hyperhive/hive-matrix-mcp
Repository files (latest commit first)
Filename Latest commit message Latest commit date
atlas 0e9b1c563d fix(#2860): no loopback default for the matrix homeserver
Third and last of #2860's agent-facing URL fallbacks. The operator's
ruling was "any special casing is done on the nix side - same binaries,
no hard coded fallback", so the default is deleted rather than replaced.

Every layer guessed the same wrong thing, and each guess was only ever
correct for a process sharing the host netns:

- nix/agent-modules/matrix.nix: matrixUrlDefault = localhost:8008, both
  as the option's default and as a sentinel the daemon unit compared
  against to decide whether to write HIVE_MATRIX_URL. Now nullOr str,
  default null, the guard is != null, and the doc says what forge.url's
  already says: null means "no matrix", not "guess one".
- nix/host-modules/hive-c0re/environment.nix: forwarded
  http://127.0.0.1:<port> when no gatewayHost was set. hive-c0re shares
  the host netns so it reads as harmless, but the value is handed to
  agents, which do not -- there it names the agent itself. Now forwarded
  only when there is a gateway vhost to name, matching the guard
  HIVE_MATRIX_PUBLIC_URL already uses twelve lines below.
- hive-matrix-mcp: paths::DEFAULT_HOMESERVER was the same address
  compiled in, so dropping the nix defaults alone would have left the
  daemon dialling loopback inside the agent's own netns -- the very bug,
  one layer down. homeserver_url() is now Option, and an account with no
  homeserver is skipped with a log, exactly as one with no token is.
  discover_token_accounts already refused to guess for the same reason.

Two comments taught the assumption back to the next reader ("shared host
netns means every agent container resolves localhost to the same
machine"); both now say which side of the netns boundary they describe.
MATRIX_HTTP keeps its value -- hive-c0re really does share the host
netns -- but no longer claims agents do.

Gated with nix eval against the extended agent-base config, as a pair:
with no url set the daemon unit carries no HIVE_MATRIX_URL, and with one
set it carries exactly that. Either check alone passes on a broken guard.
2026-08-03 20:34:36 +02:00
..
src fix(#2860): no loopback default for the matrix homeserver 2026-08-03 20:34:36 +02:00
Cargo.toml refactor(sock): one socket client, retry as a policy value 2026-07-26 22:44:48 +02:00
README.md feat(#2659): serve hive-matrix-mcp over persistent streamable-http, drop stdio bridge 2026-07-24 12:44:39 +02:00

hive-matrix-mcp

Per-agent matrix integration: a long-running daemon (hive-matrix-daemon) that holds a matrix-sdk Client + sync loop per configured account and serves the matrix tool surface (send_message, send_dm, list_rooms, read_room, …) directly over streamable-http. No stdio bridge, no per-turn respawn — claude reconnects to the same stable URL every turn.

When to use it

Look here when changing matrix tool behaviour, multi-account handling, or the incoming-event → todo/wake path. The daemon owns the whole lifecycle: per-account bring-up (accounts.rs, client.rs), the sync loop that sweeps invites/unread rooms into the harness's in-agent todo socket (timeline.rs, wake.rs), and the MCP tool router itself (mcp.rs).

Shape

One bin (hive-matrix-daemon, src/main.rs) built from the crate's own lib (src/lib.rs):

  • accounts.rs — multi-account config + the account→Client dispatch registry (main is always the hive-internal primary; extras come from HIVE_MATRIX_ACCOUNTS).
  • client.rs — session restore, stale-token recovery, avatar sync, cross-signing bootstrap.
  • timeline.rs / wake.rs — per-sync-callback invite/unread sweeps that push todos onto HIVE_AGENT_SOCKET.
  • handlers.rs — per-tool dispatch, returns protocol::DaemonResponse.
  • mcp.rs — the rmcp tool router + serve_http, resolving each call's optional account arg against the registry before calling into handlers.
  • paths.rs — per-agent path resolution (token file, matrix-sdk state dir, homeserver URL, accounts snapshot).