Hiveship MCP server

Read from the package source without running it. The installed server may list more.

• add_comment

  Add a comment to an issue

• configure

  Save Hiveship preferences for this machine, or record that the user declined. Preferences only \u2014 never send a token here; the API token comes from the environment and must not be written to a config file. Pass `skip: true` to record a decline so the user is not asked again.

• create_issuewrite action

  Create a new issue. Server defaults: status BACKLOG, priority NONE. Session-scoped agent tokens can only create into the workspace triage Inbox (find its id via list_projects with includeInbox: true); workspace-scoped tokens can create anywhere.

• create_project_updatewrite action

  Post a project status update \u2014 a health snapshot + markdown note on the project timeline; also stamps the project's current health. Check list_project_updates first so the note reflects real change. Requires the write:projects PAT scope.

• execute_custom_viewwrite action

  Run a saved view: return the issues matching its persisted filters (same output as list_issues). Paginated. Find view ids via list_custom_views. Requires the PRO+ custom-views plan feature.

• get_agent_session_activity

  Get the chronological activity feed for one agent session (thoughts, tool calls, elicitations, responses, errors). Cursor-paginated, oldest-first within the page; pass the returned cursor back to load more.

• get_guidance

  Get agent guidance for the workspace \u2014 conventions, PR checklists, review rules a team configured. Read this before starting work; pass projectId once you know which project the issue belongs to for project-specific guidance too.

• get_issue

  Get detailed info about a specific issue

• get_issue_context

  Full pre-work briefing for one issue in a single call: the issue core (status, assignee, linked PRs), its most recent comments, and its recent agent activity. Use this BEFORE starting work on an issue; use the lighter get_issue for a quick look.

• get_my_queue

  The calling agent's own work queue \u2014 issues delegated to you, oldest first (FIFO); poll it to find waiting work. Requires an agent bearer token (hsa_); PAT-authenticated servers get a 403 \u2014 use list_issues / list_agent_sessions instead.

• get_playbook

  Fetch a single playbook by name and return its full step-by-step body. Use list_playbooks first to discover available names.

• get_project_insights

  Analytics for a single project: burndown (remaining-issue series + agent/human completion split), velocity per sprint, and cycle-time percentiles (p50/p75/p95) with agent-vs-human medians. Requires the insights plan feature.

• get_setup_status

  Report whether this machine has saved Hiveship preferences, which values are set, and where they came from. Call this if you are unsure whether to run setup.

• get_workspace_insights

  Workspace-wide analytics: agent-vs-human work share, weekly throughput, open-issue load per assignee, agent-ops health (run-failure + PR-merge rates), and what needs attention (stale/unassigned issues, open PRs). Optional from/to bound the window. Requires the insights plan feature.

• link_pr

  Link a pull request to an issue after opening it \u2014 the PR shows on the issue page and, while open, the review queue. One-directional: if the PR description does not already carry the issue URL, edit it in too. Idempotent: re-linking the same provider + number refreshes it. Agent tokens need a live session on the issue.

• list_agent_sessions

  List agent work sessions (live + historical) with status, token usage, and model. Filter by status or agentId; paginated. Use get_agent_session_activity to see what a specific session actually did.

• list_comments

  List an issue\u2019s comment thread (author, date, body; one level of replies nested), oldest first. Long bodies are truncated with an explicit marker; raise limit for more.

• list_custom_views

  List the calling user's saved views (issue filters) for a project \u2014 each view\u2019s name, id, and filters. Run one with execute_custom_view. Requires the PRO+ custom-views plan feature.

• list_issues

  List issues in a project. Optional filters: status/priority/assignee/label arrays, sprint (or currentSprint), delegateType (HUMAN vs AGENT), date ranges, free-text query, sorting; paginated.

• list_labels

  List all labels in a Hiveship workspace. Labels can be attached to issues via update_issue.

• list_members

  List the human members of a workspace with their role (OWNER / ADMIN / MEMBER / VIEWER). Use the returned `user id` when assigning an issue to a person via update_issue. (Email is not exposed to agent callers.)

• list_notifications

  List the calling user's notifications in a workspace (issue assignments, status changes, comment replies, agent-session outcomes, PR links). Pass `type: "COMMENT_REPLY"` to see only mentions/replies, or `unreadOnly: true` for the unread inbox.

• list_playbooks

  List the named playbooks configured for a Hiveship workspace \u2014 reusable, versioned conventions a team saved (e.g. "how we fix flaky tests here"). Returns each playbook name, its "when to use" hint, and version, but NOT the body. Fetch a full playbook with get_playbook once you know its name.

• list_project_updates

  Read a project status-update timeline (newest first). Use this before posting a new update so the draft reflects what actually changed since the last one. Long update bodies are truncated with an explicit marker; raise limit for more.

• list_projects

  List the projects in a Hiveship workspace (paginated). Pass includeInbox: true to also surface the triage Inbox (hidden by default) when you need its id to file triage issues.

• list_recent_activity

  List the workspace audit feed \u2014 who did what (including which MCP tool or agent acted) and the entity touched. Answers "what changed recently". Requires an OWNER or ADMIN PAT.

• list_sprints

  List sprints in a project (planning, active, and completed) with issue + story-point completion counts. Pass `currentOnly: true` to get just the active sprint. Requires the PRO+ sprint-management plan feature.

• list_workflow_statuses

  List the workflow statuses available in a workspace (e.g. BACKLOG / TODO / IN_PROGRESS / DONE plus any custom statuses). Use the returned `value` as the `status` argument when creating, updating, or filtering issues.

• list_workspaces

  List the workspaces the current user belongs to (ids, names, plan tier, member/agent counts). Use the returned `id` as `workspaceId` for other tools. Requires a spanning PAT (hsp_); workspace-scoped tokens are rejected here.

• post_activitywrite action

  Post a structured activity event to an agent session. `kind` is one of thought / tool_use / elicitation / response / error. `content` shape varies by kind: thought/response = { text }, tool_use = { toolName, args, result?, durationMs? }, elicitation = { question }, error = { message, stack? }.

• search_issues

  Search a workspace by text. Matches issue titles, issue numbers (e.g. "42" or "ENG-42"), project names, and comment bodies. Comment hits link back to their parent issue.

• update_issuewrite action

  Update an issue \u2014 pass only the fields to change. null clears assigneeId / storyPoints / dueDate / sprintId ([] clears labelIds); description cannot be cleared, omit to keep it.

• update_sessionwrite action

  Update your own agent work session \u2014 move it through its lifecycle (QUEUED \u2192 WORKING \u2192 WAITING_INPUT \u2192 COMPLETED/ERRORED) and report modelUsage, tokenUsage, modelUsed, or externalUrls. Report your usage on the COMPLETED/ERRORED call: nothing else records it, and a session that never reports is shown on the story as unreported, not as zero cost. Requires an agent bearer token (h

• Code scan3 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancerepository not readable: repo not found3/15
• Maintainer identityno repository or website to verify2/10

Hiveship: common questions

Is Hiveship MCP server safe?

With care: it is graded C, so read the findings first (55/100). Read the Hiveship safety report

How do I install Hiveship?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does Hiveship need an API key?

Yes. The registry entry asks for HIVESHIP_API_TOKEN.

Is Hiveship maintained?

The latest release is v0.7.0.