vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
hyperhive/hive-agent-mcp
History
Repository files (latest commit first)
Filename Latest commit message Latest commit date
damocles 79c43a15d8 hive-c0re: scope list_schedules to what the requester can actually act on 
handle_list_schedules took no requester and returned every schedule
unfiltered, unlike cancel_schedule/edit_schedule/fire_schedule_now
which all gate on the shared ownership predicate (self, operator, or
subtree via topology::is_descendant_of). list_schedules now filters
through the same predicate, renamed cancel_authorized ->
schedule_authorized since it backs all four verbs now, not just
cancel.

Fixed five stale 'every schedule' / 'unfiltered' claims found while in
here: filter_ghost_schedule_targets's doc comment, the list_schedules
MCP tool description, docs/tools/scheduling.md's per-verb section
(already self-contradicting its own top-of-file subtree-scoping claim
before this fix), and hive-core-agent-sock's ListSchedules/Schedules
wire-type doc comments (including a stale '(privileged)' marker from
the pre-topology-subtree model).

Credit to atlas: independently found the same fix while finishing
PR #4233 (which documents this bug per mara's 'fix it, don't document
it' ruling) and caught two stale doc spots I'd missed
(hive-core-agent-sock's comments) plus proposed the
schedule_authorized rename. Compared diffs directly before either of
us pushed; he dropped his scheduling.rs changes so we didn't collide.

fixes #4237
2026-09-11 18:05:13 +02:00
..
src hive-c0re: scope list_schedules to what the requester can actually act on 2026-09-11 18:05:13 +02:00
Cargo.toml refactor(sock): one socket client, retry as a policy value 2026-07-26 22:44:48 +02:00
README.md prompts+docs: the lifecycle tools reach the whole subtree, not just direct children 2026-09-11 15:23:50 +02:00

README.md

hive-agent-mcp

The built-in hyperhive MCP server every agent gets by default. Runs a long-lived streamable-http listener (the hive-mcp-http systemd unit) that claude reconnects to each turn via --mcp-config — this avoids the per-turn stdio re-registration race that a spawned-per-turn server would hit. HTTP is the sole transport; there is no stdio mode here.

When to use it

This is where the core hyperhive tool surface lives: send, recv, remind, get_loose_ends, set_status, get_agent_meta, lifecycle (kill/start/restart/update on the agent's own subtree), scheduling, and the approval-request tools. Reach for this crate when you're adding or changing a built-in tool rather than an extraMcpServers add-on — those are separate stdio bridges (see hive-bash-mcp, hive-matrix-mcp) that dial the harness socket or their own daemon instead of living here.

Shape

  • mcp/ — the tool surface itself: one handler per tool, dispatch through client.rs back into the hyperhive broker (/run/hive/mcp.sock) or, for loose-ends v2 (todos/reminders), the in-agent socket the hive-agent harness serves.
  • client.rs — socket client to the hyperhive broker.
  • send_allow.rs — enforces the per-agent hyperhive.allowedRecipients allow-list on send.
  • paths.rs — socket + state path resolution shared with the harness's own paths.rs conventions.

Sibling of hive-agent (the serve loop that renders the --mcp-config blob pointing here). Standalone bin crate so the always-on MCP server doesn't need to link the whole turn-loop lib.