A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
Nothing to run from here
Hiveship is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
8
downloads a day
local
runs on your machine
367
downloads in 30d
What it does
MCP server for AI coding agents to interact with the Hiveship issue tracker
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'HIVESHIP_API_URL=${HIVESHIP_API_URL}' --env 'HIVESHIP_API_TOKEN=${HIVESHIP_API_TOKEN}' --transport stdio hiveship-mcp '--' npx -y @hiveship/mcp-server
# 2 — ask your agent for something these tools do
# list_projects, list_project_updates, create_project_update and 30 more
It needs HIVESHIP_API_URL, HIVESHIP_API_TOKEN: this reads them from your environment, so export them first.
Hiveship costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
SOAll 1 server
SorcRR1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Hiveship as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads HIVESHIP_API_URL (Base URL of the Hiveship API, e.g. https://hiveship.app/api), HIVESHIP_API_TOKEN (Bearer token — agent token (hsa_...) or personal access token (hsp_...)) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx HIVESHIP_API_URL …, setx HIVESHIP_API_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'HIVESHIP_API_URL=${HIVESHIP_API_URL}' --env 'HIVESHIP_API_TOKEN=${HIVESHIP_API_TOKEN}' --transport stdio hiveship-mcp '--' npx -y @hiveship/mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: HIVESHIP_API_URL — Base URL of the Hiveship API, e.g. https://hiveship.app/api; HIVESHIP_API_TOKEN — Bearer token — agent token (hsa_...) or personal access token (hsp_...). You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
33 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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.
No parameter schema on file.
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.
No parameter schema on file.
Post a project status update \u2014 a health snapshot + markdown note on the project timeline; also stamps the project
No parameter schema on file.
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.
No parameter schema on file.
Get detailed info about a specific issue
No parameter schema on file.
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.
No parameter schema on file.
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.
No parameter schema on file.
No parameter schema on file.
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.
No parameter schema on file.
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.
No parameter schema on file.
Add a comment to an issue
No parameter schema on file.
Post a structured activity event to an agent session.
No parameter schema on file.
Search a workspace by text. Matches issue titles, issue numbers (e.g.
No parameter schema on file.
List all labels in a Hiveship workspace. Labels can be attached to issues via update_issue.
No parameter schema on file.
List the workspaces the current user belongs to (ids, names, plan tier, member/agent counts). Use the returned
No parameter schema on file.
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.
No parameter schema on file.
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.
No parameter schema on file.
List sprints in a project (planning, active, and completed) with issue + story-point completion counts. Pass
No parameter schema on file.
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.
No parameter schema on file.
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.
No parameter schema on file.
The calling agent
No parameter schema on file.
No parameter schema on file.
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.
No parameter schema on file.
List the named playbooks configured for a Hiveship workspace \u2014 reusable, versioned conventions a team saved (e.g.
No parameter schema on file.
Fetch a single playbook by name and return its full step-by-step body. Use list_playbooks first to discover available names.
No parameter schema on file.
List the human members of a workspace with their role (OWNER / ADMIN / MEMBER / VIEWER). Use the returned
No parameter schema on file.
List the calling user\
No parameter schema on file.
List the workflow statuses available in a workspace (e.g. BACKLOG / TODO / IN_PROGRESS / DONE plus any custom statuses). Use the returned
No parameter schema on file.
List the calling user
No parameter schema on file.
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.
No parameter schema on file.
List the workspace audit feed \u2014 who did what (including which MCP tool or agent acted) and the entity touched. Answers
No parameter schema on file.
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.
No parameter schema on file.
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
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Hiveship or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 0.8.0 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest4656bd11f9cd1809115d7334b55f8ad0d63901ddeac35da85d8c81ff63e8ef4e
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (33 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
1 of the 33 recovered tools are registered only when !isAgentToken holds (dist/cli.js:5750) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 28.
1 of the 33 recovered tools are registered only when !isAgentToken holds (dist/cli.js:5759) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 28.
3 of the 33 recovered tools are registered only when !isAgentToken holds (dist/cli.js:5763) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 28.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
28 tools are registered unconditionally · (1) 1 more only when !isAgentToken holds (dist/cli.js:5750) · (2) 1 more only when !isAgentToken holds (dist/cli.js:5759) · (3) 3 more only when !isAgentToken holds (dist/cli.js:5763) — typically when a key or option is configured. All 33 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_projects | no tags | |
| list_project_updates | no tags | |
| create_project_update | no tags | |
| list_issues | no tags | |
| get_issue | no tags | |
| create_issue | external-sink | external-sink: keyword "create_issue" |
| update_issue | state-write | state-write: declares destructiveHint: true |
| link_pr | no tags | |
| get_issue_context | no tags | |
| list_comments | no tags | |
| add_comment | no tags | |
| post_activity | no tags | |
| search_issues | no tags | |
| list_labels | no tags | |
| list_workspaces conditional (1) | no tags | |
| get_workspace_insights | no tags | |
| get_project_insights | no tags | |
| list_sprints | no tags | |
| list_agent_sessions | no tags | |
| get_agent_session_activity | no tags | |
| get_my_queue | no tags | |
| update_session | state-write | state-write: declares destructiveHint: true |
| get_guidance | no tags | |
| list_playbooks | untrusted-input | untrusted-input: keyword "fetch" |
| get_playbook | untrusted-input | untrusted-input: keyword "fetch" |
| list_members | no tags | |
| list_notifications conditional (2) | no tags | |
| list_workflow_statuses | no tags | |
| list_custom_views conditional (3) | no tags | |
| execute_custom_view conditional (3) | no tags | |
| list_recent_activity conditional (3) | no tags | |
| get_setup_status | no tags | |
| configure | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest4656bd11f9cd1809
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.8.0. Pin a release below and the command asks for exactly that one.
0.8.0
25 Sep 2026
latestNo release note was published with this version.
0.7.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Hiveship can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.