and applies to whatever outputs the GPU has.
outputs = [ { width = 1920; height = 1080; refresh = 60; } ];
};
}
Then any consumer:
hhstream-client --socket /run/hypr-stream/stream.sock --count 1 --out frame.png
The socket is a plain file descriptor: the server serves every client that connects, and keeps running when one disconnects.
Watching a session: one port, a phrase per session
A session can publish its own screen on a web page, so a person can watch what an agent is doing from a phone. One port for the whole machine, and a path that is four words and a short tail:
hhstream session stream enable chromium-k3f9d2
# http://127.0.0.1:9988/amber-otter-lantern-harbor-7k2qp/
That URL is the whole interface — a browser <img> is the entire client, over
MJPEG — and the phrase in it is its only protection. No TLS, no second
factor: anyone who can reach the port and guess four words can watch. It is
never written to the audit log, and stream list does not print it.
Four things worth knowing before switching one on:
- It is per session and off by default. A session does not stream because it exists; it streams because somebody enabled it. What is published is that session's own container output, never the main one — the main output carries every other session, and putting it behind one session's phrase is the mistake this refuses to make.
- The phrase survives a restart. It lives in the session's record, so
somebody you read it out to keeps the URL you gave them.
disablethenenablerotates it. - Capture runs only while somebody is connected. An enabled stream nobody
is watching costs no
grimand no CPU. - Watching counts as activity. This is the one exception to "
touchis the only mark of activity": about once a minute the broker notices a connected viewer and resets that session's idle clock, so a long job you are watching on a phone is not reaped at three hours. An enabled stream with nobody watching keeps nothing alive.
services.hyprland-headless-stream.sessions.stream = {
enable = true; # runs hhstream-live; turns no stream on
# bind = "0.0.0.0"; # and openFirewall, to reach it from another device
# openFirewall = true;
};
Loopback by default, where the path to a phone is ssh -L 9988:127.0.0.1:9988.
hhstream session start <app> --stream starts an application and prints its
URL in one go, which is the usual way an agent sets one up.
Driving it from an agent: the MCP server
hhstream-mcp is the hhstream CLI behind a Model Context
Protocol surface, so an agent can look at this
desktop, put an application on it, and aim its one pointer and keyboard at that
application without writing command lines. The interface is frozen in
docs/CONTRACT-mcp.md.
It is split the way the protocol splits things:
- Resources are the state — ten of them, read by URI, and reading one
changes nothing.
hhstream://statusis whether the desktop is up,hhstream://sessionsis what is running,hhstream://sessions/<id>/logsis an application's own output,hhstream://pointeris who holds the input lease,hhstream://screenis a frame of the screen,hhstream://streamsis what is being published and who is watching. - Tools are the acts — twenty-three, one per CLI verb that does something.
session_startputs an application on the screen,pointer_acquiretakes the input lease,keyboard_typetypes,session_stream_enablepublishes the screen for a person to watch,session_killends a session.
A host decides what state to put in front of its model; the model decides what
to do. That is the whole of the split, and it is why shot is still a tool
(capturing is an act at a moment) while hhstream://screen exists beside it.
It is a thin wrapper and nothing more: every tool and every resource builds the argv list the CLI's own parser takes, runs the CLI's own handler, and maps what came back. The idle clock, the pointer lease, the allowlist and the exit-code table all stay where they were.
Install it with the module — off by default, because it is the surface through which a language model starts processes on this machine:
services.hyprland-headless-stream = {
enable = true;
sessions.enable = true; # the session, pointer and keyboard tools need the broker
mcp.enable = true; # puts `hhstream-mcp` on the system PATH
};
Then register it with a client. The transport is stdio — one process per client, spawned by the client, no port and no daemon — so the whole configuration is a command and an environment:
{
"mcpServers": {
"hhstream": {
"command": "hhstream-mcp",
"env": {
"HHSTREAM_SOCKET": "/run/hhstream/control.sock",
"HHSTREAM_FRAME_SOCKET": "/run/hypr-stream/stream.sock"
}
}
}
}
Both variables are the CLI's own and both are shown at their defaults, so they
can be left out unless this machine moved a socket. The account the client runs
as needs what the CLI needs: membership of the compositor's group (hhstream)
to read the frame socket, and of the broker's to reach the control socket. The
server cannot recover that for itself the way the CLI does — see
docs/CONTRACT-mcp.md §5 — so if shot reports it cannot read the socket, the
answer is "command": "sg", "args": ["hhstream", "-c", "hhstream-mcp"] or an
account in the group.
hhstream-mcp --list-tools and --list-resources print the two tables and
exit, which is the quickest way to check an install.
If twenty-three tools is more than a client has room for, --toolsets narrows
what is offered to whichever families are wanted — frames, sessions,
pointer, keyboard:
{ "command": "hhstream-mcp", "args": ["--toolsets", "frames,pointer,keyboard"] }
Resources are deliberately not narrowed by it: they are the host's context, not the model's tool budget. Nothing else about the server is configurable — it holds no state and caches no lease, and the pointer lease is an explicit argument on every gesture tool for exactly that reason.
| Document | What it is |
|---|---|
docs/CONTRACT.md |
the wire protocol and the module surface — the interface other people build against |
docs/CONTRACT-sessions.md |
the broker, the containers and the input lease |
docs/CONTRACT-mcp.md |
the MCP surface: the resource URIs, the tool names, their arguments and the error mapping |
docs/ARCHITECTURE.md |
how the pieces fit: compositor, capture, server, client |
README.dev.md |
how to build, test and hack on it |
examples/README.md |
the demo that films the screen: agent-eyes-demo.py |
Status: work in progress — the module and the test suite are being built.